An overview of the geology and production of the Fuling shale gas field,Sichuan Basin,China

The Fuling shale gas field in China is the largest shale gas field as well as the largest of its type discovered in any Lower Paleozoic formation.In this study,the geology and production of the upper and lower gas layers in the Fuling shale gas field are evaluated in terms of structure,shale quality,fault,initial production,and estimated ultimate recovery(EUR).The shale in the lower gas layer of the Jiaoshiba anticline is a high-quality reservoir,where the space is dominated by organic pores in kerogen,and the gas content is high.The shale gas wells reveal relatively high initial production and EUR.However,the shale in the upper gas layer of the Jiaoshiba anticline has reservoir space mainly composed of clay mineral pores and organic pores within bitumen,and the gas content is low.In terms of structure,primary gas migration may occur in the upper gas layer,resulting in free gas accumulation in the structural high,where the development effects are generally better than those in the structural low.The lower gas layer in the Pingqiao anticline,is the main interval for shale gas accumulation and development due to the high-quality shale.Under the influence of faults,the efficiency of exploration wells emplaced on top of the anticline is much lower a compared with those in the flanks.The residual synclines close to the Sichuan Basin,including the Baima and Baitao anticlines,are characterized by more recent uplifts,larger area,greater distance from the deep and large faults,and early fracture closure.Therefore,we recommend that the shale gas exploration and development should be carried out preferentially in areas close to the center of the residual synclines,featuring relatively high-pressure coefficient and moderate burial depth.

吡嘧司特钾片在中国健康志愿者空腹/餐后的生物等效性研究

目的比较单次空腹与餐后条件下吡嘧司特钾片在中国健康受试者体内的药代动力学,评价受试制剂(T)和参比制剂(R)的生物等效性。方法采用随机、开放、单剂量、两周期、双交叉生物等效性试验设计,空腹组与餐后组各入组26名与30名受试者,每周期在空腹状态或餐后状态下服用受试制剂与参比制剂10 mg,在给药周期前后按设计的时间点采集静脉血。用高效液相质谱联用法(LC-MS/MS)测定血浆中的吡嘧司特钾浓度,用Phoenix TM WinNonlin(8.3)软件计算药代动力学参数,对两制剂进行生物等效性分析。结果空腹单次口服给药受试制剂和参比制剂的t 1/2分别为(4.44±0.91)h和(4.49±0.93)h,t max中位数分别为(1.96±1.29)h和(2.18±1.25)h,C max分别为(867.12±205.56)μg·L^(-1)和(863.35±172.03)μg·L^(-1),AUC 0-t分别为(5513.23±1463.67)h·μg·L^(-1)和(5661.32±1628.65)h·μg·L^(-1),AUC 0-∞分别为(5699.81±1477.68)h·μg·L^(-1)和(5849.44±1644.75)h·μg·L^(-1);受试者的主要药代动力学参数C max、AUC 0-t、AUC 0-∞的90%置信区间的统计结果分别为92.49%~107.53%、94.71%~100.67%和95.28%~100.27%,均在80.00%~125.00%范围内,空腹口服受试制剂与参比制剂安全性良好;餐后单次口服给药受试制剂和参比制剂的t 1/2分别为(4.46±0.78)h和(4.51±0.84)h,t max中位数分别为(3.08±1.36)h和(3.28±1.28)h,C max分别为(683.83±111.87)μg·L^(-1)和(689.77±110.24)μg·L^(-1),AUC 0-t分别为(5695.99±1566.05)h·μg·L^(-1)和(5773.60±1551.04)h·μg·L^(-1),AUC 0-∞分别为(5914.06±1551.86)h·μg·L^(-1)和(5967.30±1552.89)h·μg·L^(-1);C max、AUC 0-t、AUC 0-∞的90%置信区间统计结果分别为93.56%~104.69%、96.43%~100.83%和97.29%~101.14%,均在80.00%~125.00%范围内,餐后口服受试制剂与参比制剂安全性良好。结论在空腹与餐后的单次口服给药条件下,两种吡嘧司特钾片具有较好的生物等效性。

