An e-commerce teaching system and method based on ADDIE

Abstract

This invention provides an e-commerce teaching system and method based on ADDIE, relating to the field of e-commerce service technology. The system includes: an acquisition unit for acquiring first interactive data; a capability analysis unit for obtaining corresponding capability analysis results based on the first interactive data; a course matching unit for performing course recommendation analysis based on the capability analysis results to conduct course testing and obtain simulated test results; and a teaching evaluation unit for matching and detecting the second interactive data during the course learning process with the business capabilities corresponding to each business project type. When the second interactive data matches the target business capability, a comprehensive evaluation of the learning effect is performed based on the second interactive data and the simulated test results corresponding to the target learning course group to update the advanced courses for continued teaching. The system and method of this invention can ensure the reliability of students' knowledge and skills mastery during e-commerce learning.

Description

Technical Field

[0001] This invention relates to the field of e-commerce service technology, and in particular to an e-commerce teaching system and method based on ADDIE. Background Technology

[0002] ADDIE is a systematic methodology for developing instruction. The five letters of ADDIE stand for Analysis, Design, Development, Implementation, and Evaluation. Analysis involves analyzing the behavioral goals, tasks, audience, environment, performance objectives, etc., that the instruction aims to achieve. Design involves designing the curriculum for the upcoming instructional activities. Development involves writing course content, designing layouts, and testing based on the designed curriculum framework and assessment methods. Implementation involves carrying out the developed curriculum in instruction and providing support for implementation. Evaluation involves assessing the completed instructional course and the learning outcomes for the audience.

[0003] In existing e-commerce retail business service practices, a large number of order failures and customer churn are caused by service personnel's insufficient proficiency in business operations. Moreover, the training of service personnel is ineffective because it is impossible to accurately identify the different abilities of each service personnel. Furthermore, the training is often based solely on simulated courses, which differ significantly from real-world practice scenarios and make it difficult for the learning outcomes to meet the practical ability requirements of service personnel. Summary of the Invention

[0004] This invention provides an e-commerce teaching system and method based on ADDIE to address the problems of insufficient proficiency of service personnel in business operations, leading to a large number of order failures, poor customer experience, and customer loss. Furthermore, the training of service personnel suffers from poor results due to the inability to accurately identify the differentiated abilities of each individual, and the reliance on simulated courses and training, which differs significantly from real-world scenarios, makes it difficult for the learning outcomes to meet the practical skill requirements of service personnel.

[0005] To achieve the above and other related objectives, this invention provides an e-commerce teaching system based on ADDIE, comprising: an acquisition unit for acquiring first interaction data between students and consumers during practical e-commerce retail operations; a capability analysis unit for performing e-commerce retail capability analysis corresponding to different behavioral perspectives based on the first interaction data, and obtaining corresponding capability analysis results; a course matching unit for performing course recommendation analysis based on the capability analysis results, generating target learning course groups corresponding to the target business capabilities, and generating simulated test content during the course learning process of the target learning course groups for course testing, and obtaining simulated test results; and a teaching evaluation unit for matching and detecting the second interaction data during the course learning process with the business capabilities corresponding to each business project type. When the second interaction data matches the target business capability, a comprehensive evaluation of the learning effect is performed based on the second interaction data and the simulated test results corresponding to the target learning course groups, so as to update the advanced courses of the target learning course groups for continued teaching.

[0006] In one embodiment of the present invention, the capability analysis result includes the missing capabilities and corresponding missing capability values ​​from the student's perspective; the capability analysis unit includes: an item extraction subunit, used to extract the business item type from the first interaction data; a decomposition subunit, used to decompose the first interaction data into a behavior sequence corresponding to the student's perspective according to the business item type, to obtain actual behavior sequence data, the actual behavior sequence data including actual behavior sub-data corresponding to multiple student behavior items; a quantification comparison subunit, used to perform multi-dimensional quantification comparison of the actual behavior sequence data and the ideal behavior sequence data corresponding to the business item type for each student behavior item, to obtain the cumulative capability deviation value corresponding to each student behavior item; and a deviation judgment subunit, used to judge whether the cumulative capability deviation value exceeds the deviation threshold, if so, then the student behavior item corresponding to the cumulative capability deviation value is taken as the missing capability, and the cumulative capability deviation value is taken as the missing capability value.

[0007] In one embodiment of the present invention, the quantitative comparison subunit includes: an overall evaluation module, used to evaluate the overall distance between the actual behavior sequence data and the ideal behavior sequence data corresponding to the business project type, to obtain a first capability deviation cumulative value; a vectorization module, used to perform vectorization processing on the actual behavior subdata for each modality dimension, to obtain the actual modality vector corresponding to each modality dimension, wherein the modality dimensions include text modality dimension, voice modality dimension, video modality dimension, and behavior log modality dimension; a difference comparison module, used to compare the difference between the actual modality vector and the ideal modality vector under the corresponding modality dimension of the ideal behavior sequence data, to obtain the modality deviation; a deviation calculation module, used to obtain a second capability deviation cumulative value based on the modality deviation and the dimension transformation coefficient of the corresponding modality dimension; and a weighted fusion module, used to perform weighted fusion of the first capability deviation cumulative value and the second capability deviation cumulative value, to obtain the capability deviation cumulative value corresponding to each trainee behavior item; the calculation formula for the capability deviation cumulative value is: ;in, This indicates that the ability deviates from the cumulative value. This represents the actual behavior sub-data corresponding to each student behavior item in the actual behavior sequence data. This represents the ideal behavior sub-data corresponding to each trainee behavior item in the ideal behavior sequence data. This represents the actual modality vector for each modality dimension corresponding to each learner behavior item. This represents the ideal modality vector for each modality dimension corresponding to each learner behavior item. Represents the dimension transformation coefficient. This represents the first weighting factor corresponding to the deviation of the first capability from the cumulative value. This indicates the first weighting factor corresponding to the deviation of the second capability from the cumulative value. This represents the total number of actual behavior sub-data. This represents the total number of sub-data points representing the ideal behavior.

