Technical acceptance and behavior intention prediction method based on behavior intention derivative model

Abstract

The invention discloses a technical acceptance and behavior intention prediction method based on a behavior intention derivative model. The prediction method comprises the following steps: S1, data acquisition: providing necessary input data for behavior intention prediction; s2, multiple interaction modes: providing more-dimensional information support for subsequent behavior intention prediction; s3, a behavior intention analysis model: constructing a behavior intention calculation formula through quantitative analysis of a plurality of influence factors, and providing accurate prediction of the user behavior intention; s4, construction of a prediction model: further predicting future behaviors of the user through analysis and training of user behavior intentions, and providing a basis for decision making; and S5, continuous iteration and updating of the model: performing real-time updating and optimization according to new data by adopting a continuous learning mechanism, and constructing an optimization prediction algorithm formula. The method is high in prediction accuracy, has extremely high applicability, can accurately grasp user requirements, and provides valuable decision support for technical design and popularization strategies.

Description

Technical Field

[0001] The present invention relates to the fields of behavioral psychology, user experience analysis and information technology, and in particular to a method for predicting technology acceptance and behavioral intention based on a behavioral intention derivative model. Background Art

[0002] Behavioral intention is a psychological state that reflects an individual's positive or negative attitude toward a specific behavior. It is a prediction of future behavior, indicating whether an individual will actually take action at a certain point in the future.

[0003] Existing behavioral intention models focus more on external factors (such as perceived usefulness, perceived ease of use, facilitating conditions and social influence, etc.), and ignore the interaction between multiple internal factors (such as interest, attitude, pleasure motivation and technical self-efficacy, etc.). This limitation makes it impossible to fully explain why different individuals show different behavioral intentions under similar external conditions. At the same time, this deficiency also leads to a low technology adoption rate, and the personalized design of products cannot effectively meet user needs. Therefore, it is necessary to design a technology acceptance and behavioral intention prediction method based on the behavioral intention derivative model to solve the above problems. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing technology acceptance and behavior intention prediction methods based on behavior intention derivative models, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a technology acceptance and behavioral intention prediction method based on a behavioral intention derivative model, which is suitable for solving the problem that the existing technology cannot fully explain why different individuals show differentiated behavioral intentions under similar external conditions, which in turn leads to a low technology adoption rate and the personalized design of products cannot effectively meet user needs.

[0007] In order to solve the above technical problems, the present invention provides the following technical solution: a technology acceptance and behavior intention prediction method based on a behavior intention derivative model, the prediction method comprising:

[0008] S1: Data collection: providing necessary input data for behavioral intention prediction;

[0009] S2: Multiple interaction modes: provide more dimensional information support for subsequent behavioral intention prediction;

[0010] S3: Behavior intention analysis model: Through quantitative analysis of multiple influencing factors, a behavior intention calculation formula is constructed to provide accurate prediction of user behavior intention;

[0011] S4: Construction of prediction model: Through the analysis and training of user behavior intentions, further predict the user's future behavior and provide a basis for decision-making;

[0012] S5: Continuous iteration and updating of the model: Adopt a continuous learning mechanism, perform real-time updates and optimizations based on new data, and build an optimized prediction algorithm formula.

[0013] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model of the present invention, the behavior intention calculation formula is as follows:

[0014] BI=α 1 PE+α 2 EE+α 3 SI+α 4 FC+β 1 Interest+β 2 ·TSE+

[0015] β 3 Attitude+β 4 ·HM+ε

[0016] Among them, BI is the behavioral intention value, which indicates the user's acceptance of the new technology or product and the intention to use it in the future. PE is perceived usefulness, which indicates whether the user believes that the technology or product can effectively improve the quality of work or life. EE is perceived ease of use, which indicates whether the user thinks it is easy to use the technology or product. SI is social influence, which refers to the influence of others (such as colleagues, friends, etc.) on whether the user uses the technology or product. FC is facilitating conditions, which refers to whether the user has sufficient resources, support and environmental conditions to use the technology or product smoothly. Interest is interest, which indicates the user's interest in the technology. TSE is technical self-efficacy, which indicates the user's confidence and ability to use the technology. Attitude is attitude, which indicates the user's overall evaluation of the technology. HM is pleasure motivation, which indicates whether the user can bring a pleasant experience or enjoyment when using the technology. α 1 , α 2 , α 3 , α 4 , β 1 , β 2 , β 3 and β 4 is the weight coefficient of each variable, which is used to reflect the influence of each factor on behavioral intention. ε is the error term, which represents the random error in the model or the external influencing factors that cannot be captured.