制造业现场工程师职业能力养成模式与路径——基于产教融合行业共同体的探索

在制造行业中,现场工程师的职业能力直接决定了产品质量、生产效率以及企业的竞争力。行业共同体模式作为一种新型的职业能力培养方式,正逐渐在制造业现场工程师的职业能力养成中展现出其独特的优势。该模式强调行业内的多方参与和资源共享,通过理论与实践的结合,为现场工程师提供了一个全面、系统地学习和发展平台。通过分析当前制造业现场工程师职业能力存在的问题,结合当前制造业的发展趋势以及教育强国对职业教育质量提升工作的要求,提出行业共同体职业能力养成模式及其实施路径,为职业教育高质量人才培养提供一种新的实践模式。

Layered Structural PBAT Composite Foams for Efficient Electromagnetic Interference Shielding

The utilization of eco-friendly,lightweight,high-efficiency and high-absorbing electromagnetic interference(EMI)shielding composites is imperative in light of the worldwide promotion of sustainable manufacturing.In this work,magnetic poly(butyleneadipate-coterephthalate)(PBAT)microspheres were firstly synthesized via phase separation method,then PBAT composite foams with layered structure was constructed through the supercritical carbon dioxide foaming and scraping techniques.The merits of integrating ferroferric oxideloaded multi-walled carbon nanotubes(Fe3O4@MWCNTs)nanoparticles,a microcellular framework,and a highly conductive silver layer have been judiciously orchestrated within this distinctive layered configuration.Microwaves are consumed throughout the process of“absorption-reflection-reabsorption”as much as possible,which greatly declines the secondary radiation pollution.The biodegradable PBAT composite foams achieved an EMI shielding effectiveness of up to 68 dB and an absorptivity of 77%,and authenticated favorable stabilization after the tape adhesion experiment.

Microscopic characteristics of tight sandstone reservoirs and their effects on the imbibition efficiency of fracturing fluids:A case study of the Linxing area,Ordos Basin

The Linxing area within the Ordos Basin exhibits pronounced reservoir heterogeneity and intricate micro-pore structures,rendering it susceptible to water-blocking damage during imbibition extraction.This study delved into the traits of tight sandstone reservoirs in the 8th member of the Shihezi Formation(also referred to as the He 8 Member)in the study area,as well as their effects on fracturing fluid imbibition.Utilizing experimental techniques such as nuclear magnetic resonance(NMR),high-pressure mercury intrusion(HPMI),and gas adsorption,this study elucidated the reservoir characteristics and examined the factors affecting the imbibition through imbibition experiments.The findings reveal that:①The reservoir,with average porosity of 8.40%and average permeability of 0.642×10^(-3)μm^(2),consists principally of quartz,feldspar,and lithic fragments,with feldspathic litharenite serving as the primary rock type and illite as the chief clay mineral;②Nano-scale micro-pores and throats dominate the reservoir,with dissolution pores and intercrystalline pores serving as predominant pore types,exhibiting relatively high pore connectivity;③Imbibition efficiency is influenced by petrophysical properties,clay mineral content,and microscopic pore structure.Due to the heterogeneity of the tight sandstone reservoir,microscopic factors have a more significant impact on the imbibition efficiency of fracturing fluids;④A comparative analysis shows that average pore size correlates most strongly with imbibition efficiency,followed by petrophysical properties and clay mineral content.In contrast,the pore type has minimal impact.Micropores are vital in the imbibition process,while meso-pores and macro-pores offer primary spaces for imbibition.This study offers theoretical insights and guidance for enhancing the post-fracturing production of tight sandstone reservoirs by examining the effects of these factors on the imbibition efficiency of fracturing fluids in tight sandstones.

衡阳植烟土壤理化性状和种植年限对烟叶化学成分的影响

为全面分析衡阳市烟田土壤理化特征和烟叶质量,采集衡阳市5个植烟县(市)的代表性紫色水稻土烟田土壤样品和烟叶样品,研究不同区域土壤理化性质和种植年限对烟叶化学成分的影响,并评价烟叶质量。结果表明:衡阳紫色烟田土壤的有机质含量总体处于适中和丰富水平(96.3%),速效养分含量总体处于适中及以上水平(88.9%~94.4%),pH值有68.5%的点位处于适中水平。衡南县、衡阳县、耒阳市和常宁市烟叶总氮含量较低(<1.5%);衡阳县和常宁市烟叶烟碱含量(<1.5%)和糖碱比(<8%)较低;衡南县烟叶还原糖含量偏低(<18%),其他县域烟叶水溶性总糖偏高(>22%)。相关性分析表明,不同烟区土壤磷、钾含量和微生物生物量是影响烟叶品质的重要因素。>2 mm团聚体百分含量在植烟10 a后显著下降,<2 mm团聚体百分含量显著增加。植烟年限超过10 a的土壤全氮、有机以质、微生物生物量的下降和物理结构的破坏会对烟叶品质产生负面的影响。因此,在土壤养分总量高的烟区可适当减少化肥施用,有机质含量低和土壤团聚体的破坏严重的烟区适当增施有机肥,有助于提升衡阳烟区土壤质量和烟叶品质。