[0008] In one embodiment of the present invention, the capability analysis result includes the demand capability corresponding to the consumer's perspective and the corresponding demand capability value; the capability analysis unit further includes: an emotion detection subunit, used to perform emotion signal detection corresponding to the multimodal dimension from the consumer's perspective on the first interaction data; a first correlation analysis subunit, used to perform correlation analysis on the target actual behavior sub-data corresponding to the student behavior item before the negative emotion signal was generated and the modal data of the negative emotion signal in the corresponding modal dimension when the detected emotion signal is a negative emotion signal, to obtain a first correlation value; a behavior combination subunit, used to combine the historical actual behavior sub-data corresponding to several student behavior items before the target actual behavior sub-data with the target actual behavior sub-data in an ascending manner according to the student behavior items, to obtain actual behavior combination data; a second correlation analysis subunit, used to perform correlation analysis on the actual behavior combination data and the modal data of the negative emotion signal in the corresponding modal dimension, to obtain a second correlation value; and a capability analysis subunit, used to perform demand capability analysis based on the first correlation value and the second correlation value to obtain the demand capability corresponding to the consumer's perspective and the corresponding demand capability value.

[0009] In one embodiment of the present invention, the capability analysis subunit includes: a correlation difference calculation module, used to calculate the difference between two adjacent correlation values ​​corresponding to each trainee behavior item based on a first correlation value and a second correlation value, to obtain the correlation increment; a curve construction module, used to establish a correlation increment trend curve over time based on the correlation increment; a change detection module, used to detect the change amplitude of the change trend curve, and take the trainee behavior item corresponding to the start time of the sudden change in the change trend curve up to before the negative emotional signal subsides as the demand capability from the consumer's perspective; and a capability calculation module, used to obtain the demand capability value corresponding to each demand capability based on the initial value of the trainee behavior item corresponding to the demand capability for emotional coordination, the negative emotional intensity increment of the negative emotional signal corresponding to each trainee behavior item, and the capability demand index corresponding to the corresponding trainee behavior item.

[0010] In one embodiment of the present invention, the formula for calculating the demand capability value is as follows: ;in, Indicates the demand capacity value. This represents the initial value of the capacity requirement. This indicates the increment of negative emotional intensity corresponding to the trainee's behavioral item. This indicates the competency requirement index corresponding to each trainee's behavioral item. This indicates the increased demand capacity corresponding to a failed order. This represents the demand capacity loss value corresponding to a successful order. Indicates the order status, with a value of 0 or 1. This indicates that the order status is "order successful". This indicates that the order status is "order failed".

[0011] In one embodiment of the present invention, the capability analysis results include the missing capabilities and corresponding missing capability values ​​from the student's perspective, and the required capabilities and corresponding required capability values ​​from the consumer's perspective; the course matching unit includes: a capability screening subunit, used to perform capability overlap screening based on missing capabilities and required capabilities to obtain target business capabilities, the target business capabilities including overlapping capabilities and independent capabilities; a capability fusion subunit, used to perform weighted fusion of the missing capability values ​​corresponding to the missing capabilities and the required capability values ​​corresponding to the required capabilities among the overlapping capabilities to obtain a fused capability value; a capability combination subunit, used to freely combine overlapping capabilities and independent capabilities to obtain capability combinations; and a course search subunit, used to search the course knowledge base based on the capability combinations, generate target learning course groups corresponding to the target business capabilities, and generate simulated test content during the course learning process of the target learning course groups to conduct course testing and obtain simulated test results.

[0012] In one embodiment of the present invention, the course search subunit includes: a library search module, used to search the course knowledge base according to the ability combination to obtain a set of learning course groups under different combination forms; an ability comparison module, used to compare the ability improvement value of each ability corresponding to each learning course group in the learning course group set with the fusion ability value corresponding to the overlapping ability and the independent ability value corresponding to the independent ability in the ability combination to obtain available learning course groups whose fusion ability value and independent ability value are both less than the corresponding ability improvement value; a comprehensive calculation module, used to perform a comprehensive calculation of the ability improvement difficulty of the available learning course groups to obtain the comprehensive learning difficulty corresponding to each available learning course group; a course selection module, used to select the available learning course group with the lowest comprehensive learning difficulty as the target learning course group; a sorting module, used to generate a target learning course ranking according to the correlation between overlapping abilities and independent abilities in the target learning course group; and a course testing module, used to generate corresponding simulated test content based on the order of the target learning course ranking and the completion progress of each target learning course to conduct course testing and obtain simulated test results.

[0013] In one embodiment of the present invention, the teaching evaluation unit includes: a capability detection subunit, used to detect business capabilities in the second interactive data during the course learning process to obtain a second business capability; a capability improvement calculation subunit, used to calculate the difference between the learning capability value corresponding to the second business capability and the historical capability value corresponding to the target business capability when the second business capability is consistent with the corresponding target business capability, to obtain a capability improvement value; a comprehensive improvement calculation subunit, used to merge the capability improvement value with the simulated improvement value corresponding to the simulated test result to obtain a comprehensive improvement value; and an improvement judgment subunit, used to judge whether the comprehensive improvement value meets the improvement threshold requirement of the target learning course corresponding to the target learning course in the target learning course group. If it does not meet the requirement, the target learning course group is updated based on the upgradable value between the comprehensive improvement value and the improvement threshold, and advanced courses with corresponding learning difficulty are extracted for continued teaching. The upgradable value is negatively correlated with the learning difficulty of the advanced courses.

[0014] To achieve the above and other related objectives, this invention also provides an e-commerce teaching method based on ADDIE, comprising: acquiring first interaction data between students and consumers during practical e-commerce retail operations; performing e-commerce retail capability analysis corresponding to different behavioral perspectives based on the first interaction data to obtain corresponding capability analysis results; performing course recommendation analysis based on the capability analysis results to generate target learning course groups corresponding to the target business capabilities, and generating simulated test content during the course learning process of the target learning course groups for course testing to obtain simulated test results; matching and detecting the second interaction data during the course learning process with the business capabilities corresponding to each business project type; when the second interaction data matches the target business capability, performing a comprehensive evaluation of the learning effect based on the second interaction data and the simulated test results corresponding to the target learning course groups to update the advanced courses of the target learning course groups for continued teaching.

