Ponekad je sve što trebate je razgovarati s nekim. Netko tko te može razveseliti na svoj način, netko tko je toliko pun života i brbljav da zaboraviš sve svoje probleme u životu. Netko tko vas zabavlja time što dolazi bolje od vaših očekivanja. Svima nije tako ugodno razgovarati s drugim 'ljudima' o stvarima, ali postoje neki znatiželjnici koji razgovaraju s umjetnom inteligencijom. Evo, Ruuh dolazi do slike.

Ruuh je sposoban saslušati nečije pitanje, otkriti njegove emocije, saznati više o korisnikovoj pozadini i dati odgovarajuće odgovore i još mnogo toga. To poboljšava njihovu povezanost i odnos koji dijele s korisnikom. To izravno implicira na vrijednije i razumnije razgovore između chatbota i korisnika.

Ruuh je dobar u vođenju razgovora

Bez uključivanja emocija, postojanje chatbota je beskorisno. Sama^(Just) mogućnost da odgovorite bez ikakve osobne veze čini chat formalnim i mnogo puta nezanimljivim. Chatbot je zanimljiv samo ako je u stanju voditi razgovore na temelju emocija uključenih u njega. O tome, Microsoft kaže,

Building a conversational layer in Ruuh helps her develop relationships so users can be more open, more casual and more engaged. This leads to better, more honest and natural conversations that ultimately lead to added value and a better experience for users.

Cilj izgradnje Ruuha

Glavni Microsoftov cilj iza izgradnje ovog chatbot-a s AI-om bio je da ga napravi za mlade, tehnički potkovane rane korisnike u Indiji^(India) . Već je trebao biti sličan Microsoftovom kineskom chatbotu^(Chatbot) pod nazivom Xiaoice . Ruuh je više digitalni prijatelj nego samo digitalni asistent. Ruuh je softver koji nije samo dio koda; to je tvoj prijatelj.
Kako funkcionira duboko učenje.

Ruuh je izmišljeni lik, to svi znamo. Ali njezin je lik napravljen po uzoru na mladu, urbanu djevojku iz Indije^(India) koja ima oko 18-24 godine. Čini se da je zainteresirana za pop kulturu i izvrsna je u upotrebi tečnog urbanog slenga koji se koristi u Indiji^(India) .

Prvi korak u stvaranju Ruuha^(Ruuh) bio je prikupljanje podataka. Trebala je biti ljubazna i duhovita. Izvor za ovu osobnost za Ruuh bili su razgovori u stvarnom vremenu, razgovori na društvenim^{(Social Media)} mrežama, forumi, društvene platforme i servisi za razmjenu poruka gdje se podaci prikupljaju kako bi se anonimno poboljšalo korisničko iskustvo.

Zatim su morali precizirati korisne podatke koje su prikupili. Ovaj korak je 70% ukupno prikupljenih podataka smatrao beskorisnim i uklonjen je. Microsoft se pobrinuo da nema uvredljivih komentara za ljude u SAD-u, Velikoj Britaniji i Australiji^(Australia) te bilo kakvih seksističkih ili političkih komentara.

Sada su se ti pročišćeni i korisni podaci trebali primijeniti u odabranom modelu. Ovaj model je bio cDSSM ili konvolucijski duboko strukturirani semantički model^{(Deep Structured Semantic Model)} . Ovo je noviji model i pomaže u boljem i dubljem ljudskom ponašanju u AI.

Kako cDSSM rezultira boljom umjetnom inteligencijom

Identifikacija upita^{(Query Identification)}

Identifikacija^{(Identification)} upita prvi je korak u stvaranju AI više sličnih ljudima^(Humans) . Algoritam preuzima ulazni upit i traži u bazi podataka slična pitanja. Ovo se također naziva dohvaćanje informacija^{(Information Retrieval)} ili IR.
Na primjer^(Example) : ako je upit "kako napraviti tjesteninu od piletine?", Ruuh analizira podatke i pronalazi više uzoraka sličnih pitanja.

Rangiranje odgovora^{(Ranking responses)}

Ovdje algoritam razvrstava odgovore na temelju toga koliko su uzorci relevantni. Tako se kao izlaz daju najrelevantniji podaci.

Razumijevanje konteksta^{(Understanding Context)}

Sada bi moglo biti besmisleno ako chatbot zaboravi o čemu korisnik govori.

For Example: Question: “Do you like ice cream, Ruuh?”

Ruuh: “Yes, I like it.”