An attention-based teacher-student model for multivariate short-term landslide displacement prediction incorporating weather forecast data

Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and property.However,traditional methods have the limitation of random selection in sliding window selection and seldom incorporate weather forecast data for displacement prediction,while a single structural model cannot handle input sequences of different lengths at the same time.In order to solve these limitations,in this study,a new approach is proposed that utilizes weather forecast data and incorporates the maximum information coefficient(MIC),long short-term memory network(LSTM),and attention mechanism to establish a teacher-student coupling model with parallel structure for short-term landslide displacement prediction.Through MIC,a suitable input sequence length is selected for the LSTM model.To investigate the influence of rainfall on landslides during different seasons,a parallel teacher-student coupling model is developed that is able to learn sequential information from various time series of different lengths.The teacher model learns sequence information from rainfall intensity time series while incorporating reliable short-term weather forecast data from platforms such as China Meteorological Administration(CMA)and Reliable Prognosis(https://rp5.ru)to improve the model’s expression capability,and the student model learns sequence information from other time series.An attention module is then designed to integrate different sequence information to derive a context vector,representing seasonal temporal attention mode.Finally,the predicted displacement is obtained through a linear layer.The proposed method demonstrates superior prediction accuracies,surpassing those of the support vector machine(SVM),LSTM,recurrent neural network(RNN),temporal convolutional network(TCN),and LSTM-Attention models.It achieves a mean absolute error(MAE)of 0.072 mm,root mean square error(RMSE)of 0.096 mm,and pearson correlation coefficients(PCCS)of 0.85.Additionally,it exhibits enhanced prediction stability and interpretability,rendering it an indispensable tool for landslide disaster prevention and mitigation.

Enhancer of Shoot Regeneration 2(ESR2)regulates pollen maturation and vitality in watermelon(Citrullus lanatus)

Watermelon(Citrullus lanatus)holds global significance as a fruit with high economic and nutritional value.Exploring the regulatory network of watermelon male reproductive development is crucial for developing male sterile materials and facilitating cross-breeding.Despite its importance,there is a lack of research on the regulation mechanism of male reproductive development in watermelon.In this study,we identified that ClESR2,a VIIIb subclass member in the APETALA2/Ethylene Responsive Factor(AP2/ERF)superfamily,was a key factor in pollen development.RNA insitu hybridization confirmed significantClESR2 expression in the tapetum and pollen during the later stage of anther development.The pollens of transgenic plants showed major defects in morphology and vitality at the late development stage.The RNA-seq and protein interaction assay confirmed that ClESR2 regulates pollen morphology and fertility by interacting with key genes involved in pollen development at both transcriptional and protein levels.These suggest that Enhancer of Shoot Regeneration 2(ESR2)plays an important role in pollen maturation and vitality.This study helps understand the male reproductive development of watermelon,providing a theoretical foundation for developing male sterile materials.

Stable photocurrent-voltage characteristics of perovskite single crystal detectors obtained by pulsed bias

Photocurrent-voltage characterization is a crucial method for assessing key parameters in x-ray or y-ray semiconductor detectors,especially the carrier mobility lifetime product.However,the high biases during photocurrent measurements tend to cause severe ion migration,which can lead to the instability and inaccuracy of the test results.Given the mixed electronic-ionic charac teristics,it is imperative to devise novel methods capable of precisely measuring photocurrentvoltage characteristics under high bias conditions,free from interference caused by ion migration.In this paper,pulsed bias is employed to explore the photocurrent-voltage characteristics of MAPbBr_(3) single crystals.The method yields stable photocurrent-voltage characteristics at a pulsed bias of up to 30 V,proving to be effective in mitigating ion migration.Through fitting the modified Hecht equation,we determined the mobility lifetime products of 1.0×10^(2) cm^(2)·V^(-1)for hole and 2.78×10~(-3)cm^(2)·V^(-1)for electron.This approach offers a promising solution for accurately measuring the transport properties of carriers in perovskite.