[0015] The beneficial effects of this invention are as follows: This invention proposes an e-commerce teaching system and method based on ADDIE. By acquiring first interaction data and analyzing student capabilities from different behavioral perspectives based on this data, it determines the student's capabilities from multiple angles, such as the student's own perspective and the consumer's perspective. Subsequently, based on the determined capability analysis results from each behavioral angle, a comprehensive analysis of learning course recommendations is performed to derive a target learning course group that meets the student's current actual needs. Furthermore, during course recommendation, corresponding simulated test content is generated based on the learning progress of the target learning course group for course testing, and the corresponding simulated test results are obtained. To better reflect the learning outcomes of students, interactive data can be acquired again during the learning process. This second interactive data can be matched with the business capabilities corresponding to each business project type. If the business capability matched by the second interactive data is the target business capability corresponding to the first interactive data, the corresponding simulation test results can be directly retrieved and compared with the second interactive data for a comprehensive evaluation of the learning outcome. This determines the current learning effectiveness of the student, allowing for the updating and arrangement of advanced courses based on the student's learning progress. Through this method, not only can the student's true mastery of e-commerce learning in the retail industry be understood, but also suitable courses can be selected for advanced teaching based on the student's learning outcomes, ensuring the reliability of the student's knowledge and skills acquired during e-commerce learning. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0017] In the attached diagram: Figure 1 The structural block diagram of the ADDIE-based e-commerce teaching system provided in the embodiments of the present invention; Figure 2 The diagram shown is a flowchart of an e-commerce teaching method based on ADDIE provided in an embodiment of the present invention.

[0018] The attached figures are labeled as follows: Unit 111: Acquisition; Unit 112: Competency Analysis; Unit 113: Curriculum Matching; Unit 114: Teaching Assessment. Detailed Implementation

[0019] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0021] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0022] Please see Figure 1 This invention provides an e-commerce teaching system based on ADDIE, comprising: an acquisition unit 111 for acquiring first interaction data between students and consumers during e-commerce retail business practice; a capability analysis unit 112 for performing e-commerce retail capability analysis corresponding to different behavioral perspectives based on the first interaction data, and obtaining corresponding capability analysis results; a course matching unit 113 for performing course recommendation analysis based on the capability analysis results, generating target learning course groups corresponding to the target business capabilities, and generating simulated test content during the course learning process of the target learning course groups for course testing, and obtaining simulated test results; and a teaching evaluation unit 114 for matching and detecting the second interaction data during the course learning process with the business capabilities corresponding to each business project type. When the second interaction data matches the target business capability, a comprehensive evaluation of the learning effect is performed based on the second interaction data and the simulated test results corresponding to the target learning course groups, so as to update the advanced courses of the target learning course groups for continued teaching.

[0023] As can be seen from the above, in the process of e-commerce teaching based on the retail industry, the acquisition unit 111 can obtain the first interaction data between students and consumers during students' practical e-commerce retail operations. After obtaining the first interaction data, the capability analysis unit 112 can analyze the student's capabilities from different behavioral perspectives based on the first interaction data, thereby determining the capability analysis results of the student from multiple perspectives, such as the student's own perspective and the consumer's perspective. Subsequently, the course matching unit 113 conducts a comprehensive analysis based on the determined capability analysis results from each behavioral perspective, thereby deriving a target learning course group that meets the current student's actual needs for learning. Furthermore, when recommending courses, corresponding simulated test content will be generated based on the learning progress of the target learning course group for course testing, and the corresponding simulated test results will be obtained. To better reflect the learning outcomes of students, the teaching assessment unit 114 will further acquire interactive data during the learning process. This second interactive data will be matched with the business capabilities corresponding to each business project type. If the business capability matched by the second interactive data is the target business capability corresponding to the first interactive data, the corresponding simulation test results can be directly retrieved and compared with the second interactive data for a comprehensive evaluation of the learning outcome. This will determine the current learning effectiveness of the student, allowing for the updating and arrangement of advanced courses based on the student's learning progress. Through this method, not only can we understand the student's true grasp of e-commerce learning in the retail industry, but we can also select suitable courses for advanced teaching based on the student's learning outcomes, ensuring the reliability of the student's knowledge and skills acquired during e-commerce learning.

[0024] It is worth noting that the first interaction data can include video modal data, voice modal data, text modal data, and behavior log modal data corresponding to each moment. For text modal data, this could be the dialogue text between learners and consumers in chat tools, comment sections, etc. Voice modal data could be voice recordings from live chat sessions, voice customer service, on-site communication, etc., containing voice data of learners and consumers, as well as emotional data during their voice expressions. Video modal data could be the video stream of communication between learners and consumers during on-site or live broadcasts, which could include dynamic data such as facial expressions and body language. For behavior log data, this could be the sequence of actions performed by learners in the e-commerce backend, such as page dwell time, click flow, and order processing actions.

[0025] In the ADDIE-based e-commerce teaching system of this invention, the capability analysis results include the missing capabilities and corresponding missing capability values ​​from the student's perspective, and the required capabilities and corresponding required capability values ​​from the consumer's perspective. That is, the missing capabilities and corresponding missing capability values ​​that students need to possess can be extracted from the first interaction data from the student's perspective, and the required capabilities and corresponding required capability values ​​of consumers can be extracted from the first interaction data from the consumer's perspective.