[0017] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model of the present invention, wherein: the high behavior threshold is set to 4.0 and the medium behavior threshold is set to 2.5 in the output result of the behavior intention calculation formula;

[0018] If BI>4.0, it means that users have strong behavioral intention and high technology adoption rate;

[0019] If 2.5≤BI≤4.0, it means that the user's behavioral intention is moderate and hesitant, and further training, education and promotion are needed to improve their acceptance;

[0020] If BI is less than 2.5, it means that users have low acceptance of the technology and special attention should be paid to their feedback to identify and improve dissatisfaction.

[0021] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model described in the present invention, the optimization prediction algorithm formula is as follows:

[0022]

[0023] P opt (t) represents the optimized prediction result based on time step t, representing the optimized prediction value of technology acceptance, which is updated in real time according to new data over time. i (t) is the quantitative data of external factors, α i is the regression coefficient of the external factor, ln(X i (t)+1) is a nonlinear function that captures the incremental effect of external factors. i (t) is the quantitative data of the internal factors, β i is the regression coefficient of the internal factor, is a nonlinear function that captures the impact of intrinsic factors on behavioral intention, and λ is an adjustment factor that controls the flexibility of the overall model. is the weighted sum of the feedback data, It is external learning feedback that adjusts the adaptability of the prediction model to changes in external information.

[0024] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model described in the present invention, the high acceptance threshold is set according to the output result of the optimized prediction algorithm formula. and a low acceptance threshold

[0025] like It indicates that users are highly willing to accept the technology and will become early adopters or loyal users;

[0026] like It indicates that users are hesitant to accept the technology and need to increase their trust and interest in the technology through further education, training, promotion activities, etc.;

[0027] like It indicates that users have low willingness to accept the technology, and the probability of adopting the technology is low due to the influence of external or internal factors.

[0028] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model of the present invention, the data collection is specifically implemented by the following steps:

[0029] S11: Collect user characteristics: collect basic characteristics of users through user registration information or other identity authentication systems;

[0030] S12: Behavioral intention score: Adapt the scale based on the existing research model to collect subjective evaluations of users’ behavioral intentions;

[0031] S13: Variable scoring: Design an evaluation scale for the eight variables proposed in the hypothesis;

[0032] S14: User usage times: Automated data collection by recording user interaction data.

[0033] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model of the present invention, wherein: in said S2, specifically including the following three interaction modes:

[0034] Questionnaire survey: Obtain users’ subjective opinions and feedback on new technologies by distributing questionnaires online or offline;

[0035] Behavior log: embed data collection code to automatically record the user's actual usage behavior;

[0036] Interview: Select representative users for in-depth interviews to explore hidden needs and psychological factors.

[0037] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model of the present invention, the prediction model is implemented by the following steps:

[0038] S41: Variable encoding: numerical processing of categorical variables;

[0039] S42: Data normalization: Standardize continuous variables to ensure the uniformity of model input;

[0040] S43: Data balance: A certain sample was randomly selected according to stratification for pre-test, achieving a Cronbach α value higher than 0.70;

[0041] S44: Calculate Pearson's Product Moment coefficient to determine the relationship between the independent and dependent variables;

[0042] S45: Train the model to optimize model parameters: collect the errors between the predicted results and the actual behavior, analyze the potential causes, and use online learning mechanisms to update the model weights as new data is continuously collected.