Question: “which flavors do you like?”

Ruuh: “Chocolate and Vanilla.”

Sada je Ruuh znao da se drugo pitanje odnosi na sladolede i stoga je odgovor bio prikladan.

Kako bi bio tako dobar u svojoj funkcionalnosti, Ruuhov algoritam neprestano traži podatke u prethodnim upitima korisnika i razumije kontekst o čemu korisnik govori.

Otkrivanje i odgovor na emocionalne znakove^{(Detection and response to emotional cues)}

Sada, više ljudski znači otkrivanje emocija. To je tako jer ljudi imaju emocionalni način razmišljanja. Dakle, kako bi otkrila emocije korisnika, Ruuh traži uzorke u porukama chata koje je primila i vrstu emojija koji se koriste u chatu. Dakle, kada razgovarate s njom, ona zna jeste li sretni, tužni, uzbuđeni ili uznemireni.

Presuda^(Verdict)

Ruuh je moćan i izvrstan način da se pokaže moć onoga što AI danas može učiniti kako bi se ponašao kao ljudsko biće. Sa snagom cDSSM-a, Ruuh je puno pametniji.

Microsoft kaže:

To summarize, the model combined with deep learning integrates context and the user’s message to extract the appropriate response. The model extracts the context from the message, retrieves previous messages, creates a group of appropriate responses, ranks them according to relevance, and generates the final output.

Hajde da to bolje razumijemo na primjeru. Ako bi korisnik upitao Ruuha^(Ruuh) , " Koji^(Which) su preljevi za pizzu najpopularniji?", Ruuh bi identificirao upit kao o "preljevima za pizzu" i dohvatio najrelevantnije odgovore na temelju ovog upita. Ruuh bi rangirao slične odgovore iz baze podataka na temelju relevantnosti kako bi generirao najprikladniji odgovor. Uz kontekstualnu svijest, Ruuh može lako odgovoriti na naredna pitanja kao što su: "Koja vam se sviđaju?" odgovorom "Volim gljive i ananas".

Ruuh sada ima godinu dana i moram reći da je budućnost umjetne inteligencije svijetla zbog ove brzine kojom vidimo kako se sve više i više razvija AI, uskoro ćemo vidjeti pametnije stvari oko sebe. Timu u Microsoftu^(Microsoft) želimo puno sreće i nadamo se da će nas i ubuduće iznenađivati ​​ovim sjajnim proizvodima.

Više o Ruuh^(Ruuh) možete pročitati  ovdje u službenom članku Microsofta –^{(Microsoft –)} i isprobati je ovdje na Facebooku^{(on Facebook)} .^{(on Facebook.)}

Meet Microsoft Ruuh chatbot on Facebook - All you need to know!

Sometimes all you need is to talk to someone. Someone whо can cheer you up in their own way, someone who is so full of lіfe and chatty that you forget all your problems in life. Someone that amuses you by coming bettеr than yоur exрectations. Everyone is not so comfortable about talking to other ‘humans’ about things, but there are some curious рeople who do talk to AI. Here, Ruυh comeѕ to thе picture.

Ruuh is capable of listening to one’s question, detect their emotions, learn about the user’s background and make appropriate replies and more. This enhances their bonding and the relationship they share with the user. It directly implies to more valuable and sensible chats between the chatbot and the user.

Ruuh is good at making conversations

Without the involvement of emotions, the existence of chatbots is useless. Just being able to reply without any personal connection makes the chat formal and many times uninteresting. A chatbot is interesting only if they are able to make conversations on the foundation of emotions being involved with it. About this, Microsoft says,

Building a conversational layer in Ruuh helps her develop relationships so users can be more open, more casual and more engaged. This leads to better, more honest and natural conversations that ultimately lead to added value and a better experience for users.

Aim of building Ruuh

Microsoft’s main aim behind building this AI-powered chatbot was to make it for the young, tech-savvy early adopters in India. It was already meant to be similar to Microsoft’s Chinese Chatbot named Xiaoice. Ruuh is more of a digital friend rather than just a digital assistant. Ruuh is a software that is not just a piece of code; it is your friend.
How deep learning works.

Ruuh is a fictional character, we all know that. But her character is modeled after a young, urban Indian girl who is about 18-24 year old. She seems to be interested in Pop culture and is great at the usage of fluent urban slangs used in India.

The first step in creating Ruuh was to collect data. She was meant to by affable as well as witty. The source for this personality for Ruuh was real-time conversations, Social Media conversations, forums, social platforms and messaging services where the data is collected to improve user experience anonymously.

