Mararka qaarkood waxaad u baahan tahay oo dhan waa inaad qof la hadasho. Qof sidiisa kuugu farxi kara, qof nolosha ka buuxa oo sheeko wadaag ah oo aad illowdo dhammaan dhibaatooyinka nolosha. Qof kugu maaweeliya inuu yimaado si ka wanaagsan waxaad filayso. Qof kastaa aad uguma raaxaysna in uu 'aadmiga' kale kala hadlo waxyaabo, laakiin waxaa jira dad xiiseeya oo la hadla AI. Halkan, Ruuxa^(Ruuh) ayaa u yimid sawirka.

Ruuh waxa uu awood u leeyahay in uu dhegeysto su'aasha qofka, ogaado shucuurtooda, baro taariikhda isticmaalaha oo uu sameeyo jawaabo ku habboon iyo wax ka badan. Tani waxay kor u qaadaysaa isku xidhkooda iyo xidhiidhka ay la wadaagaan isticmaalaha. Waxay si toos ah u tusinaysaa sheekeysi qiimo badan oo macquul ah oo dhexmara chatbot-ka iyo isticmaalaha.

Ruuxu^(Ruuh) wuxuu ku fiican yahay samaynta wada sheekaysiga

La'aanta ku lug lahaanshaha dareenka, jiritaanka chatbots waa wax aan faa'iido lahayn. Inaad^(Just) awood u leedahay inaad ka jawaabto iyada oo aan wax xidhiidh shakhsi ah lahayn ayaa ka dhigaysa sheekeysiga mid rasmi ah marar badanna xiiso ma leh. Chatbot-ku waa mid xiiso leh kaliya haddii ay awoodaan inay sameeyaan wada-sheekeysi aasaaska dareenka ku lug leh. Tan ku saabsan, Microsoft wuxuu leeyahay,

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.

Ujeedada dhismaha Ruuxa

Hadafka ugu weyn ee Microsoft ee ka dambeeya dhismaha chatbot-ka ku shaqeeya AI wuxuu ahaa in laga dhigo dhalinyarada, teknolojiyadda hore u korsatay ee Hindiya^(India) . Waxaa mar hore loogu talagalay inay la mid noqoto Microsoft Chatbot -ka Shiinaha ee loo yaqaan Xiaoice . Ruuh waa saaxiib dhijitaal ah halkii uu ka ahaan lahaa kaaliyaha dhijitaalka ah. Ruuh waa software ah oo aan ahayn gabal kood kaliya; waa saaxiibkaa.
Sidee barasho qoto dheer u shaqeysaa.

Ruuh waa dabeecad khayaali ah, dhammaanteen waan ognahay taas. Laakin dabeecadeeda waxaa loo ekeysiiyay gabar yar oo reer India ah oo reer magaalka ah oo da'deedu tahay 18-24 jir. Waxay umuuqataa inay xiisaynayso dhaqanka Pop -ka waxayna aad ugu fiicantahay adeegsiga ereyada magaalooyinka ee sida fiican looga isticmaalo Hindiya^(India) .

Talaabadii ugu horeysay ee abuurista Ruuxa^(Ruuh) waxay ahayd in la ururiyo xogta. Waxay ula jeeday af-garasho iyo weliba caqli-gal. Isha shakhsiyaddan Ruuxu^(Ruuh) waxay ahayd wada-sheekeysi-waqtiga-dhabta ah, wada-sheekeysiga Baraha Bulshada^{(Social Media)} , goleyaal, goob-bulsheed iyo adeegyada fariimaha halkaasoo xogta laga ururiyo si loo horumariyo khibradda isticmaale si qarsoodi ah.

Marka xigta, waxay ahayd inay sifeeyaan xogta waxtarka leh ee ay ururiyeen. Talaabadani waxay qaadatay 70% wadarta guud ee xogta la ururiyay oo aan faa'iido lahayn waana laga saaray. Microsoft waxay hubisay inaysan jirin faallooyin gaf ah oo loogu talagalay dadka ku nool Mareykanka, UK iyo Australia iyo faallooyin kasta oo galmo ama siyaasadeed.

Hadda, xogtan la safeeyey ee faa'iidada leh waxay ahayd in lagu dabaqo qaabka la doortay. Qaabkani waxa uu ahaa cDSSM ama Qaabka Semantic^{(Deep Structured Semantic Model)} ee Qoto-dheer ee Habaysan ee Convolutional . Kani waa nooc cusub oo waxa uu ka caawinayaa in ka sii wanaagsan oo qoto dheer dhaqanka aadanaha u eg ee AI.

Sida cDSSM ay u keento AI ka wanaagsan

Aqoonsiga weydiinta^{(Query Identification)}

Aqoonsiga^{(Identification)} weydiinta waa tillaabada ugu horraysa ee AI ka dhigaysa mid sida Aadanaha^(Humans) oo kale ah . Algorithm wuxuu qaataa weydiinta gelinta wuxuuna eegayaa xogta su'aalaha la midka ah. Tan waxa kale oo loo tixraacaa sida Xog-celinta^{(Information Retrieval)} ama IR.
Tusaale ahaan^(Example) : haddii weydiintu tahay, "Sideen u sameeyaa baastada digaaga?", Ruuh wuxuu^(Ruuh) falanqeeyaa xogta wuxuuna helaa muunado badan oo su'aalo la mid ah.

Jawaabaha kala saraynta^{(Ranking responses)}

Halkan, algorithm ayaa xalliya jawaabaha ku salaysan sida muunadyadu u khuseeyaan. Tani waa sida xogta ugu habboon loo bixiyo wax soo saar ahaan.