[0043] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model described in the present invention, wherein: in S5, the model parameters are continuously adjusted through real-time data feedback and automatic updating of the behavior log to ensure that it can adapt to changes in user behavior. As user behavior data accumulates, the prediction ability of the model is gradually enhanced, the accuracy of the prediction is continuously improved, and it adapts to the changes in the needs of different user groups.

[0044] As a preferred solution of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model of the present invention, wherein: the α i Used to measure the contribution of each external factor to behavioral intention, β i Used to measure the contribution of each intrinsic factor to behavioral intention.

[0045] Beneficial effects of the present invention:

[0046] Strong comprehensiveness: By introducing external and internal variables to conduct multi-dimensional analysis of user behavior intentions and quantifying multiple influencing factors, the present invention overcomes the limitations of traditional single variable models and can more comprehensively capture and analyze the complex factors that affect user behavior;

[0047] High prediction accuracy: It can process the relationship between multiple variables at the same time and quantify the influence of each factor on behavioral intention by optimizing the prediction algorithm, thereby improving the accuracy and reliability of the prediction;

[0048] Wide applicability: The behavioral intention prediction model of the present invention has strong applicability and can be applied in various new technology scenarios, whether in the field of information systems, smart devices, medical technology, or educational technology, and can provide accurate user behavior prediction. Since the present invention can integrate multiple internal and external variables and has flexible adaptability, the input and weight of the model can be adjusted according to the specific needs of different fields, thereby achieving high customization;

[0049] User experience optimization: This invention can not only predict user behavior intentions, but also deeply analyze the key factors that drive user behavior, especially the interaction between internal and external factors. Through the quantitative analysis of these driving factors, developers can accurately grasp user needs and provide valuable decision-making support for technology design and promotion strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0051] Figure 1 A schematic diagram of the steps of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model proposed in the present invention;

[0052] Figure 2 This is a relationship network diagram of the technology acceptance and behavior intention prediction method based on the behavior intention derivative model proposed in the present invention. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0057] Embodiment 1

[0058] Reference Figure 1-Figure 2, which is an embodiment of the present invention, provides a technology acceptance and behavior intention prediction method based on a behavior intention derivative model, the prediction method comprising:

[0059] S1: Data collection: providing necessary input data for behavioral intention prediction;

[0060] S11: Collect user characteristics: collect basic characteristics of users through user registration information or other identity authentication systems;

[0061] S12: Behavioral intention score: Based on the existing research model, the scale is adapted to collect users' subjective evaluation of behavioral intention. The behavioral intention score is the user's subjective evaluation of the new technology and is the core data source for the behavioral intention analysis model. Users score the perceived usefulness and ease of use of the new technology to form preliminary behavioral intention data;

[0062] S13: Variable scoring: For the eight variables proposed in the hypothesis (4 external variables and 4 internal variables),

[0063] Design assessment scales for corresponding variables, and these scores will further affect the prediction accuracy of behavioral intention;

[0064] S14: User usage times: Automated data collection is performed by recording user interaction data. The user’s actual usage behavior is recorded through automated data collection methods, including clicks, function usage frequency, login frequency, etc. This data reflects the user’s frequency of technology contact and participation.

[0065] S2: Multiple interaction modes: provide more dimensional information support for subsequent behavioral intention prediction;

[0066] Questionnaire survey: Obtain users’ subjective intentions and feedback on new technologies through online or offline questionnaires. Distribute questionnaires online (such as email, social platforms) or offline (such as face-to-face surveys) and design scientific questionnaire content to ensure that it covers aspects such as new technology acceptance, demand analysis, and potential resistance.

[0067] Behavior log: embed data collection code to automatically record the user's actual usage behavior;

[0068] Interview: Select representative users for in-depth interviews to explore hidden needs and psychological influencing factors. Randomly select representative users from the user group for one-on-one interviews. Extract key opinions and suggestions through voice transcription and analysis tools. Semi-structured or unstructured questioning can be used during the interview to ensure coverage of diverse user feedback.

