Tag Archives: google

Ideas and Improvements for Apple’s Siri

6 Replies
Siri, the personal digital assistant

Siri, the personal digital assistant

Recently I’ve been quite interested in Apple’s Siri, ever since I received my iPhone 4S and watching the WWDC Developer’s conference. At first I thought it was just a novelty, but upon seeing the upcoming features in iOS 6, my interest has been heightened. I’m interested in machine learning, AI, UI design, and aggregating content, as I’ve tried to do before. See: History of speech AI and How Siri works.

Concept and Functionality
Siri is essentially a search / AI engine thats powered by the voice.

The original Siri application relied upon a number of partners, including:
OpenTable, Gayot, CitySearch, BooRah, Yelp, Yahoo Local, ReserveTravel, Localeze for restaurant and business questions and actions;
Eventful, StubHub, and LiveKick for events and concert information;
MovieTickets, Rotten Tomatoes, and the New York Times for movie information and reviews;
Bing Answers and Wolfram Alpha for factual question answering;
Bing, Yahoo, and Google for web search.
Apple integrated it with default iOS functionality, such as contacts, calendars and text messages. It also supports search from Google, Bing, Yahoo, Wolfram Alpha and Wikipedia. Siri also works with Google Maps and Yelp! search in the United States only.

Context specific service searching
What I would like to see is Siri searching certain services depending on what keywords are being said. For example, if I say a query such as “What is the Earth’s circumference?” or “What is the area of a circle?” then it should direct me to Wolfram Alpha because Siri recognizes these queries as mathematical questions.
Asking about the news should take me to the New York Times, CNN or maybe show me some blog posts, tweets, etc.
Famous persons or companies can take me to their wikipedia page, twitter page, facebook page and website.
If I asked a knowledge question such as “Who was Rene Descartes?” or “Who invented basketball?” then it should direct me to a Wikipedia article or Yahoo/Bing Answers page. Location queries should pull up Google (or soon Apple) Maps.
Programming questions should take me to StackOverflow or some related forums.
Food queries will pull up Yelp and OpenTable to make a reservation and read reviews.
Asking about travel should pull up Priceline/Expedia/Kayak and TripAdvisor.
Movie based queries should take me to Fandango and Rottentomatoes, concert tickets to TicketMaster and event tickets to EventBrite.
Job related queries can take me to LinkedIn or Glassdoor.
In short, Siri should link all these Web 2.0 companies (that all have an API) together. Its the ultimate content aggregator.

update:
I think it would be better if you said the name of the service that you want Siri to pull from if there’s multiple sources.
So for example, if I were to say “Java, Wikipedia” – then Siri would pull from Wikipedia. But “Java, Google” would just do a google search,
and “Java, Stack Overflow” would search stack overflow for the keyword. This would make it easy and intuitive for Siri to bring up the correct response.

Integration with web and OS X
How about having Siri come to Macs and PCs? How about having Siri be accessible as a web application running on the cloud? Almost all computers come with microphones, so why not? I see the advantage of making Siri exclusive to iOS but soon I think Apple should make it widely available.

Text input
The main problem with me using Siri is that it looks awkward when I’m talking to it in a public place, or using it at a meeting can be distracting. So Siri should take text input to fix that. I’m sure some Java parser in the backend is translating natural speech into strings anyway, so it shouldn’t be too hard to make a text based option.

Expanding services
Siri should be able to integrate with countless Web 2.0 services. And it should be locale specific. If I’m in China, then Siri should integrate with Baidu, QQ, Sina, etc. If I’m looking for a deal, then Siri can pull up Groupon. Point is, Siri can be the glue that ties all these services together. And maybe pulling up Youtube when I’m looking for a funny cat video or something. Perhaps Siri can learn from users in general, in context, and know what to say in response depending on what other users have said to it (a la Cleverbot).

Social integration and Ad delivery
Siri now provides Apple with the same data as Facebook. It can learn about a user’s behavior, their location, their preferences, their hobbies, etc. Anything about a user can be learnt through Siri, so now Apple can do anything and everything that Facebook can do, including delivering targeted ads. If Siri knows you’ve been going to mexican restaurants lately, maybe it can show you an ad from another mexican restaurant nearby. Or maybe suggest you to buy Star Wars from iTunes or Netflix if you’ve been watching sci-fi movies lately. Or maybe show some ads from ESPN if you’ve been watching or asking about sports alot. Or direct me to the iTunes store for Usher’s new album or concert if I’ve been listening to a lot of his songs. Since Siri knows everything about you, it can be the ultimate ad and content delivery vessel.

