In this paper, the problem of piano practice time allocation is categorized as an integer planning problem, and focuses on 0-1 integer planning in integer planning. Based on the advantageous information in the 0-1 integer programming problem, the value of feasible solutions and the index set corresponding to the feasible solutions are proposed to realize the piano practice time allocation based on integer programming. For the evaluation of piano playing effect, a piano playing effect evaluation method based on the extraction of musical melody features is proposed, which adopts the base note cycle extraction algorithm based on the short-time autocorrelation method to extract the base note of the musical melody, and improves the linear scaling algorithm to solve the problem of uneven playing speeds and so on. In the piano practice practice allocation experiment, the average allocation time of player A applying the time allocation method of this paper is 2516s, which is higher than that of player B with the traditional allocation time, and the average concentration time accounts for 98.53% of the average time, which is better than that of player B’s 95.43% share. Compared with the traditional manual evaluation method, the evaluation results of this paper’s piano playing effect evaluation method in different test times sum up to 1, and the evaluation effect is better.

This paper constructs the evaluation index system of city image IP brand communication efficacy, and utilizes hierarchical analysis and fuzzy comprehensive evaluation to construct a comparison matrix to assign and quantify them. Then, it constructs a regression model to analyze the influencing factors of city brand image communication efficacy with city brand image communication management power, communication power and relationship power as independent variables and city brand image perception as dependent variable. With empirical factor analysis, the chi-square degrees of freedom ratio CMIN/DF is 1.034, and the root mean square of approximation error RMSEA is 0.017, the assessment model has a good fit, which verifies the scientificity of the communication effectiveness assessment framework system. The communication effect of a city’s brand image is assessed and found to have a comprehensive score of 86.16. The city brand image communication management power, communication power and relationship power all have a positive influence on the city brand image communication effectiveness.

Bridge construction is an important link in the construction of transportation infrastructure, which plays a key role in ensuring the smoothness and safety of road traffic. This paper systematically organizes the process of laser point cloud technology in bridge quality monitoring, and proposes an improved adaptive hyperparametric RANSAC point cloud segmentation algorithm to realize the bridge quality monitoring. Firstly, the basic process of RANSAC algorithm is sorted out, and the mean downsampling operation is adopted to replace the center of gravity downsampling method, which improves the point average degree of downsampling. Next, the FPS algorithm is combined with the method of selecting seed points to expand the range of selected values of seed points under the premise of meeting the relevant requirements. After splitting multiple fitting surfaces, the split fitting surfaces are combined to optimize the unfitted points and improve the fitting rate of the algorithm. The detection accuracy of the bearing flatness of bridge number 3 under the method of this paper is improved by 78.26%, and the maximum deviation of the detected bridge constitutive point offset is only 0.623m, which is within the acceptable range of bridge error monitoring. The feasibility of laser point cloud technology for bridge quality monitoring is verified.

Wireless sensor networks, which integrate a variety of technologies such as sensors, microelectromechanical systems, wireless communications, and distributed information processing, have become a cutting-edge field for studying the behavior of intelligent autonomous self-governing systems in groups. This paper explores distributed sensor networks in intelligent buildings, uses QoS routing algorithm based on ant colony optimization to implement the strategy of energy efficiency regulation of distributed sensor networks, and conducts experimental analysis on the performance of the algorithm as well as distributed sensor networks. Compared with the PCCAA algorithm, the node degree variance and channel percentage variance of this paper’s algorithm are smaller, the network link distribution and channel allocation are more balanced, and the topology is better. Meanwhile, the average power of this paper’s algorithm is slightly larger than that of the PCCAA algorithm, which is able to increase the robustness of the network while reducing the energy consumption and BER to ensure the network performance. In addition, the variance of the node energy consumption of this paper’s algorithm in different networks is smaller than that of the PCCAA algorithm, which indicates that this paper’s algorithm can make the node energy consumption of the whole network more balanced, and then improve the energy efficiency of the whole network. Simulation experiments prove that the algorithm in this paper effectively allocates node bandwidth through the quantization mechanism, thus reducing the amount of inter-node communication, while the corresponding sampling interval extension strategy can save the overall energy consumption of the network. The algorithm proposed in this paper has important practical value for energy efficiency regulation of sensor networks in intelligent buildings.

With the arrival of the big data era, a huge amount of text data of college language is generated, and how to manage these text data efficiently and mine useful information has become the focus of many scholars. The study first preprocesses and represents the university language text data, proposes a feature screening method based on Shannon entropy and JS-scatter, and then combines the principal component analysis algorithm with the dimensionality reduction of the extracted features on this basis. Subsequently, a pre-trained high-dimensional word vector spatial mapping model is introduced to generate richer semantic representations, and a pre-trained high-dimensional word vector spatial mapping model based on the pre-trained high-dimensional word vector spatial mapping model is designed. Finally, the method proposed in this paper is tested experimentally. Under different feature dimensions, the macro-averages of this paper’s method are 72%, 44.2%, 67.1%, and 3.3% higher than those of IG, PMI, ANOVA, and JS methods. At the feature dimension k=350, the macro-mean of this paper’s method is 0.853, when the classification effect reaches the optimization. In the spatial mapping relationship of word vectors, the accuracy of the mapping of this paper’s method also reaches 11.2% for the words with word frequency sorted from the first 5000 to the first 6000. This proves the effectiveness and feasibility of this paper’s method.