[0069] S3: Behavior intention analysis model: Through quantitative analysis of multiple influencing factors, a behavior intention calculation formula is constructed. Combining the external factors (PE, EE, SI, FC) of the existing UTAUT model and the internal psychological factors (Interest, TSE, Attitude, HM) proposed by the present invention, a comprehensive behavior intention analysis model is established, which comprehensively considers the individual differences of users and provides accurate prediction of user behavior intentions;

[0070] S4: Construction of prediction model: Through the analysis and training of user behavior intentions, further predict the user's future behavior and provide a basis for decision-making;

[0071] S41: Variable encoding: numerical processing of categorical variables;

[0072] S42: Data normalization: Standardize continuous variables to ensure the uniformity of model input;

[0073] S43: Data balance: A certain number of samples were randomly selected according to stratification for pre-testing to achieve a Cronbach α value higher than 0.70. According to the distribution of the data, oversampling or undersampling methods were adopted to make the number of samples of each type of data relatively balanced;

[0074] S44: Calculate Pearson's Product Moment coefficient to determine the relationship between the independent and dependent variables;

[0075] S45: Train the model to optimize model parameters: collect the errors between the predicted results and the actual behaviors, analyze the potential causes, adopt online learning mechanism, update the model weights when new data is continuously collected, and use cross-validation and other methods to optimize the hyperparameters of the training model; through error analysis, adjust the model structure and parameters so that the model can better adapt to the data of different user groups.

[0076] S5: Continuous iteration and updating of the model: Adopting a continuous learning mechanism, updating and optimizing in real time based on new data, and building an optimized prediction algorithm formula;

[0077] Through real-time data feedback and automatic updating of behavior logs, the model parameters are continuously adjusted to ensure that it can adapt to changes in user behavior. By monitoring the user's continuous behavior data, a feedback mechanism is established, and online learning algorithms (such as incremental learning) are embedded in the model. The model weights are dynamically updated. As user behavior data accumulates, the model's predictive ability gradually increases, the accuracy of the prediction is continuously improved, and it adapts to the changing needs of different user groups. Based on the long-term accumulation of data, the model is regularly retrained, weights are adjusted, and algorithms are optimized to ensure the stability and accuracy of the model.

[0078] The formula for calculating behavioral intention is as follows:

[0079] BI=α 1 PE+α 2 EE+α 3 SI+α 4 FC+β 1 Interest+β 2 ·TSE+

[0080] β 3 Attitude+β 4 HM+ε

[0081] Among them, BI is the behavioral intention value, which indicates the user's acceptance of the new technology or product and the intention to use it in the future. PE is perceived usefulness, which indicates whether the user believes that the technology or product can effectively improve the quality of work or life. EE is perceived ease of use, which indicates whether the user thinks it is easy to use the technology or product. SI is social influence, which refers to the influence of others (such as colleagues, friends, etc.) on whether the user uses the technology or product. FC is facilitating conditions, which refers to whether the user has sufficient resources, support and environmental conditions to use the technology or product smoothly. Interest is interest, which indicates the user's interest in the technology. TSE is technical self-efficacy, which indicates the user's confidence and ability to use the technology. Attitude is attitude, which indicates the user's overall evaluation of the technology. HM is pleasure motivation, which indicates whether the user can bring a pleasant experience or enjoyment when using the technology. α 1 , α 2 , α 3 , α 4 , β 1 , β 2 , β 3 and β 4 is the weight coefficient of each variable, which is used to reflect the influence of each factor on behavioral intention. ε is the error term, which represents the random error in the model or the external influencing factors that cannot be captured.

[0082] In the output of the behavioral intention calculation formula, the high behavior threshold is set to 4.0 and the medium behavior threshold is set to 2.5;

[0083] If BI>4.0, it means that users have strong behavioral intention and high technology adoption rate;

[0084] If 2.5≤BI≤4.0, it means that the user's behavioral intention is moderate and hesitant, and further training, education and promotion are needed to improve their acceptance;

[0085] If BI is less than 2.5, it means that users have low acceptance of the technology and special attention should be paid to their feedback to identify and improve dissatisfaction.

