Nogle gange er alt hvad du behøver at tale med nogen. En der kan muntre dig op på deres egen måde, en der er så fuld af liv og snakkesalig, at du glemmer alle dine problemer i livet. Nogen, der morer dig ved at komme bedre end dine forventninger. Alle er ikke så trygge ved at tale med andre 'mennesker' om ting, men der er nogle nysgerrige mennesker, der taler med AI. Her kommer Ruuh til billedet.

Ruuh er i stand til at lytte til ens spørgsmål, opdage deres følelser, lære om brugerens baggrund og komme med passende svar og mere. Dette forbedrer deres binding og forholdet, de deler med brugeren. Det indebærer direkte mere værdifulde og fornuftige chats mellem chatbotten og brugeren.

Ruuh er god til at lave samtaler

Uden involvering af følelser er eksistensen af ​​chatbots ubrugelig. Bare^(Just) det at kunne svare uden nogen personlig forbindelse gør chatten formel og mange gange uinteressant. En chatbot er kun interessant, hvis de er i stand til at lave samtaler på grundlag af følelser involveret i den. Om dette siger Microsoft ,

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.

Målet med at bygge Ruuh

Microsofts hovedformål bag opbygningen af ​​denne AI-drevne chatbot var at gøre det til de unge, teknologikyndige early adopters i Indien^(India) . Det var allerede beregnet til at ligne Microsofts kinesiske Chatbot ved navn Xiaoice . Ruuh er mere en digital ven end blot en digital assistent. Ruuh er en software, der ikke bare er et stykke kode; det er din ven.
Hvordan deep learning fungerer.

Ruuh er en fiktiv karakter, det ved vi alle sammen. Men hendes karakter er modelleret efter en ung, urban Indien^(India) og pige, der er omkring 18-24 år gammel. Hun ser ud til at være interesseret i popkultur^(Pop) og er god til at bruge flydende byslang, der bruges i Indien^(India) .

Det første skridt i at skabe Ruuh var at indsamle data. Det var meningen, at hun var elskværdig såvel som vittig. Kilden til denne personlighed for Ruuh var samtaler i realtid, samtaler på sociale medier^{(Social Media)} , fora, sociale platforme og beskedtjenester, hvor dataene indsamles for at forbedre brugeroplevelsen anonymt.

Dernæst skulle de forfine de nyttige data, som de indsamlede. Dette trin tog 70 % af de samlede indsamlede data som ubrugelige og blev fjernet. Microsoft sørgede for, at der ikke er stødende kommentarer til personer i USA, Storbritannien og Australien^(Australia) og sexistiske eller politiske kommentarer.

Nu skulle disse raffinerede og nyttige data anvendes i den valgte model. Denne model var cDSSM eller Convolutional Deep Structured Semantic Model . Dette er en nyere model og hjælper med mere bedre og dybere menneskelignende adfærd i AI.

Hvordan cDSSM resulterer i bedre AI

Forespørgselsidentifikation^{(Query Identification)}

Forespørgselsidentifikation er^{(Identification)} det første skridt i at gøre AI mere som mennesker^(Humans) . En algoritme tager inputforespørgslen og leder efter lignende spørgsmål i databasen. Dette kaldes også informationssøgning^{(Information Retrieval)} eller IR.
For eksempel^(Example) : hvis forespørgslen er "hvordan laver jeg kyllingepasta?", analyserer Ruuh dataene og finder flere eksempler på lignende spørgsmål.

Rangering af svar^{(Ranking responses)}

Her sorterer algoritmen svarene ud fra, hvor relevante prøverne er. Sådan gives de mest relevante data som output.

Forståelse af kontekst^{(Understanding Context)}

Nu er det måske meningsløst, hvis chatbotten glemmer, hvad brugeren taler om.

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

Ruuh: “Yes, I like it.”

Question: “which flavors do you like?”

Ruuh: “Chocolate and Vanilla.”

Nu vidste Ruuh , at det andet spørgsmål handlede om is, og derfor var svaret passende.

For at være så god til sin funktionalitet, slår Ruuhs algoritme konstant op efter data i de tidligere forespørgsler fra brugeren og forstår konteksten omkring det, brugeren taler om.

Detektion og respons på følelsesmæssige signaler^{(Detection and response to emotional cues)}

Nu betyder mere menneskelignende registrering af følelser. Dette skyldes, at mennesker har følelsesmæssige tankegange. Så for at opdage brugernes følelser, ser Ruuh op efter mønstre i chatbeskeder modtaget af hende og den type emojis, der bruges i chatten. Så når du taler med hende, ved hun, om du er glad, ked af det, ophidset eller ked af det.

Dom^(Verdict)

Ruuh er kraftfuld og en fantastisk måde at vise styrken af, hvad AI kan gøre i dag for at opføre sig som et menneske. Med kraften fra cDSSM er Ruuh meget smartere.

Microsoft siger:

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.

Lad os forstå dette bedre med et eksempel. Hvis en bruger spurgte Ruuh , " Hvilke^(Which) pizzapålæg er mest populære?", ville Ruuh identificere forespørgslen som om 'pizzapåfyldninger' og hente de mest relevante svar baseret på denne forespørgsel. Ruuh ville rangere lignende svar fra databasen baseret på relevans for at generere det mest passende svar. Med kontekstuel bevidsthed kan Ruuh nemt besvare opfølgende spørgsmål såsom: "Hvilke kan du lide?" ved at svare "Jeg elsker svampe og ananas".

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.

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

Sometimes all you need is to talk to someone. Someone who can cheer уou υp in their own way, ѕomeone 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 expectations. Everyone is not so сomfortable about talking to other ‘humаnѕ’ about things, but there are some curious people who do talk to AI. Hеre, Ruuh comes to the рiсture.

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

• Tilbagekald tredjepartsadgang fra Facebook, Google, Microsoft, Twitter

• Sådan tilføjer du Zoom til Microsoft Teams

• Microsoft Intune synkroniserer ikke? Tving Intune til at synkronisere i Windows 11/10

• Indstil en adgangskodeudløbsdato for Microsoft-konto og lokal konto

• Sådan roser du nogen på Microsoft Teams for deres veludførte arbejde

• Sådan begrænser du automatisk afspilning af medier i Microsoft Edge-browseren

• Sådan udtrækkes domænenavne fra URL'er i Microsoft Excel

• Sådan slår du afsnitsmærker fra i Microsoft Word

• Microsoft Visual C++ Redistributable Package: FAQ og download

• Ret Microsoft Store-fejl 0x80072F7D

• Sådan indstilles eller ændres Microsoft Edge-hjemmesiden på Windows 11/10

• Hvad er en ASD-fil, og hvordan åbner man den i Microsoft Word?

• Microsoft Remote Desktop Assistant til Windows 10

• Microsoft Edge Browser Tips og Tricks til Windows 11/10

• Sådan installeres Microsoft Teams på Linux og macOS

• Sådan skjuler du titellinje med lodrette faner i Microsoft Edge

• Windows 365 Cloud PC-detaljer, pris, udgivelsesdato, ofte stillede spørgsmål

• Sådan bruger og tilføjer du arbejds-/skolekonti til Microsoft Authenticator-appen

• Microsoft-konto login fejl 0x800706d9 på Windows 10