Knowledge mapping technology can effectively integrate and manage knowledge, and fully show the relationship between knowledge. Based on this, knowledge mapping is applied to the construction of the resource base of the ideology and politics course to explore its association with the teaching content. After sorting out the relevant concepts and construction methods of knowledge mapping, this paper proposes the design method of course ideology based on knowledge mapping. The web crawler tool is utilized to crawl the text data of the Civics material and preprocess the data. The seven-step method and Protégé, an important tool for ontology modeling, were used to complete the construction of the ontology model of the curriculum Civics and Politics domain. Finally, BERT, GGAT, CRF, and graph pooling techniques are combined to construct the general architecture of the Civics knowledge extraction model to realize the extraction of Civics knowledge. The method of Civics knowledge relation extraction in this paper performs well in the comparison experiment, and the AUC value of the method reaches 41.59%. More than 90% of the students express their liking and agreement with the teaching model based on knowledge graph, which verifies that the teaching model based on knowledge graph proposed in this paper has a positive and active effect on the learning aspect of students’ Civics knowledge.

Frequent lightning activity has the potential to cause damage to man-made facilities, cause forest fires and other hazards, and the prediction of lightning activity can help to avoid the occurrence of these disasters. In this paper, based on the lightning activity data of a region, the distribution pattern of lightning activity is identified at different elevations and latitudes and longitudes. Then geodetic distance and contributing nearest-neighbor similarity are introduced, and a GS-DBSCAN clustering algorithm is proposed to realize the spatial prediction of lightning activity by using the method of leastsquares fitting of prediction equations. The lightning activity directions after data clustering show topographic correlation, and the overlap between lightning activity directions and topography is about 35%. Combined with the prediction images, it is found that the lightning activity prediction results of this paper’s method are closer to the real value than other algorithms, with an average offset error of less than 1.1km, an accuracy rate of >85%, and a false alarm rate of <35%, which reflects a good prediction performance.

Increasing the degree of mixed use of urban land and building diverse and multifunctional urban spaces are important ways to shape urban vitality and promote healthy development of neighborhoods and social inclusion. Taking the urban area of City A as the research object, the article screens and classifies the collected POI data, and realizes the division and identification of functional areas in the core urban area of City A by calculating the degree of chaotic urban land use in parcels based on entropy under the fine-grained grid scale of the road network. Subsequently, the calculation methods of spatial weights and bandwidths of the model based on ordinary least squares and the Moran’s index eliciting the GWR model are introduced. Finally, eight factors that have an impact on neighborhood and social inclusion were selected as explanatory variables, and an empirical study of the spatial distribution of neighborhood and social inclusion and the influencing factors was carried out using the geographically weighted regression model. The study found that the functional mixing degree in the main urban area of City A generally shows the spatial distribution of high-mixing degree plots of land with “center clustering and multi-point scattering”, and locally shows the characteristics of piecewise clustering in the central area, linear clustering along the main roads, and pointwise clustering around the subway stations. The four influencing factors of common habits, psychosocial distance, social contact behavior and external behavioral interference are positively correlated with the changes of neighborhood relationship and social inclusion.

In this paper, a pressure distribution model of seepage field based on complex reservoir conditions is established based on a finite element mathematical model. Due to the non-homogeneity and multiple flow characteristics of the reservoir, the mathematical model of fractured horizontal wells based on reservoir and fracture is established by solving the finite element equations of oil-phase pressure and water-phase saturation under the two-dimensional oil-water two-phase finite element model. Through numerical simulation of the coupling between the permeability change of the fractured fracture and the bedrock in the oil seepage field, the influence of different fracture parameters on the pressure distribution is analyzed, and each parameter is optimized. Investigations of stress-strain, porosity and permeability in time and space in low-permeability reservoirs found that in the region near the bottom of the well, each parameter varies more, while the farther away from the bottom of the well region the less affected it is. The relative position of the fracture to the well has a large effect on the production of fractured horizontal wells, but this parameter can be artificially regulated. Repeated fracturing cumulative oil incremental analysis found that “fracture network bandwidth, main fracture half-length and main fracture inflow capacity” have the greatest influence on the high permeability strip, the factors of angular wells and low permeability zones, and the repeated fracturing cumulative oil incremental simulation of each fracture parameter has the greatest effect on the fracture network bandwidth, main fracture half-length and main fracture inflow capacity under the coupled model of Well 3 (23.25%), and the optimal values of the parameters are 100m, 100m, 100m, 100m, 100m, 100m and 100m respectively. optimal values of the parameters are 100 m, 150×10-3μm2·m, 20 m and 45×10-3μm2·m, respectively.

There is a close relationship between adolescent mental health and physical health, so it is of great practical signiϐicance to explore the speciϐic inϐluencing factors and early warning model of students’ mental health. In this paper, the early warning model of students’ mental health risk is constructed. Firstly, the association rules and Apriori algorithm are used to explore the relationship between the important inϐluencing factors of students’ mental health and common psychological problems, and then the CMA-ES-XGBoost prediction model is proposed to address the defects of the XGBoost prediction model that has high complexity and low prediction accuracy. It adopts the hyperparameters of CMA-ES optimization algorithm to ϐind the optimal hyperparameter solution, and solves the fuzzy phenomenon existing in the early warning of mental health risks by fuzzy logic method, which reduces the error of prediction results. It is experimentally veriϐied that the mental health prediction method based on CMA-ES-XGBoost performs well on the task of students with mental health risk, and the prediction accuracy is 89.66%, which is better than the comparison model. It can accurately detect the mood ϐluctuations of students with different types of personality when they are exposed to multiple extroverted stimuli, and accurately predict the emotional risk. It shows that the model in this paper realizes the function of predicting students’ mental health status and achieves the expected goal of model design.