[0026] When analyzing and extracting the missing capabilities and corresponding missing capability values ​​from the perspective of the learner in the capability analysis results, the capability analysis unit 112 can be used for corresponding capability analysis processing. Specifically, the capability analysis unit 112 may further include: a project extraction subunit, used to extract the business project type from the first interaction data; a decomposition subunit, used to decompose the first interaction data into a behavior sequence corresponding to the learner's perspective based on the business project type, to obtain actual behavior sequence data, which includes actual behavior sub-data corresponding to multiple learner behavior items; a quantitative comparison subunit, used to perform multi-dimensional quantitative comparison of the actual behavior sequence data and the ideal behavior sequence data corresponding to the business project type for each learner behavior item, to obtain the cumulative capability deviation value corresponding to each learner behavior item; and a deviation judgment subunit, used to determine whether the cumulative capability deviation value exceeds the deviation threshold. If so, the learner behavior item corresponding to the cumulative capability deviation value is taken as a missing capability, and the cumulative capability deviation value is taken as a missing capability value.

[0027] First, the project extraction subunit extracts the business project type corresponding to the first interaction data. Then, the decomposition subunit analyzes the behavioral sequences corresponding to the learner's perspective within the first interaction data based on the business project type, identifying the actual behavioral sequence data. Next, the quantification comparison subunit performs a multi-dimensional quantification comparison of each learner's behavioral item with the ideal behavioral sequence data corresponding to the business project type, thus determining the cumulative deviation value of the learner's behavioral item. Finally, the deviation judgment subunit determines whether the cumulative deviation value exceeds a deviation threshold. If the cumulative deviation value is greater than the threshold, it indicates a significant deviation, and the learner's behavioral item corresponding to this cumulative deviation value can be considered a missing ability, with the cumulative deviation value itself becoming the missing ability value.

[0028] In the capability analysis unit 112, the quantitative comparison subunit may further include: an overall assessment module, used to assess the overall distance between the actual behavior sequence data and the ideal behavior sequence data corresponding to the business project type, to obtain a first capability deviation cumulative value; a vectorization module, used to perform vectorization processing on the actual behavior sub-data for each modality dimension, to obtain the actual modality vector corresponding to each modality dimension, the modality dimensions including text modality dimension, voice modality dimension, video modality dimension and behavior log modality dimension; a difference comparison module, used to compare the difference between the actual modality vector and the ideal modality vector under the corresponding modality dimension of the ideal behavior sequence data, to obtain the modality deviation; a deviation calculation module, used to obtain a second capability deviation cumulative value based on the modality deviation and the dimension transformation coefficient of the corresponding modality dimension; and a weighted fusion module, used to weightedly fuse the first capability deviation cumulative value and the second capability deviation cumulative value to obtain the capability deviation cumulative value corresponding to each trainee behavior item.

[0029] In calculating the cumulative capability deviation, the overall assessment module first evaluates the distance between the actual behavior sequence data and the ideal behavior sequence data corresponding to the business project type, thus determining the first cumulative capability deviation. Then, the vectorization module transforms the actual behavior sub-data into vectors for each modality dimension, obtaining the corresponding actual modality vectors for each modality dimension. Next, the difference comparison module compares the difference between the actual modality vectors and the ideal modality vectors for the corresponding modality dimensions of the ideal behavior sequence data, determining the modality deviation between the actual and ideal modality vectors. Furthermore, the deviation calculation module multiplies and accumulates the modality deviations for each modality dimension with the corresponding dimensional transformation coefficients to determine the second cumulative capability deviation. Finally, the weighted fusion module weights and fuses the first and second cumulative capability deviations using a weighting factor to calculate the cumulative capability deviation for each trainee behavior item. This method accurately describes the deviation of the actual behavior sequence data from the ideal behavior sequence data.

[0030] The formula for calculating the cumulative value of capability deviation is: ; in, This indicates that the ability deviates from the cumulative value. This represents the actual behavior sub-data corresponding to each student behavior item in the actual behavior sequence data. This represents the ideal behavior sub-data corresponding to each trainee behavior item in the ideal behavior sequence data. This represents the actual modality vector for each modality dimension corresponding to each learner behavior item. This represents the ideal modality vector for each modality dimension corresponding to each learner behavior item. Represents the dimension transformation coefficient. This represents the first weighting factor corresponding to the deviation of the first capability from the cumulative value. This indicates the first weighting factor corresponding to the deviation of the second capability from the cumulative value. This represents the total number of actual behavior sub-data. This represents the total number of sub-data points representing the ideal behavior. Dimension transformation coefficients for each modality dimension can be set based on empirical values. Additionally, the first and second weighting factors can also be pre-set based on empirical values.

[0031] When analyzing and extracting the demand capabilities and corresponding demand capability values ​​from the consumer perspective in the capability analysis results, the capability analysis unit 112 can be used for corresponding capability analysis processing. Specifically, the capability analysis unit 112 may further include: an emotion detection subunit, used to detect emotion signals corresponding to the multimodal dimensions from the consumer's perspective in the first interaction data; a first correlation analysis subunit, used to perform correlation analysis on the target actual behavior sub-data corresponding to the student behavior items before the negative emotion signal was generated and the modal data of the negative emotion signal in the corresponding modal dimension when the detected emotion signal is a negative emotion signal, to obtain a first correlation value; a behavior combination subunit, used to combine the historical actual behavior sub-data corresponding to several student behavior items before the target actual behavior sub-data with the target actual behavior sub-data in an ascending manner according to the student behavior items, to obtain actual behavior combination data; a second correlation analysis subunit, used to perform correlation analysis on the actual behavior combination data and the modal data of the negative emotion signal in the corresponding modal dimension, to obtain a second correlation value; and a capability analysis subunit, used to perform demand capability analysis based on the first correlation value and the second correlation value, to obtain the demand capability corresponding to the consumer's perspective and the corresponding demand capability value.