Better Multilingual support and Translation
Siri will integrate with over 15 languages with iOS 6, so I would like to see quality recognition for different dialects and accents, particularly for Asian languages. And this would probably require a lot of native speakers and language specialists, but I think if Siri can do this well, then it could also be the best translator (by storing speech patterns and tonal variance). We all know Google Translate sucks for Asian languages, so I’m sure Apple can do it better!

Now that Siri is multilingual and will integrate with car manufacturers soon (potentially replacing navigation), I see lots of potential with it in the future. It has the possibility of overshadowing Google or Facebook, since it both searches by voice, and retains user information. So these are just some of my ideas for future improvements from Siri, but where it goes remains to be seen.

Analog vs Digital; gradual replacement of daily devices by digital products

1 Reply

As things become more and more digitized these days, we find more and more of our daily devices being replaced by new digitized mediums. Please note that when I use ‘analog’ I mean the original medium.

Vinyl vs CD:
An example is music players. Back in the old days, we used a device called the record player to listen to music. This device used a medium called vinyl which is an exact copy of the soundwaves pressed into it. What you hear from each LP is the exact reproduction of the music; there are no compressed bits of audio, no 16-bit compression, 320kbps streaming, or whatever. This is as close as music gets to a live performance (which is pure analog because you hear it with your ears at the time it plays). It has since been replaced by CDs and MP3s, which basically takes samples of the sound and compresses them. Whether or not it sounds worse depends on different people. Which would you choose? Vinyl (analog) or CD/MP3 (digital)?

Vinyl and MP3

Vinyl and MP3

Film vs Digital photos:
Back in the old days, we used a film camera to take pictures and record movies. film is available in different mm (35mm, 16mm, 8mm) which represents what kind of film format is used. Similarly, movie projectors depends on the size of the reel and the film its using. Film has been superseded by Digital Cameras, DSLRs, Camcorders, and even phones(!) today. But some still say that old film cannot be replaced. It’s the ‘analog’ medium. There is no sense of megapixels or size of movie in gigabytes of whatever. Light is focused and captured onto photographic films which is developed in a dark room. There is no concept of dark rooms or film negatives in the digital age today. Instead, there is only how many megapixels, what is the storage size, aperture size, lens size, HD quality, etc. In addition, digital photos cannot be physically shared unless they are printed, which may not result in the same feeling as film. Which would you choose? Film Camera (analog) or Digital Camera (digital)?

Film vs Digital

Film vs Digital

Other trends
Although Cameras and Music players are the most prominent, digital products have been replacing almost every product that we produced in the 20th century. Radio has been replaced by Spotify, Last.fm and Pandora. TV is gradually getting replaced by Netflix, Hulu and Youtube. Ebooks using Amazon’s Kindle and Nook readers have been replacing traditional books. iPhones and Android devices have been replacing landline (old school) telephones. How often do you see pay phones nowadays? What about painting a picture using oil or watercolor? Now you can do that on a tablet! What happened to board games? Now we play Angry Birds on the phone. An entire drawer of documents can now be fit onto a small USB key. Shopping no longer needs to be done at brick and mortar stores, just go to Ebay and Amazon. Who needs Encyclopedia Britannica when you have Wikipedia and Google? Asking friends for reviews has been replaced by Yelp. Nobody uses Maps anymore when you have Google Maps. No need to hire expensive stock advisors when you have Google Finance. Who uses typewriters when you have Google Docs? No need to cut out coupons when you have Groupon. Who reads newspapers when you can just go to CNN? What used to be handwritten letters sent across the world to an eager penpal months later has now been replaced by email, typed in an instant and received in an instant. And face to face contact is gradually being replaced by Skype, texting, instant messaging, and Facebook. Heck, I”m even writing a blog post that only two decades ago would have warranted a small diary! (blogging never existed back then, unless you count newspaper articles).

While I do like how there are new, more convenient ways of living, sometimes I long for the more meaningful ways that life used to be lived. Living without a phone for a few weeks has taught me to enjoy the simpler things in life rather than commenting on someone’s Facebook wall (like for example, actually going up to the person to wish them a happy birthday). And I kind of miss that, now that digital products have replaced everything. What do you think about this topic? please leave your comment.