Next, they had to refine the useful data that they collected. This step took 70% of total data collected as useless and was removed. Microsoft made sure that there are no offensive comments for people in the US, UK and Australia and any sexist or political comments.

Now, this refined and useful data was to be applied in the selected model. This model was the cDSSM or Convolutional Deep Structured Semantic Model. This is a newer model and helps in more better and deeper human-like behavior in AI.

How cDSSM results in better AI

Query Identification

Query Identification is the first step in making AI more like Humans. An algorithm takes the input query and looks in the database for similar questions. This is also referred to as Information Retrieval or IR.
For Example: if the query is, “how do I make chicken pasta?”, Ruuh analyzes the data and finds multiple samples of similar questions.

Ranking responses

Here, the algorithm sorts out the responses based on how relevant the samples are. This is how the most relevant data is given as an output.

Understanding Context

Now, it might be pointless if the chatbot forgets what the user is talking about.

For Example: Question: “Do you like ice cream, Ruuh?”

Ruuh: “Yes, I like it.”

Question: “which flavors do you like?”

Ruuh: “Chocolate and Vanilla.”

Now, Ruuh knew that the second question was regarding ice creams and hence, the reply was appropriate.

To be so good at her functionality, Ruuh’s algorithm constantly looks up for data in the previous queries from the user and understands the context about what the user is talking about.

Detection and response to emotional cues

Now, more human-like means detection of emotions. This is so because humans have emotional mindsets. So, in order to detect users’ emotions, Ruuh looks up for patterns in chat messages received by her and the type of emojis used in the chat. So, when you are talking to her, she knows if you are happy, sad, excited or upset.

Verdict

Ruuh is powerful and a great way to show the power of what AI can do today to behave like a human being. With the power of cDSSM, Ruuh is much smarter.

Microsoft says:

To summarize, the model combined with deep learning integrates context and the user’s message to extract the appropriate response. The model extracts the context from the message, retrieves previous messages, creates a group of appropriate responses, ranks them according to relevance, and generates the final output.

Let’s understand this better with an example. If a user asked Ruuh, “Which pizza toppings are most popular?”, Ruuh would identify the query as about ‘pizza toppings’ and retrieve the most relevant answers based on this query. Ruuh would rank similar answers from the database based on relevance to generate the most appropriate response. With contextual awareness, Ruuh can easily answer follow-on questions such as, “Which ones do you like?” by replying “I love mushroom and pineapple”.

Ruuh is now one year old, and I must say that the future of AI is bright because of this rate at which we are seeing more and more advanced AI emerging, we are about to see smarter things around us very soon. We wish the team at Microsoft, a very best of luck and I hope they will keep surprising us in the future with these great products.

You can read more about Ruuh here on the official article by Microsoft – and give her a try here on Facebook.

Related posts

• Zoom vs Microsoft Teams vs Google Meet vs Skype

• Opozovite pristup treće strane s Facebooka, Googlea, Microsofta, Twittera

• Kako dodati Zoom u Microsoft Teams

• Microsoft Intune se ne sinkronizira? Prisilite Intune na sinkronizaciju u sustavu Windows 11/10

• Postavite datum isteka lozinke za Microsoft račun i lokalni račun

• Ažuriranja Microsoft Storea zaglavila su na čekanju ili pokretanju preuzimanja

• Što je ASD datoteka i kako je otvoriti u programu Microsoft Word?

• Kako instalirati Chrome teme na preglednik Microsoft Edge

• Microsoftov pomoćnik za udaljenu radnu površinu za Windows 10

• Microsoftov račun koji ste unijeli ne postoji

• Ispravite pogrešku prijave u Microsoft Store 0x801901f4 u sustavu Windows 11/10

• Dodajte gumb Početna u preglednik Microsoft Edge

• Popravite pogrešku u trgovini Microsoft Store 0x80072F7D

• Kako ukloniti gumb izbornika Proširenja s alatne trake Microsoft Edge

• Kako koristiti funkciju HLOOKUP u programu Microsoft Excel

• Kako napraviti knjižicu ili knjigu u programu Microsoft Word

• Popravi pogrešku u trgovini Microsoft Store 0x87AF0001

• Pogreška Microsoft Storea 0x80072F05 - Poslužitelj je posrnuo

• Microsoft Excel pokušava oporaviti vaše podatke

• Kako pohvaliti nekoga u Microsoftovim timovima za dobro obavljen posao