[0032] When analyzing demand capabilities and corresponding demand capability values, the capability analysis unit 112 can use the emotion detection subunit to detect the emotional signals of consumers in the first interaction data across multiple modal dimensions such as text, video, and voice, thereby detecting the intensity and positive / negative values ​​of the emotional signals. When the emotional signal is negative, the first correlation analysis subunit can perform correlation analysis between the target actual behavior sub-data corresponding to the student behavior item before the negative emotional signal and the modal data of the negative emotional signal in the corresponding modal dimension to determine the first correlation value between the target actual behavior sub-data and the corresponding modal data. Simultaneously, to determine the specific cause of the negative emotional signal, the behavior combination subunit can sequentially combine the historical actual behavior sub-data corresponding to several student behavior items preceding the target actual behavior sub-data with the target actual behavior sub-data in an ascending order along the historical time direction, forming actual behavior combination data. This actual behavior combination data is then subjected to correlation analysis between the second correlation analysis subunit and the modal data of the negative emotional signal in the corresponding modal dimension to obtain the second correlation value between each actual behavior combination data and the corresponding modal data. Finally, by using the curves formed by the first and second correlation values ​​through the capability analysis sub-unit, we can accurately analyze the consumer's demand capability and corresponding demand capability value under the drive of negative emotions.

[0033] In the capability analysis unit 112, the capability analysis subunit may further include: a correlation difference calculation module, used to calculate the difference between two adjacent correlation values ​​corresponding to each student behavior item based on the first correlation value and the second correlation value, to obtain the correlation increment; a curve construction module, used to establish a trend curve of the correlation increment over time based on the correlation increment; a change detection module, used to detect the change amplitude of the trend curve, and take the student behavior item corresponding to the start time of the sudden change in the trend curve to the time before the negative emotional signal fades as the demand capability from the consumer's perspective; and a capability calculation module, used to obtain the demand capability value corresponding to each demand capability based on the initial value of the demand capability for emotional coordination capability of the student behavior item corresponding to the demand capability, the negative emotional intensity increment of the negative emotional signal corresponding to each student behavior item, and the capability demand index corresponding to the corresponding student behavior item.

[0034] When calculating the required capability value, the correlation difference calculation module first calculates the correlation difference between the first and second correlation values, and between adjacent second correlation values, to obtain the incremental correlation between each pair of values. Then, the curve construction module uses the incremental correlation over time to construct a trend curve of the correlation increment. Next, the change detection module detects the magnitude of change in the trend curve. When a sudden increase in the correlation increment is detected at a certain moment, the starting point corresponding to this sudden change can be taken as the student behavior item before the negative emotional signal fades—that is, the student behavior item before the emotional signal intensity reaches its maximum value—and used as the required capability from the consumer's perspective, i.e., the capability required by the student. Finally, the capability calculation module uses the initial value of the student behavior item's ability to coordinate emotions, the increment of negative emotional signal intensity for each student behavior item, and the capability requirement index corresponding to the corresponding student behavior item, to comprehensively analyze the demand intensity of each capability using the required capability value calculation formula, thereby determining the required capability value for each capability.

[0035] Preferably, the formula for calculating the demand capacity value can be expressed as: ; in, Indicates the demand capacity value. This represents the initial value of the capacity requirement. This indicates the increment of negative emotional intensity corresponding to the trainee's behavioral item. This indicates the competency requirement index corresponding to each trainee's behavioral item. This indicates the increased demand capacity corresponding to a failed order. This represents the demand capacity loss value corresponding to a successful order. Indicates the order status, with a value of 0 or 1. This indicates that the order status is "order successful". This indicates that the order status is "order failed." (Increase in negative sentiment intensity) This can be obtained by subtracting the second negative emotional intensity of the previous learner's behavior item from the first negative emotional intensity of the current learner's behavior item. The ability requirement index corresponding to the learner's behavior item can be pre-defined based on experience values. The increased ability requirement corresponding to order failure... Demand capacity loss value corresponding to successful order It also refers to the increment or decrement of the initial value of the capability requirement based on experience.

[0036] Specifically, when When the demand capacity value is calculated, the formula can be expressed as follows: And when When the demand capacity value is calculated, the formula can be expressed as follows: .

[0037] When calculating the first or second correlation value, one can query the emotion-induced data of the actual behavior sub-data, compare the correlation between the emotions generated by the emotion-induced data and the corresponding emotions in the modal data, and determine the corresponding correlation value based on the weight of each emotion-induced data. The formula can be expressed as follows: , This represents the ratio of the first correlation value to the second correlation value. This indicates the degree of correlation between the emotion generated by each emotion-inducing data point and the corresponding emotion in the modal data. This represents the weight corresponding to each emotion-induced data point.

[0038] In the ADDIE-based e-commerce teaching system of the present invention, the course matching unit 113 may further include: a capability screening subunit, used to screen for capability overlap based on missing capabilities and required capabilities to obtain target business capabilities, wherein the target business capabilities include overlapping capabilities and independent capabilities; a capability fusion subunit, used to perform weighted fusion of the missing capability value corresponding to the missing capability in the overlapping capabilities and the required capability value corresponding to the required capability to obtain a fused capability value; a capability combination subunit, used to freely combine overlapping capabilities and independent capabilities to obtain capability combinations; and a course search subunit, used to search the course knowledge base based on the capability combinations, generate target learning course groups corresponding to the target business capabilities, and generate simulated test content during the course learning process of the target learning course groups to conduct course tests and obtain simulated test results.

[0039] In the process of developing and testing target-based learning course groups, the ability screening sub-unit can be used to identify overlapping abilities between missing and required abilities, thus deriving overlapping and independent abilities. For overlapping abilities, the ability fusion sub-unit can be used to weight and fuse the missing ability value corresponding to the missing ability with the required ability value corresponding to the required ability. The resulting fused ability value can better reflect the importance of overlapping abilities from different behavioral perspectives, ensuring a high degree of fit between learning courses and overlapping abilities, and improving the teaching effectiveness of students selecting target-based learning course groups based on fused ability values. The formula for calculating the fused ability value can be expressed as follows: ,in, This indicates the first weight corresponding to the deviation of the ability from the cumulative value. This represents the second weight corresponding to the required capability value. After determining the integration capability value, overlapping and independent capabilities can be freely combined through the capability combination sub-unit to form different capability combinations. Then, the course search sub-unit searches the course knowledge base based on the capability combinations to generate the optimal target learning course group corresponding to the target business capability. During the course learning process of the target learning course group, corresponding simulated test content is generated based on each target learning course to conduct course testing and obtain simulated test results.