I also took the opportunity to take some pictures with Instagram. I wonder if Ansel Adams would be proud of me. Would he have thought that one day, a miniature sized phone in my pocket would be able to take a picture of this quality? and share it without actually handing it physically to anyone?

Sunset at SF's Ocean Beach

Sunset at SF's Ocean Beach

Sakura at Golden Gate Park

Sakura at Golden Gate Park

Hunger games, Korean grammar, and Mobile Computing

2 Replies

Hunger Games

I just finished watching the Hunger Games in theaters. You probably all heard of it by now. I’ve never read the book, so after watching it here’s my thoughts. I think the story seemed like it jumped a long too fast, a common problem when adapting books to movies. Some characters are not fleshed out at all. There’s gore in the movie even though its PG-13. but overall it was an okay movie. If you’ve watched Twilight and Harry Potter, there’s more of the same teenage fiction here, though somewhat more mature. I still can’t help thinking the book should have been written with an Asian American or Hispanic American lead. The movie felt like it was out of the 1950s. I mean, mostly Caucasian crowd with some scattering of African Americans. If this takes place in the future United States, wouldn’t white people be a minority by then? But I’m sure even if the book did have Asians, Hollywood would never cast an Asian American actor for a blockbuster film, of course not. Though I might add that the Asian American community is really looking for a rolemodel right now. What Jeremy Lin has demonstrated is that Asians are underrepresented, and overlooked by media, and we should strive to have more Asians out there doing creative arts like acting and performing, and being athletes, rather than being the usual business people / scientists / engineers / etc that are not prominent in the media.

Korean Grammer

Still some outstanding questions about Korean grammar.

-what does adding -ㄴ to a verb do? ie. 한다vs하다, 가다vs간다

-what does adding -긴 do?

-difference between 이야 and 이니?

-내가 vs 나는?

-겠다 vs 거야 vs 야지 for future tense (will do)

-what does adding -지 do? like 하는지,하지서 vs 하면,하지면

-what does adding -나 and -까 do?

-무슨 vs 뭐?

I’m studying Korean.
‎1. 난 한국어를 공부해.
2. 난 한국어를 공부하고 있어.
3. 난 한국어를 공부하지.
4. 난 한국어를 공부한다. (more for writing).

I’ll study Korean.
1. 난 한국어를 공부해야지.
2. 난 한국어를 공부할 거에요.
3. 난 한국어를 공부할거야.
4. 난 한국어를 공부할게.
5. 난 한국어를 공부할래.
6. 난 한국어를 공부하겠어.

I should study Korean
1. 난 한국어를 공부해야 돼.

I studied Korean.
1. 난 한국어를 공부했어.

나는 사과를 먹었어.
나는 사과를 먹었는데.
나는 사과를 먹었잖아.
나는 사과를 먹었지.
나는 사과를 먹었다고.

Mobile Computing Trends

There’s a good article on mobile computing right here:

http://www.businessinsider.com/the-future-of-mobile-deck-2012-3?op=1

Basically it talks about the future of mobile computing. We know that mobile apps and mobile web content will continue to grow at a rate faster than PCs did. But I think this article draws its results primarily from research done in the US. The USA is not a proxy for the rest of the world. We are the richest country in the world, and that explains part of the reason why mobile penetration and mobile content consumption is so high here. The key to get from this is that feature phones are still widely used in developing nations in Asia, Latin America and Africa. Those emerging markets are where most of the growth is going to be. Thus to make smartphones more popular, we should focus on making them more affordable to everyone. Once that happens, I can imagine many more apps designed and interpreted with multilingual use, and locale-specific implementations. Right now China is one of Apple’s biggest consumers, and they will only get bigger. In fact, the mindset we have to adopt for the future is not only to cater to US consumers (where the majority of smartphone users live) but to the rest of the world as well. In time, I believe this is what will happen.

On a side note, ever wonder why Chinese sites look so different than American sites? Look at www.netease.com or www.sohu.com and you can see that its very cluttered and alot of information on once page. Contrast this with the simpler web 2.0-style interfaces that American sites use, a la Twitter or Foursquare. I wonder what would happen if we take some American apps (most of which deliver content through the cloud) and port it over to China? How would sites like www.mint.com or www.foursquare.com or www.groupon.com be perceived if we make a chinese version and locale specific? That would be interesting to find out, and a good opportunity as well.