Fahamka Dulucda^{(Understanding Context)}

Hadda, waxaa laga yaabaa inay macno darro tahay haddii chatbot-ka uu iloobo waxa isticmaaluhu ka hadlayo.

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

Ruuh: “Yes, I like it.”

Question: “which flavors do you like?”

Ruuh: “Chocolate and Vanilla.”

Hadda, Ruuh waxay^(Ruuh) ogaatay in su'aasha labaad ay tahay ku saabsan jalaatada, markaa, jawaabtu waxay ahayd mid habboon.

Si aad ugu wanagsanto shaqadeeda, algorithmamka Ruuh waxay si joogto ah u raadisaa xogta su'aalihii hore ee isticmaalaha oo ay fahmaan macnaha guud ee ku saabsan waxa isticmaaluhu ka hadlayo.

Ogaanshaha iyo ka jawaabista tilmaamaha dareenka^{(Detection and response to emotional cues)}

Hadda, dad badan oo u eg macneheedu waa ogaanshaha dareenka. Tani waa sababta oo ah dadku waxay leeyihiin maskax maskaxeed. Marka, si loo ogaado shucuurta isticmaalayaasha, Ruuh waxay raadisaa qaababka fariimaha sheekeysiga ee ay heshay iyo nooca emojis ee loo isticmaalo sheekeysiga. Markaa, marka aad la hadlayso, way garanaysaa inaad faraxsan tahay, murugoonayso, aad faraxsan tahay ama aad ka xun tahay.

Xukun^(Verdict)

Ruuh waa awood iyo hab weyn oo lagu muujiyo awooda waxa AI maanta samayn karo si uu u dhaqmo sida bini'aadamka. Awoodda cDSSM, Ruuh aad ayuu uga caqli badan yahay.

Microsoft wuxuu leeyahay:

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.

Aynu si fiican u fahanno arrintan tusaale. Haddii isticmaaluhu uu waydiiyo Ruuh , " Kuwadee^(Which) pizza toppings ayaa ugu caansan?", Ruuh waxay u aqoonsan doontaa su'aalaha ku saabsan 'biisaha toppings' oo dib u soo ceshano jawaabaha ugu habboon ee ku salaysan weydiintan. Ruuh waxa uu ka qiimayn doonaa jawaabaha la midka ah xogta xogta ku salaysan ee ku haboon si loo dhaliyo jawaabta ugu habboon. Wacyigelinta macnaha guud, Ruuxa^(Ruuh) wuxuu si fudud uga jawaabi karaa su'aalaha daba-galka ah sida, "Kuwee ayaad jeceshahay?" adigoo ku jawaabaya "Waan jeclahay likaha iyo cananaaska".

Ruuh hadda waa hal sano jir, waana inaan sheego in mustaqbalka AI uu ifayo sababtoo ah heerkan aan ku aragno AI oo aad u horumarsan oo soo baxaya, waxaan ku dhowdahay inaan aragno waxyaabo caqli badan oo nagu wareegsan. Waxaan u rajeyneynaa kooxda Microsoft , nasiib aad u wanaagsan waxaanan rajeynayaa inay nagu sii yaabin doonaan mustaqbalka alaabtan weyn.

Waxaad wax badan oo ku saabsan Ruuh ka akhriyi kartaa  halkan maqaalka rasmiga ah ee Microsoft - oo ku sii tijaabi halkan Facebook^{(on Facebook)} .^{(on Facebook.)}

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

Sometimes all you need is to talk to someone. Someonе who can cheer уou up in thеir own waу, someone who is so full of life and chatty that you forget all your problems in life. Someone that amuses you by coming better than your expectatіons. Everyonе is not so comfortable about tаlking to other ‘humans’ about things, but thеrе are sоme curiоus people who do talk to AI. Here, Ruυh comeѕ to the 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

• Soo dhawoow vs Kooxaha Microsoft vs Google Meet vs Skype

• Ka noqo gelitaanka qolo saddexaad Facebook, Google, Microsoft, Twitter

• Sida loogu daro Zoom kooxaha Microsoft

• Microsoft Intune miyaanay wada shaqayn? Ku qas Intune in ay isku xidho Windows 11/10

• Deji taariikhda uu dhacayo erayga sirta ah ee Koontada Microsoft iyo Koontada Maxaliga ah

• Sida si toos ah loogu gudbiyo iimaylka gudaha Microsoft Outlook

• Sida loo isticmaalo Sawirka qaabka Sawirka ee Microsoft Edge Browser

• Sida loo damiyo calaamadaha Paragraph ee Microsoft Word

• Microsoft Hyper-V Server waa u bilaash qiimayn aan xadidnayn

• Sida loo dhaqan geliyo Raadinta Badbaadada Google ee Microsoft Edge gudaha Windows 10

• Maamul abka mareegaha ee dhaxalka leh ee leh Xariirka Liiska Goobta Ganacsiga ee Microsoft

• Sida dib-u-diiwaangelinta ama dib loogu rakibo Apps Store Microsoft Windows 11/10

• Sida loo dejiyo ama loo beddelo bogga hore ee Microsoft Edge Windows 11/10

• Sida loo habeeyo Microsoft Edge bogga tab cusub

• Koontada Microsoft ee aad gelisay ma jiro

• Hagaaji Cilada Dukaanka Microsoft 0x80072F7D

• Akoonka Microsoft wuxuu galay qalad 0x800706d9 Windows 10

• Sida loogu rakibo kooxaha Microsoft Linux iyo macOS

• Waxaa maqan, Weydii maamulahaaga inuu awood u yeesho kooxaha Microsoft

• Sida looga soo saaro magacyada domain URL-yada Microsoft Excel