[0040] In the course matching unit 113, the course search subunit may further include: a library search module, used to search the course knowledge base according to the ability combination to obtain a set of learning course groups under different combination forms; an ability comparison module, used to compare the ability improvement value of each ability corresponding to each learning course group in the learning course group set with the fusion ability value corresponding to the overlapping ability in the ability combination and the independent ability value corresponding to the independent ability, to obtain available learning course groups whose fusion ability value and independent ability value are both less than the corresponding ability improvement value; a comprehensive calculation module, used to perform a comprehensive calculation of the ability improvement difficulty of the available learning course groups to obtain the comprehensive learning difficulty corresponding to each available learning course group; a course selection module, used to select the available learning course group with the lowest comprehensive learning difficulty as the target learning course group; a sorting module, used to generate a ranking of target learning courses according to the correlation between overlapping abilities and independent abilities in the target learning course group; and a course testing module, used to generate corresponding simulated test content based on the ranking of target learning courses and the completion progress of each target learning course to conduct course testing and obtain simulated test results.

[0041] In the process of constructing target learning course groups and conducting simulated test content for course testing, the library search module can first search the course knowledge base using different ability combinations to obtain a set of learning course groups with different combinations. Then, the ability comparison module compares the ability improvement values ​​of each ability in each learning course group with the fusion ability values ​​corresponding to overlapping abilities and the independent ability values ​​corresponding to independent abilities in the ability combinations. This allows for the selection of usable learning course groups where both the fusion ability value and the independent ability value are less than the corresponding ability improvement value. For multiple usable learning course groups, the comprehensive calculation module can further calculate the overall learning difficulty of each usable learning course group by performing a comprehensive calculation of the ability improvement difficulty. Furthermore, the course selection module selects the available learning course group with the lowest overall learning difficulty as the target learning course group. Then, the sorting module utilizes the correlation between overlapping and independent abilities within the target learning course group to adjust the order of the individual target learning courses, thereby generating a target learning course ranking. For example, the ranking can be generated based on the learning sequence relationships between overlapping abilities, independent abilities, or between overlapping and independent abilities. Finally, the course testing module generates corresponding simulated test content upon completion of each target learning course, according to the order of the target learning course ranking. The simulated test results are then statistically analyzed to represent the student's simulated mastery of the course knowledge.

[0042] In the ADDIE-based e-commerce teaching system of the present invention, the teaching evaluation unit 114 may further include: a capability detection subunit, used to detect business capabilities in the second interactive data during the course learning process to obtain a second business capability; a capability improvement calculation subunit, used to calculate the difference between the learning capability value corresponding to the second business capability and the historical capability value corresponding to the target business capability when the second business capability is consistent with the corresponding target business capability, to obtain a capability improvement value; a comprehensive improvement calculation subunit, used to merge the capability improvement value with the simulated improvement value corresponding to the simulated test result to obtain a comprehensive improvement value; and an improvement judgment subunit, used to judge whether the comprehensive improvement value meets the improvement threshold requirement of the target learning course corresponding to the target learning course group. If it does not meet the requirement, the target learning course group is updated based on the upgradable value between the comprehensive improvement value and the improvement threshold, and advanced courses with corresponding learning difficulty are extracted for continued teaching. The upgradable value is negatively correlated with the learning difficulty of the advanced courses.

[0043] When comprehensively evaluating learning effectiveness using the second interactive data and simulation test results, the capability detection subunit can first use the same method as the first interactive data to detect business capabilities in the second interactive data during the course learning process, thereby deriving the corresponding second business capabilities. Then, the capability improvement calculation subunit compares the existing second business capabilities with the corresponding target business capabilities. When they match, the difference between the learning capability value corresponding to the second business capability (e.g., overlapping or independent capabilities) and the historical capability value corresponding to the target business capability is calculated to obtain the capability improvement value. Next, the comprehensive improvement calculation subunit merges the capability improvement value with the simulated improvement value corresponding to the simulation test results to calculate the corresponding comprehensive improvement value. Finally, the improvement judgment subunit determines whether the comprehensive improvement value meets the improvement threshold requirement of the target learning course group. If the comprehensive improvement value is less than the improvement threshold, the course is upgraded to an advanced course. Furthermore, when providing advanced courses, the system can generate an appropriate difficulty value for the advanced courses based on the potential improvement value between the overall improvement value and the improvement threshold. Based on this appropriate difficulty value, the system can select advanced courses with corresponding learning difficulties to update the target learning course group for continued teaching, so as to ensure that the teaching of advanced courses can better match the learning ability of students.

[0044] The formula for calculating the overall improvement value can be expressed as: ; in, Indicates the ability enhancement value. This represents the learning ability value. Indicates historical ability value, Indicates the overall improvement value. This represents the simulated boost value. This indicates the first boost weight corresponding to the ability boost value. This represents the second boost weight corresponding to the simulated boost value. This first and second boost weight can be determined based on empirical values.

[0045] The formula for calculating the adaptation difficulty value can be expressed as: ; in, This indicates the difficulty level of the adaptation. Indicates the potential upside value. This indicates raising the threshold. This represents the benchmark increase value, which can be obtained from empirical values.

[0046] Please see Figure 2 The present invention also provides an e-commerce teaching method based on ADDIE, comprising: Step S10: Obtain the first interaction data between the trainee and the consumer during the practical operation of e-commerce retail business; Step S20: Analyze e-commerce retail capabilities based on the first interaction data, corresponding to different behavioral perspectives, and obtain the corresponding capability analysis results; Step S30: Based on the capability analysis results, perform course recommendation analysis, generate target learning course groups corresponding to the target business capabilities, and generate simulated test content during the course learning process of the target learning course groups to conduct course testing and obtain simulated test results; Step S40: Match the second interactive data during the course learning process with the business capabilities corresponding to each business project type. When the second interactive data matches the target business capability, conduct a comprehensive evaluation of the learning effect based on the second interactive data and the simulation test results corresponding to the target learning course group, and update the advanced courses of the target learning course group for continued teaching.