Effectivity and safety of trifocal intraocular lenses and capsular tension rings implantation for cataract patients with axial high myopia

●AIM:To assess effectivity and safety of trifocal intraocular lenses(IOLs)and capsular tension rings in treating cataract patients with axial high myopia.●METHODS:A prospective nonrandomized controlled clinical trial was conducted.Totally 98 eyes(74 patients)who underwent femtosecond laser-assisted cataract surgery(FLACS)with trifocal IOLs were enrolled in the study and followed up for 2y after surgery:46 eyes(33 patients)with capsular tension ring implantation in the long axial lengths(AL)group(26<AL<29 mm)and 52 eyes(41 patients)in the normal AL group(22<AL<24.5 mm).Postoperative outcomes about effectivity and safety,including the subjective and objective visual quality,and postoperative complications were assessed.●RESULTS:Uncorrected distance visual acuity at 5 m and uncorrected intermediate visual acuity at 60 and 80 cm in the long AL group were significantly worse than those in the normal AL group at 3mo postoperatively(P<0.05).The differences in reading speed,spectacle independence and potential visual complaints between the two groups were not statistically significant(P>0.05).The dysfunctional lens index and total modulation transfer function(MTF)average height were similar between the two groups.The postoperative internal coma aberrations in the axial high myopia eyes were significantly higher than that in the normal AL group(P<0.05).The total satisfaction score in the long AL group(91.32±2.76)was slightly higher than that in the normal AL group(90.36±3.47),but there was no difference(P=0.136).A statistically negative correlation was found between corrected distance visual acuity(CDVA)and dysfunctional lens index(r=-0.382,P=0.009),and between CDVA and the total MTF average height(r=-0.374,P=0.01).But there was no significant correlation between CDVA and total satisfaction score(r=0.059,P=0.696).Postoperative complications mainly presented as posterior capsular opacity(PCO),retinal detachment and cystoid macular edema.There was no difference in the incidence of fundus disease(6.5%vs 3.8%,P=0.663)or PCO(17.4%vs 7.7%,P=0.217)between the two groups at two years.●CONCLUSION:The utilization of trifocal IOL and capsular tension ring implantation is beneficial for cataract patients with axial high myopia undergoing FLACS.This approach not only ensures excellent subjective feelings and objective visual quality,but also does not increase the incidence of postoperative complications.

Cardioprotective Potential of Cymbopogon citratus Essential Oil against Isoproterenol-induced Cardiomyocyte Hypertrophy:Possible Involvement of NLRP3 Inflammasome and Oxidative Phosphorylation Complex Subunits

Objective:Cymbopogon citratus(DC.)Stapf is a medicinal and edible herb that is widely used for the treatment of gastric,nervous and hypertensive disorders.In this study,we investigated the cardioprotective effects and mechanisms of the essential oil,the main active ingredient of Cymbopogon citratus,on isoproterenol(ISO)-induced cardiomyocyte hypertrophy.Methods:The compositions of Cymbopogon citratus essential oil(CCEO)were determined by gas chromatography-mass spectrometry.Cardiomyocytes were pretreated with 16.9µg/L CCEO for 1 h followed by 10µmol/L ISO for 24 h.Cardiac hypertrophy-related indicators and NLRP3 inflammasome expression were evaluated.Subsequently,transcriptome sequencing(RNA-seq)and target verification were used to further explore the underlying mechanism.Results:Our results showed that the CCEO mainly included citronellal(45.66%),geraniol(23.32%),and citronellol(10.37%).CCEO inhibited ISO-induced increases in cell surface area and protein content,as well as the upregulation of fetal gene expression.Moreover,CCEO inhibited ISO-induced NLRP3 inflammasome expression,as evidenced by decreased lactate dehydrogenase content and downregulated mRNA levels of NLRP3,ASC,CASP1,GSDMD,and IL-1β,as well as reduced protein levels of NLRP3,ASC,pro-caspase-1,caspase-1(p20),GSDMD-FL,GSDMD-N,and pro-IL-1β.The RNA-seq results showed that CCEO inhibited the increase in the mRNA levels of 26 oxidative phosphorylation complex subunits in ISO-treated cardiomyocytes.Our further experiments confirmed that CCEO suppressed ISO-induced upregulation of mt-Nd1,Sdhd,mt-Cytb,Uqcrq,and mt-Atp6 but had no obvious effects on mt-Col expression.Conclusion:CCEO inhibits ISO-induced cardiomyocyte hypertrophy through the suppression of NLRP3 inflammasome expression and the regulation of several oxidative phosphorylation complex subunits.

