With the development of information technology, human beings are constantly producing a large amount of information at all times. How to obtain the information that users are interested in from the large amount of information has become an issue of great concern to users and even business managers. In order to solve this problem, from traditional machine learning to deep learning recommendation systems, researchers continue to improve optimization models and explore solutions. Because researchers have optimized more on the recommendation model network structure, they have less research on enriching recommendation model features, and there is still room for in-depth recommendation model optimization. Based on the DIN\cite{Authors01} model, this paper adds multi-head and multi-modal modules, which enriches the feature sets that the model can use, and at the same time strengthens the cross-combination and fitting capabilities of the model. Experiments show that the multi-head multi-modal DIN improves the recommendation prediction effect, and outperforms current state-of-the-art methods on various comprehensive indicators.

The travel marketing platform of Alibaba serves an indispensable role for hundreds of different travel scenarios from Fliggy, Taobao, Alipay apps, etc. To provide personalized recommendation service for users visiting different scenarios, there are two critical issues to be carefully addressed. First, since the traffic characteristics of different scenarios, it is very challenging to train a unified model to serve all. Second, during the promotion period, the exposure of some specific items will be re-weighted due to manual intervention, resulting in biased logs, which will degrade the ranking model trained using these biased data. In this paper, we propose a novel Scenario-Aware Ranking Network (SAR-Net) to address these issues. SAR-Net harvests the abundant data from different scenarios by learning users' cross-scenario interests via two specific attention modules, which leverage the scenario features and item features to modulate the user behavior features, respectively. Then, taking the encoded features of previous module as input, a scenario-specific linear transformation layer is adopted to further extract scenario-specific features, followed by two groups of debias expert networks, i.e., scenario-specific experts and scenario-shared experts. They output intermediate results independently, which are further fused into the final result by a multi-scenario gating module. In addition, to mitigate the data fairness issue caused by manual intervention, we propose the concept of Fairness Coefficient (FC) to measures the importance of individual sample and use it to reweigh the prediction in the debias expert networks. Experiments on an offline dataset covering over 80 million users and 1.55 million travel items and an online A/B test demonstrate the effectiveness of our SAR-Net and its superiority over state-of-the-art methods.

Apple will soon offer the HomePod mini in three new colors. Announced during the company's Unleased event on Monday, the new yellow, orange and blue colorways will join the existing white and space gray models in November. The price will remain unchanged at $99 in the US. Apple first announced the HomePod mini last fall. As you'd expect, the speaker comes with deep integration with the company's other products. In addition to Siri support, its built-in U1 ultra-wideband chip allows you to quickly and easily hand off audio from your iPhone to the speaker.

Apple thinks it has a simple way to boost Apple Music adoption: limit control in return for a lower fee. The company has introduced an Apple Music Voice Plan that offers access to the full song catalog for just $5 per month, so long as you're willing to rely solely on Siri control. It's pitched as ideal for HomePod and AirPod owners and others who are more likely to use a voice assistant than tap their phone. The new tier will be available later in the fall in 17 countries, including the US, UK and Canada. You can start a trial by asking Siri to "start my Apple Music Voice trial."

Most people associate artificial intelligence and machine learning with futuristic applications like Terminator, Hal or Samantha, but applications using AI and ML are more common than you think. We have Siri, Alexa and Google Assistant. The ML algorithm recommends movies on Netflix, and we shouldn't forget about the Tesla self-driving car.

When people think about artificial intelligence (AI) today, they might think of computers that can speak to us like Alexa or Siri, or grand projects like self-driving cars. These are very exciting and attention-grabbing, but the reality of AI is actually thousands of tools and apps running quietly behind the scenes, making our lives more straightforward by automating simple tasks or making predictions. This is true across every industry and business function, and particularly true in marketing, where leveraging AI to put products and services in front of potential customers has been standard practice for some time, even though we may not always realize it! In business today, the term AI is used to describe software that is capable of learning and getting better at doing its job without input from humans. This means that while we've become used to using machines to help us with the heavy lifting, now they can start to help us with jobs that require thinking and decision-making, too.