[0047] In summary, the e-commerce teaching system and method based on ADDIE disclosed in this invention acquires first interaction data and analyzes student capabilities from different behavioral perspectives based on this data, thereby determining the student's capability analysis results from multiple angles, such as the student's own perspective and the consumer's perspective. Subsequently, a comprehensive analysis of learning course recommendations is performed based on the determined capability analysis results from each behavioral perspective, thereby deriving a target learning course group that meets the current student's actual needs for learning. Furthermore, during course recommendation, corresponding simulated test content is generated based on the learning progress of the target learning course group for course testing, and the corresponding simulated test results are obtained. To better reflect the learning outcomes of students, interactive data can be acquired again during the learning process. This second interactive data is then matched with the business capabilities corresponding to each business project type. If the business capability matched by the second interactive data is the target business capability corresponding to the first interactive data, the corresponding simulation test results can be directly retrieved and compared with the second interactive data for a comprehensive evaluation of the learning outcome. This determines the current learning effectiveness of the student, allowing for the updating and arrangement of advanced courses based on the student's learning progress. Through this method, not only can the true mastery of e-commerce knowledge related to the retail industry be understood, but also suitable courses can be selected for advanced teaching based on the student's learning outcomes, ensuring the reliability of the knowledge and skills acquired during e-commerce learning. Therefore, this invention effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0048] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. An e-commerce teaching system based on ADDIE, characterized in that, include: The acquisition unit is used to acquire the first interaction data between trainees and consumers during their e-commerce retail business practice. The capability analysis unit is used to perform e-commerce retail capability analysis corresponding to different behavioral perspectives based on the first interaction data, and obtain the corresponding capability analysis results. The course matching unit is used to perform course recommendation analysis based on the capability analysis results, generate target learning course groups corresponding to the target business capabilities, and generate simulated test content during the course learning process of the target learning course groups to conduct course testing and obtain simulated test results. The teaching evaluation unit is used to match and test the second interactive data during the course learning process with the business capabilities corresponding to each business project type. When the second interactive data matches the target business capability, a comprehensive evaluation of the learning effect is carried out based on the second interactive data and the simulation test results corresponding to the target learning course group, so as to update the advanced courses of the target learning course group for continued teaching.

2. The e-commerce teaching system based on ADDIE according to claim 1, characterized in that, The ability analysis results include the missing abilities from the trainee's perspective and the corresponding missing ability values; The capability analysis unit includes: The project extraction subunit is used to extract the business project type from the first interactive data; The decomposition subunit is used to decompose the first interaction data according to the business project type, corresponding to the behavior sequence from the student's perspective, to obtain actual behavior sequence data, wherein the actual behavior sequence data includes actual behavior sub-data corresponding to multiple student behavior items. The quantitative comparison subunit is used to perform a multi-dimensional quantitative comparison of the actual behavior sequence data and the ideal behavior sequence data corresponding to the business project type for each trainee behavior item, and to obtain the cumulative ability deviation value corresponding to each trainee behavior item; and The deviation judgment subunit is used to determine whether the cumulative deviation value of the ability exceeds the deviation threshold. If so, the student behavior item corresponding to the cumulative deviation value of the ability is taken as the missing ability, and the cumulative deviation value of the ability is taken as the missing ability value.

3. The e-commerce teaching system based on ADDIE according to claim 2, characterized in that, The quantization comparison subunit includes: The overall assessment module is used to perform an overall distance assessment between the actual behavior sequence data and the ideal behavior sequence data corresponding to the business project type, and obtain the first capability deviation cumulative value. The vectorization module is used to perform vectorization processing on the actual behavior sub-data for each modality dimension to obtain the actual modality vector corresponding to each modality dimension. The modality dimensions include text modality dimension, voice modality dimension, video modality dimension and behavior log modality dimension. The difference comparison module is used to compare the difference between the actual modal vector and the ideal modal vector under the corresponding modal dimension of the ideal behavior sequence data to obtain the modal deviation; The deviation calculation module is used to obtain the second capability deviation cumulative value based on the modal deviation and the dimension transformation coefficient of the corresponding modal dimension; and The weighted fusion module is used to weight and fuse the first cumulative ability deviation value and the second cumulative ability deviation value to obtain the cumulative ability deviation value corresponding to each student behavior item. The formula for calculating the cumulative value of the capability deviation is: ； in, This indicates that the ability deviates from the cumulative value. This represents the actual behavior sub-data corresponding to each student behavior item in the actual behavior sequence data. This represents the ideal behavior sub-data corresponding to each trainee behavior item in the ideal behavior sequence data. This represents the actual modality vector for each modality dimension corresponding to each learner behavior item. This represents the ideal modality vector for each modality dimension corresponding to each learner behavior item. Represents the dimension transformation coefficient. This represents the first weighting factor corresponding to the deviation of the first capability from the cumulative value. This indicates the first weighting factor corresponding to the deviation of the second capability from the cumulative value. This represents the total number of actual behavior sub-data. This represents the total number of sub-data points representing the ideal behavior.

4. The e-commerce teaching system based on ADDIE according to claim 1, characterized in that, The capability analysis results include the demand capability from the consumer's perspective and the corresponding demand capability value. The capability analysis unit also includes: The emotion detection subunit is used to detect emotion signals in the first interaction data in a multimodal dimension corresponding to the consumer's perspective; The first correlation analysis subunit is used to perform correlation analysis on the target actual behavior sub-data corresponding to the student behavior item before the negative emotion signal was generated and the modal data of the negative emotion signal in the corresponding modal dimension when the emotion signal is detected to be a negative emotion signal, so as to obtain a first correlation value. The behavior combination sub-unit is used to combine the historical actual behavior sub-data corresponding to several student behavior items before the target actual behavior sub-data with the target actual behavior sub-data in an ascending manner to obtain actual behavior combination data. The second correlation analysis subunit is used to perform correlation analysis between the actual behavior combination data and the modal data of the negative emotional signal in the corresponding modal dimension to obtain a second correlation value; and The capability analysis subunit is used to perform demand capability analysis based on the first correlation value and the second correlation value to obtain the demand capability and corresponding demand capability value from the consumer's perspective.