不同干燥方式对封鳊鱼品质的影响

为探明不同干燥方式对封鳊鱼品质及鱼肉理化性质的影响,试验采用自然、冷风、冷冻、冷风—热风联合和热泵5种干燥方式对封鳊鱼进行干燥,研究不同干燥方式对鳊鱼质量损失、干燥速率、硫代巴比妥酸值、挥发性盐基总氮、水分活度、复水率、质构特性和微观结构的影响。试验结果表明,自然干燥的干燥速率低、鱼肉复水率差、氧化最严重、腐败程度较高,但弹性和咀嚼性较好;冷冻干燥的干燥速率最快,鱼肉复水率最高,氧化和腐败程度最低,但弹性和咀嚼性差;冷风干燥的干燥速率低,但鱼肉复水率较好,仅低于冷冻干燥,氧化和腐败程度也仅高于冷冻干燥,且弹性和咀嚼性最好;热泵干燥的干燥速率较高,但鱼肉复水率低、氧化和腐败程度均较高、质构特性较差;联合干燥的干燥速率较快,但鱼肉复水率最低、腐败最严重、质构特性差。

丁香油对蟹黄鲜虾酱贮藏品质的影响

将丁香油添加到蟹黄鲜虾酱中,25℃恒温贮藏180d,通过对蟹黄鲜虾酱贮藏过程中丙二醛含量、总巯基含量、脂肪酸组成及含量、呈味物质含量进行定期检测,并结合滋味物质的味道强度值和味道当量在贮藏过程中的变化,探索丁香油对蟹黄鲜虾酱贮藏过程品质的影响。结果显示,丁香油能抑制丙二醛的生成、总巯基的降低和不饱和脂肪酸的分解,添加丁香油的蟹黄鲜虾酱呈味核苷酸、鲜味氨基酸、甜味氨基酸、游离氨基酸含量和味精当量值显著高于不添加丁香油的蟹黄鲜虾酱。研究表明,在贮藏过程中,丁香油对蟹黄鲜虾酱不仅具有抗脂肪和蛋白质氧化的作用,还能够提高其贮藏稳定性和风味。

青少年应对方式与非自杀性自伤关系的研究进展

非自杀性自伤(NSSI)在青少年中是一个重要的公共卫生问题。青少年的应对方式与非自杀性自伤有关,采取回避、自责、发泄情绪、忍耐、药物滥用、行为脱离和幻想的消极应对方式会增加NSSI的发生,而寻求社会和家人支持、合理化的积极应对方式可减少NSSI的发生。本文将对青少年的应对方式与NSSI关系的研究进展进行综述。

ROAV法分析超高压处理对小龙虾仁关键挥发性成分的影响

为了明确小龙虾仁特征性风味成分,并进一步探究超高压处理对小龙虾仁风味的影响,采用顶空固相微萃取-气相色谱-质谱联用法(SPME-GC-MS)对一定条件下超高压处理前后小龙虾仁挥发性成分进行定性定量分析,结合感觉阈值和相对气味活度值(ROAV)对其进行关键风味化合物分析,同时结合响应面多元回归分析及回归方程系数显著性检验探究超高压处理三因素对小龙虾仁风味的影响。结果显示:小龙虾仁在特定超高压条件下处理前后分别检出挥发性成分54和48种,其中同时检出的挥发性成分有37种;超高压小龙虾仁关键风味化合物为:己醛、庚醛、辛醛、壬醛、癸醛、十二醛、2-癸酮、2-十一酮和2-正戊基呋喃共9种,比未经过超高压处理的样品多出1种(2-十一酮);保压时间和施压温度对小龙虾仁风味影响显著(p<0.05),实际生产应在保证商品品质的基础上,尽量降低保压时间和施压温度,才能获得更为良好的产品风味。