[0086] The optimization prediction algorithm formula is as follows:

[0087]

[0088] P opt (t) represents the optimized prediction result based on time step t, representing the optimized prediction value of technology acceptance, which is updated in real time according to new data over time. i (t) is the quantitative data of external factors, α i is the regression coefficient of the external factors, which is used to measure the contribution of each external factor to the behavioral intention. i (t)+1) is a nonlinear function that captures the incremental effect of external factors. i (t) is the quantitative data of the internal factors, β i is the regression coefficient of the intrinsic factor, which is used to measure the contribution of each intrinsic factor to behavioral intention. is a nonlinear function that captures the impact of intrinsic factors on behavioral intention, and λ is an adjustment factor that controls the flexibility of the overall model. is the weighted sum of the feedback data, It is external learning feedback that adjusts the adaptability of the prediction model to changes in external information.

[0089] Set a high acceptance threshold based on the output of the optimized prediction algorithm formula and a low acceptance threshold

[0090]

[0091] like It indicates that users are highly willing to accept the technology and will become early adopters or loyal users;

[0092] like It indicates that users are hesitant to accept the technology and need to increase their trust and interest in the technology through further education, training, promotion activities, etc.;

[0093] like It indicates that users have low willingness to accept the technology, and the probability of adopting the technology is low due to the influence of external or internal factors.

[0094] By introducing external variables and internal variables to conduct multi-dimensional analysis of user behavior intentions and quantifying multiple influencing factors, the present invention overcomes the limitations of traditional single variable models, can more comprehensively capture and analyze the complex factors that affect user behavior, can simultaneously process the interrelationships between multiple variables, and quantify the degree of influence of each factor on behavioral intentions by optimizing the prediction algorithm, thereby improving the accuracy and reliability of the prediction;

[0095] The behavioral intention prediction model of the present invention has strong applicability and can be applied in various new technology scenarios, whether in the field of information systems, smart devices, medical technology, or educational technology, and can provide accurate user behavior prediction. Since the present invention can integrate multiple internal and external variables and has flexible adaptability, the input and weight of the model can be adjusted according to the specific needs of different fields, thereby achieving high customization;

[0096] The present invention can not only predict user behavior intentions, but also deeply analyze the key factors driving user behavior, especially the interaction between internal and external factors. Through the quantitative analysis of these driving factors, developers can accurately grasp user needs and provide valuable decision-making support for technology design and promotion strategies.

[0097] Embodiment 2

[0098] Referring to Tables 1 to 3, which are the second embodiment of the present invention, this embodiment is different from the first embodiment in that, in order to verify its beneficial effects, experimental comparison data between the present invention and the prior art are provided.

[0099] This embodiment aims to verify the application of the prediction method based on the behavioral intention derivative model in smart home products (such as smart door locks). The experimental steps include data collection, behavioral intention scoring, variable evaluation, model training and optimization, etc.

[0100] First, we collected basic characteristic data (such as age, gender, occupation) and behavioral data (such as usage frequency, number of function accesses, etc.) from 1,000 users. The data collection methods include user registration information, questionnaires, behavior logs, etc.

[0101] A questionnaire was designed to collect users’ ratings on the perceived usefulness and ease of use of the product as input for behavioral intention prediction. The user ratings ranged from 1 to 5, with an average rating of 4.2, indicating that users had a high overall acceptance of the product.

[0102] We scored external factors (perceived usefulness, perceived ease of use, social influence, and facilitating conditions) and internal factors (interest, attitude, technical self-efficacy, and pleasure motivation) based on the feedback provided by users. The scores of each factor were relatively balanced, indicating that users had a strong consistency in their evaluation of these variables;

[0103] We used regression models and structural equation models (SEM) to train the collected data and quantify the impact of each variable on behavioral intention. Through cross-validation and error analysis, we optimized the model to ensure its high prediction accuracy.

[0104] Table 1: User basic information and rating data table

[0105]

[0106] Table 2: User behavior data table

[0107]

[0108] Table 3: Comparison of predicted results and actual behavior

[0109]

[0110]

[0111] Analysis of Table 1: Users' perceived usefulness, ease of use, and intrinsic factors (such as interest and attitude) all received high scores, indicating that the product is well accepted. The high scores in the table show that users have a high degree of identification with the product, which lays the foundation for the subsequent prediction of behavioral intentions.