5. The e-commerce teaching system based on ADDIE according to claim 4, characterized in that, The capability analysis subunit includes: The correlation difference calculation module is used to calculate the difference between two adjacent correlation values ​​corresponding to each student behavior item based on the first correlation value and the second correlation value, so as to obtain the correlation increment. The curve construction module is used to establish a trend curve of the correlation degree increment over time based on the correlation degree increment. The change detection module is used to detect the magnitude of change in the trend curve, and to take the student behavior items from the start time corresponding to a sudden increase in the trend curve to the time before the negative emotional signal subsides as the corresponding demand capabilities from the consumer's perspective; and The ability calculation module is used to obtain the required ability value corresponding to each required ability based on the initial value of the ability requirement for emotional coordination of the trainee behavior item corresponding to the required ability, the negative emotional signal intensity increment of the negative emotional signal corresponding to each trainee behavior item, and the ability requirement index corresponding to the corresponding trainee behavior item.

6. The e-commerce teaching system based on ADDIE according to claim 5, characterized in that, The formula for calculating the required capacity value is: ； in, Indicates the demand capacity value. This represents the initial value of the capacity requirement. This represents the increment of negative emotional intensity corresponding to the aforementioned student behavior item. This indicates the competency requirement index corresponding to each trainee's behavioral item. This indicates the increased demand capacity corresponding to a failed order. This represents the demand capacity loss value corresponding to a successful order. Indicates the order status, with a value of 0 or 1. This indicates that the order status is "order successful". This indicates that the order status is "order failed".

7. The e-commerce teaching system based on ADDIE according to claim 1, characterized in that, The capability analysis results include the missing capabilities and corresponding missing capability values ​​from the perspective of trainees, and the required capabilities and corresponding required capability values ​​from the perspective of consumers. The course matching unit includes: The capability filtering subunit is used to perform capability overlap filtering based on the missing capabilities and the required capabilities to obtain target business capabilities, wherein the target business capabilities include overlapping capabilities and independent capabilities. The capability fusion subunit is used to perform weighted fusion of the missing capability value corresponding to the missing capability in the overlapping capabilities and the demand capability value corresponding to the demand capability to obtain a fused capability value. A capability combination subunit is used to freely combine the overlapping capabilities and the independent capabilities to obtain a capability combination; and The course search subunit is used to search the course knowledge base based on the capability combination, generate target learning course groups corresponding to the target business capabilities, and generate simulated test content during the course learning process of the target learning course groups to conduct course testing and obtain simulated test results.

8. The e-commerce teaching system based on ADDIE according to claim 7, characterized in that, The course search sub-unit includes: The library search module is used to search the course knowledge base based on the combination of abilities to obtain a set of learning course groups under different combination forms. The ability comparison module is used to compare the ability improvement value of each ability corresponding to each learning course group in the learning course group set with the fusion ability value corresponding to the overlapping ability and the independent ability value corresponding to the independent ability in the ability combination, so as to obtain the available learning course groups in which both the fusion ability value and the independent ability value are less than the corresponding ability improvement value; The comprehensive calculation module is used to perform a comprehensive calculation of the difficulty of ability improvement for the available learning course groups, and to obtain the comprehensive learning difficulty corresponding to each available learning course group. The course selection module is used to select the available learning course group with the lowest overall learning difficulty as the target learning course group. The sorting module is used to generate a ranking of the target learning courses based on the correlation between the overlapping abilities and the independent abilities in the target learning course group; and The course testing module is used to generate corresponding simulated test content based on the order of the target learning courses and the completion progress of each target learning course, so as to conduct course testing and obtain simulated test results.

9. The e-commerce teaching system based on ADDIE according to claim 1, characterized in that, The teaching assessment unit includes: The capability detection subunit is used to detect business capabilities in the second interactive data during the course learning process to obtain the second business capabilities. The capability enhancement calculation subunit is used to calculate the difference between the learning capability value corresponding to the second business capability and the historical capability value corresponding to the target business capability when the second business capability is consistent with the corresponding target business capability, so as to obtain the capability enhancement value. The comprehensive improvement calculation subunit is used to fuse the capability improvement value with the simulated improvement value corresponding to the simulated test results to obtain a comprehensive improvement value; and An improvement judgment subunit is used to determine whether the comprehensive improvement value meets the improvement threshold requirement of the target learning course corresponding to the target learning course group. If it does not meet the requirement, the target learning course group is updated based on the upgradable value between the comprehensive improvement value and the improvement threshold, and advanced courses with corresponding learning difficulty are extracted for continued teaching. The upgradable value is negatively correlated with the learning difficulty of the advanced courses.

10. An e-commerce teaching method based on ADDIE, characterized in that, include: Acquire the first interaction data between trainees and consumers during their practical e-commerce retail business operations; Based on the first interaction data, e-commerce retail capability analysis corresponding to different behavioral perspectives is performed to obtain the corresponding capability analysis results; Based on the capability analysis results, a course recommendation analysis is performed to generate target learning course groups corresponding to the target business capabilities. Simulated test content is generated during the course learning process of the target learning course groups to conduct course testing and obtain simulated test results. The second interactive data during the course learning process is matched and tested with the business capabilities corresponding to each business project type. When the second interactive data matches the target business capability, a comprehensive evaluation of the learning effect is carried out based on the second interactive data and the simulation test results corresponding to the target learning course group, so as to update the advanced courses of the target learning course group for continued teaching.

Images