Adversarial attacks against commercial black-box speech platforms, including cloud speech APIs and voice control devices, have received little attention until recent years. The current "black-box" attacks all heavily rely on the knowledge of prediction/confidence scores to craft effective adversarial examples, which can be intuitively defended by service providers without returning these messages. In this paper, we propose two novel adversarial attacks in more practical and rigorous scenarios. For commercial cloud speech APIs, we propose Occam, a decision-only black-box adversarial attack, where only final decisions are available to the adversary. In Occam, we formulate the decision-only AE generation as a discontinuous large-scale global optimization problem, and solve it by adaptively decomposing this complicated problem into a set of sub-problems and cooperatively optimizing each one. Our Occam is a one-size-fits-all approach, which achieves 100% success rates of attacks with an average SNR of 14.23dB, on a wide range of popular speech and speaker recognition APIs, including Google, Alibaba, Microsoft, Tencent, iFlytek, and Jingdong, outperforming the state-of-the-art black-box attacks. For commercial voice control devices, we propose NI-Occam, the first non-interactive physical adversarial attack, where the adversary does not need to query the oracle and has no access to its internal information and training data. We combine adversarial attacks with model inversion attacks, and thus generate the physically-effective audio AEs with high transferability without any interaction with target devices. Our experimental results show that NI-Occam can successfully fool Apple Siri, Microsoft Cortana, Google Assistant, iFlytek and Amazon Echo with an average SRoA of 52% and SNR of 9.65dB, shedding light on non-interactive physical attacks against voice control devices.

The population is aging, and becoming more tech-savvy. The United Nations predicts that by 2050, one in six people in the world will be over age 65 (up from one in 11 in 2019), and this increases to one in four in Europe and Northern America. Meanwhile, the proportion of American adults over 65 who own a smartphone has risen 24 percentage points from 2013-2017, and the majority have Internet in their homes. Smart devices and smart home technology have profound potential to transform how people age, their ability to live independently in later years, and their interactions with their circle of care. Cognitive health is a key component to independence and well-being in old age, and smart homes present many opportunities to measure cognitive status in a continuous, unobtrusive manner. In this article, we focus on speech as a measurement instrument for cognitive health. Existing methods of cognitive assessment suffer from a number of limitations that could be addressed through smart home speech sensing technologies. We begin with a brief tutorial on measuring cognitive status from speech, including some pointers to useful open-source software toolboxes for the interested reader. We then present an overview of the preliminary results from pilot studies on active and passive smart home speech sensing for the measurement of cognitive health, and conclude with some recommendations and challenge statements for the next wave of work in this area, to help overcome both technical and ethical barriers to success.

National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China, School of Artificial Intelligence, University of Chinese Academy of Sciences, China, and Peng Cheng Laboratory, China The cold-start recommendation is an urgent problem in contemporary online applications. It aims to provide users whose behaviors are literally sparse with as accurate recommendations as possible. Many data-driven algorithms, such as the widely used matrix factorization, underperform because of data sparseness. This work adopts the idea of meta-learning to solve the user's cold-start recommendation problem. We propose a meta-learning based cold-start sequential recommendation framework called metaCSR, including three main components: Diffusion Representer for learning better user/item embedding through information diffusion on the interaction graph; Sequential Recommender for capturing temporal dependencies of behavior sequences; Meta Learner for extracting and propagating transferable knowledge of prior users and learning a good initialization for new users. The extensive quantitative experiments on three widely-used datasets show the remarkable performance of metaCSR in dealing with user cold-start problem. Meanwhile, a series of qualitative analysis demonstrates that the proposed metaCSR has good generalization. Recommendation systems (RS) intend to address the information explosion by finding a set of items for users to meet their personalized interests in many online applications, such as E-commerce websites [17], social networks [14], video-sharing sites [3] and news websites [36]. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Abstracting with credit is permitted.

The ability to integrate multiple sources of information for business is revolutionized using Artificial Intelligence. Business strategy becomes a complex part due to the rise in competition. Using AI, we can perform certain tasks which fall beyond human efforts. A basic example of that is high-frequency stock trading. Let's look at particular areas of AI which help in revenue growth management.