[0112] Analysis of Table 2: Users' login frequency and function usage times show behavioral differences among different age groups. For example, young users have a higher usage frequency, while older users have a lower usage frequency. This provides a basis for further optimizing product design and promotion strategies. Through behavioral data analysis, we can identify differences in needs among different user groups and help formulate personalized promotion strategies.

[0113] Analysis of Table 3: Table 3 compares the difference between the predicted behavior intention value and the actual behavior score. For example, the predicted behavior intention value of user 1 is 4.3, while the actual behavior score is 4, and the prediction error is 0.3, indicating that the prediction is relatively accurate. For other users, the prediction error remains within a reasonable range, proving the stability and accuracy of the model.

[0114] The present invention can more accurately predict user behavior by introducing a comprehensive analysis of internal and external factors. Traditional models only rely on a few external factors, while the present invention significantly improves the prediction accuracy by introducing internal factors such as interests and attitudes. The low error values ​​in the data table further prove the effectiveness of the present invention, especially in personalized recommendations and dynamic updates. Compared with existing static models, the real-time feedback mechanism of the present invention can continuously optimize the model according to changes in user behavior, thereby improving the flexibility and stability of prediction.

[0115] In summary: By comparing the data, it can be concluded that the prediction method of the present invention has significant advantages over traditional technologies: it can comprehensively consider multi-dimensional factors and provide more accurate user behavior predictions, thereby helping developers optimize product design, formulate personalized promotion strategies, and improve the market adoption rate of technology.

[0116] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for predicting technology acceptance and behavioral intention based on a behavioral intention derivative model, characterized in that: The prediction method comprises: S1: Data collection: providing necessary input data for behavioral intention prediction; S2: Multiple interaction modes: provide more dimensional information support for subsequent behavioral intention prediction; S3: Behavior intention analysis model: Through quantitative analysis of multiple influencing factors, a behavior intention calculation formula is constructed to provide accurate prediction of user behavior intention; S4: Construction of prediction model: Through the analysis and training of user behavior intentions, further predict the user's future behavior and provide a basis for decision-making; S5: Continuous iteration and updating of the model: Adopt a continuous learning mechanism, perform real-time updates and optimizations based on new data, and build an optimized prediction algorithm formula.

2. The method for predicting technology acceptance and behavioral intention based on the behavioral intention derivative model according to claim 1, characterized in that: The behavioral intention calculation formula is as follows: BI=α1·PE+α2·EE+α3·SI+α4·FC+β1·Interest+β2·TSE+ β3·Attitude+β4·HM+ε Among them, BI is the behavioral intention value, which indicates the user's acceptance of the new technology or product and the intention to use it in the future; PE is perceived usefulness, which indicates whether the user believes that the technology or product can effectively improve the quality of work or life; EE is perceived ease of use, which indicates whether the user thinks it is easy to use the technology or product; SI is social influence, which refers to the influence of others (such as colleagues, friends, etc.) on whether the user uses the technology or product; FC is facilitating conditions, which refers to whether the user has sufficient resources, support and environmental conditions to use the technology or product smoothly; Interest is interest, which indicates the user's interest in the technology; TSE is technical self-efficacy, which indicates the user's confidence and ability to use the technology; Attitude is attitude, which indicates the user's overall evaluation of the technology; HM is pleasure motivation, which indicates whether the user can bring a pleasant experience or enjoyment when using the technology; α1, α2, α3, α4, β1, β2, β3 and β4 are the weight coefficients of each variable, which are used to reflect the influence of each factor on behavioral intention; ε is the error term, which indicates the random error in the model or the external influencing factors that cannot be captured.