基于粒子群优化的四川地震人员死亡率研究

地震发生之后,在没有展开现场调查之前,地震人员伤亡的快速评估对于地震应急救援响应具有重大意义。从四川地区收集了1970-2008年间的30个地震案例,根据美国地质勘查局（USGS）的全球地震快速评估（PAGER）系统中烈度与地震人口死亡率的经验模型,利用粒子群优化算法学习得到了四川地区各烈度下的人口死亡率。最后利用2008年汶川地震的相关数据对得到的人员死亡率模型进行了验证。仿真实验结果表明,所得到的地震人员死亡率模型对于四川地区的地震人员损失快速评估具有较好的适用性。

中医特色疗法对妊娠剧吐有效性的网状Meta分析

目的应用网状Meta分析评价中医特色治疗妊娠剧吐的有效性。方法检索从建库到2022年2月28日收录的中医特色治疗妊娠剧吐的随机对照试验,根据Cochrane偏倚风险评估工具对所筛选的文献进行质量评价,应用RevMan 5.3软件生成偏倚风险评估报告,Stata 13.1软件对数据进行统计分析及图形绘制。结果共纳入24篇文献,1660例患者,累计概率排序图(SUCRA)排序依次为:针刺>穴位按摩>艾灸>穴位注射>穴位贴敷>耳穴压豆>常规西医。结论6种中医特色治疗均优于单独常规西医治疗,且针刺疗效最佳。

Public Sentiment Analysis of Social Security Emergencies Based on Feature Fusion Model of BERT and TextLevelGCN

At present, the emotion classification method of Weibo public opinions based on graph neural network cannot solve the polysemy problem well, and the scale of global graph with fixed weight is too large. This paper proposes a feature fusion network model Bert-TextLevelGCN based on BERT pre-training and improved TextGCN. On the one hand, Bert is introduced to obtain the initial vector input of graph neural network containing rich semantic features. On the other hand, the global graph connection window of traditional TextGCN is reduced to the text level, and the message propagation mechanism of global sharing is applied. Finally, the output vector of BERT and TextLevelGCN is fused by interpolation update method, and a more robust mapping of positive and negative sentiment classification of public opinion text of “Tangshan Barbecue Restaurant beating people” is obtained. In the context of the national anti-gang campaign, it is of great significance to accurately and efficiently analyze the emotional characteristics of public opinion in sudden social violence events with bad social impact, which is of great significance to improve the government’s public opinion warning and response ability to public opinion in sudden social security events. .

An Analysis of the Evolution of Online Public Opinion on Public Health Emergencies by Combining CNN-BiLSTM + Attention and LDA

In this paper, the Foxconn epidemic event in Zhengzhou was taken as an example to analyze the evolution of online public opinion on public health emergencies. In order to improve the performance of online public opinion analysis, based on the life cycle theory and LDA theory, the emotional changes of Internet users in four stages of the Foxconn incident centered on the evolution of inscription were divided. The emotions of netizen speech at different stages are analyzed based on CNN-BiLSTM + Attention model, which uses Convolutional Neural Network (CNN) to extract local features. Bi-directional Long Short-Term Memory (BiLSTM) is used to efficiently extract contextual semantic features and long distance dependencies, and then combined with attention mechanism to add emotional features. Finally, Softmax classifier realizes text emotion prediction. The experimental results show that: compared with TextCNN, BiLSTM, BiLSTM + Attenion, CNN-BiLSTM model, the emotion classification model has better effects in the accuracy rate, accuracy rate, recall rate and F value. By analyzing the emotional distribution and evolution trend of public opinion under “text topic”, the paper accurately deconstructs the development characteristics of public opinion in public health emergencies, in order to provide reference for relevant departments to deal with public opinion in public health emergencies. .

Research on Prediction of Sentiment Trend of Food Safety Public Opinion

Emotion has a nearly decisive role in behavior, which will directly affect netizens’ views on food safety public opinion events, thereby affecting the development direction of public opinion on the event, and it is of great significance for food safety network public opinion to predict emotional trends to do a good job in food safety network public opinion guidance. In this paper, the dynamic text representation method XLNet is used to generate word vectors with context-dependent dependencies to distribute the text information of food safety network public opinion. Then, the word vector is input into the CNN-BiLSTM network for local semantic feature and context semantic extraction. The attention mechanism is introduced to give different weights according to the importance of features, and the emotional tendency analysis is carried out. Based on sentiment analysis, sentiment value time series data is obtained, and a time series model is constructed to predict sentiment trends. The sentiment analysis model proposed in this paper can well classify the sentiment of food safety network public opinion, and the time series model has a good effect on the prediction of food safety network public opinion sentiment trend. .