3. The method for predicting technology acceptance and behavioral intention based on the behavioral intention derivative model according to claim 2, characterized in that: In the output of the behavioral intention calculation formula, the high behavior threshold is set to 4.0 and the medium behavior threshold is set to 2.5; If BI>4.0, it means that users have strong behavioral intention and high technology adoption rate; If 2.5≤BI≤4.0, it means that the user's behavioral intention is moderate and hesitant, and further training, education and promotion are needed to improve their acceptance; If BI is less than 2.5, it means that users have low acceptance of the technology and special attention should be paid to their feedback to identify and improve dissatisfaction.

4. The method for predicting technology acceptance and behavioral intention based on the behavioral intention derivative model according to claim 1 is characterized by: The optimization prediction algorithm formula is as follows: P opt (t) represents the optimized prediction result based on time step t, representing the optimized prediction value of technology acceptance, which is updated in real time according to new data over time. i (t) is the quantitative data of external factors, α i is the regression coefficient of the external factor, ln(X i (t)+1) is a nonlinear function that captures the incremental effect of external factors. i (t) is the quantitative data of the internal factors, β i is the regression coefficient of the internal factor, is a nonlinear function that captures the impact of intrinsic factors on behavioral intention, and λ is an adjustment factor that controls the flexibility of the overall model. is the weighted sum of the feedback data, It is external learning feedback that adjusts the adaptability of the prediction model to changes in external information.

5. The method for predicting technology acceptance and behavior intention based on the behavior intention derivative model according to claim 4 is characterized by: Set a high acceptance threshold based on the output of the optimized prediction algorithm formula and a low acceptance threshold like It indicates that users are highly willing to accept the technology and will become early adopters or loyal users; like It indicates that users are hesitant to accept the technology and need to increase their trust and interest in the technology through further education, training, promotion activities, etc.; like It indicates that users have low willingness to accept the technology, and the probability of adopting the technology is low due to the influence of external or internal factors.

6. The method for predicting technology acceptance and behavior intention based on the behavior intention derivative model according to claim 1, characterized in that: The data collection is specifically implemented through the following steps: S11: Collect user characteristics: collect basic characteristics of users through user registration information or other identity authentication systems; S12: Behavioral intention score: Adapt the scale based on the existing research model to collect subjective evaluations of users’ behavioral intentions; S13: Variable scoring: Design an evaluation scale for the eight variables proposed in the hypothesis; S14: User usage times: Automated data collection by recording user interaction data.

7. The method for predicting technology acceptance and behavioral intention based on a behavioral intention derivative model according to claim 1, characterized in that: In the S2, the following three interaction modes are specifically included: Questionnaire survey: Obtain users’ subjective opinions and feedback on new technologies by distributing questionnaires online or offline; Behavior log: embed data collection code to automatically record the user's actual usage behavior; Interview: Select representative users for in-depth interviews to explore hidden needs and psychological factors.

8. The method for predicting technology acceptance and behavioral intention based on a behavioral intention derivative model according to claim 1, characterized in that: The prediction model is implemented by the following steps: S41: Variable encoding: numerical processing of categorical variables; S42: Data normalization: Standardize continuous variables to ensure the uniformity of model input; S43: Data balance: A certain sample was randomly selected according to stratification for pre-test, achieving a Cronbach α value higher than 0.70; S44: Calculate Pearson's Product Moment coefficient to determine the relationship between the independent and dependent variables; S45: Train the model to optimize model parameters: collect the errors between the predicted results and the actual behavior, analyze the potential causes, and use online learning mechanisms to update the model weights as new data is continuously collected.

9. The method for predicting technology acceptance and behavior intention based on the behavior intention derivative model according to claim 1, characterized in that: In the S5, the model parameters are continuously adjusted through real-time data feedback and automatic updating of behavior logs to ensure that it can adapt to changes in user behavior. As user behavior data accumulates, the predictive ability of the model is gradually enhanced, the accuracy of the prediction is continuously improved, and it can adapt to changes in the needs of different user groups.

10. The method for predicting technology acceptance and behavior intention based on the behavior intention derivative model according to claim 4, characterized in that: The α i Used to measure the contribution of each external factor to behavioral intention, β i Used to measure the contribution of each intrinsic factor to behavioral intention.

Images