Geekly Articles each Day
📜 ⬆️ ⬇️

Voice interface for ordering a car by phone in action

robophone
Hi, Habr. For a long time I thought about how to approach this large and complex article.

A year ago, it was decided to start the service of ordering a new format car in the old wrapper.
We do not have a call center, there is no mobile application for passengers, all orders are taken by the robot on the phone using synthesis and voice recognition, as well as a sufficiently large software package.

This idea has been in the air for a long time and it is being voiced every now and then in various sources, and we managed to realize it. The service is running, running, and even making a profit, and even growing.
Anyone who is interested in how to launch a new project for the market, which has no analogues, but having a bunch of competitors, I ask under the cat.

Start


A year and a half ago, a turning point came, we decided to actively pursue our projects. A list of candidates was compiled and heated discussions began. And the most interesting is that the current project was not on this list. The choice fell on one project and even later its MVP was implemented, but then the idea appeared “To make the service of ordering a car over the telephone without dispatchers using synthesis and speech recognition”. Not everyone thought this idea was viable, even I had doubts, but as they say, if you don’t try, you don’t know. Development began, and it was the first mistake.
')

First city


And so began the transformation of ideas into products. Initially, a lot of time was devoted to call scenarios (and it was in vain, it was worth thinking about more important things).

The general scheme of creating a trip:


The overall scheme of the trip:


Training


In the beginning there was no idea how to advertise this service, how to look for drivers. There was also no idea how many problems to solve.
It was decided to start in the regional center with a population of ~ 500 thousand people.
Advertising to attract passengers chose the following formats: groups in social. networks, contextual advertising, asphalt, banners.

Drivers attracted through Avito and groups in the social. networks. The scheme was chosen that the driver goes on the line at any time convenient for him.

Start and Fail


And so, by the appointed date, everything was ready, and the launch day came. After the launch immediately appeared a huge number of problems.

The passengers

It was not enough people called, and their number did not grow much with time, it was clear that the amount of advertising that we could afford was not enough financially. As it turned out, the city’s advertising budget of 500 thousand should be no less than 200 thousand rubles a month, and so it was necessary to advertise for at least six months. Those. minimum advertising budget 1.2 million rubles.

Drivers

We naively thought that we got drivers. In fact, we scored a handful of people. Many did not go on the line, many even went online and simply did not even take the orders that were next to them. We also could not provide uniform coverage of a big city by drivers.

As a result, it became clear that to roll out the service, you need to either take at least 10 drivers for a salary, or introduce additional payments to drivers.

We tried a lot:


After a month of work, the service reached a record of 10 orders per day, just a drop in the ocean.
But it was acquired the first idea of ​​the industry in which they got involved.
It became clear that we need a substantial budget for rolling. By the minimum for half a year in a half-million city it is about 2 million rubles. And even the availability of such funds did not guarantee the success of the project given the high competition.

Second City (Resurrection of the Phoenix from the Ashes)


The first pancake was a lump, but we acquired knowledge and experience and had a working system in our hands, which simply did not have enough blood infusion in the form of finances. It is worth noting that from the technical point of view we have solved all the problems, the question arose of what to do next.

Without hesitation, we followed one of the tips from the very good book Marketing Wars.

It became obvious that the city of 500 thousand was too tough for us, and there were too big fish there, which it was pointless to fight with. The idea was chosen to try their hand in cities of up to 100 thousand people.

Training


This time it all started not with the development, but with the exploration of the market. The district center in our region was chosen with a population of about 35 thousand people. Just looking for a city closer to us, so that you can travel if necessary.

We traveled to the city, evaluated the environment in which we were to work, looked for competitors, etc. (now this is our obligatory practice).

The main sources of promotion were identified. As it turned out in a small town there are not so many of them, as a plus and a minus. On the one hand, you need less money, but on the other hand, it is difficult to quickly make a large-scale advertising campaign.

With the competition, everything was just much simpler. All competing services in such small cities still work on radios with live dispatchers. Here our manufacturability has become a significant competitive advantage.

Advertising to attract passengers chose the following formats: groups in social. networks, contextual advertising, banners, radio.

Business processes


For the drivers, a scheme was still chosen, suggesting work on a free schedule.
A single price was set for the city, which allowed us not to recognize the addresses, but simply send the sound file to the drivers.

There is no need to count the travel time and distance. Prices for trips out of town were determined by drivers (but in vain).

Launch


And then a couple of months after the failure in the regional center, a new attempt in a small town. Before the launch, a meeting of drivers was organized to explain the work rules.
The launch was vigorous, in the first days it was already 20 orders a day.

Growth


For 2 months the service became the leader of a small town, and because of us other services began to close. Calls to competitors began with an offer to buy their services. It would be a success, the model fully justified itself. Of course, in the process of growth, we met a huge number of technical and business problems, but everything was solved. And what is important, people were not frightened by the robot taking orders, they quickly got used to it.

Innovations


In a small town, we took a big step forward:

Monetization

Initially, the monetization model was not thought out at all, and it was a big blunder. At first, the drivers drove for free, and we paid service providers, speech synthesis and speech recognition services, hosting, etc. When it became clear that the model was working, monetization was introduced.

Shifts

One of the major problems was that drivers go on the line when they want, and there is no way to control it. It was decided to introduce shifts, and at the same time make them paid. Day we divided into 6 shifts of 4 hours. The price of a shift depended on the number of calls from passengers.

Discounts

Tricky discount systems were introduced. For drivers on shifts (for example, the second shift per day is 30% cheaper). For passengers, a discount was introduced for every n-th trip.

Price per distance

Initially, there was a single price for the city. The reason for this was the technical difficulties and mentality of the inhabitants of small cities. Subsequently, when the service grew, we introduced the system of recognition of departure and destination addresses and switched to the dependence of price on distance. In small towns, it makes no sense to set the price per kilometer, it is enough to make price gradations.

Third city


On the experience of a small town, it was decided that the model is ready for scaling, and now it is just necessary to connect new cities.

Training


They did not go far, another district center was chosen 100 km. The population there was about 33 thousand people. The ways of promotion were the same. It was decided not to change the schemes of work with passengers and drivers.

Start and fail


The launch in the third city revealed new unexpected problems.

First problem

We did not get the right number of drivers, or rather, we thought we had scored. A lot of people called, but there were really few who were ready to work. According to our estimates, afterwards, of all those who say that they will work, only about 10-20% will actually be.

Second problem

The launch took place 3 days before February 23, and when the day came for the defender of the fatherland, there was a peak of orders.

On this day, 60 passengers called, but the drivers went to the line 0. This was a complete surprise. Then it was March 8, and again a large number of orders were not delivered.

It all turned out as in the expression “With a shield or on a shield,” and we ended up on a shield.

Attempts at rehabilitation

We stubbornly did not give up and began to take urgent measures


The main problem was the drivers, they did not want to work in any way. In this city, we face the main problem of Russia: people do not want to work .
We are often called to get a job and when they find out that in order to earn money they have to work, they refuse to say what they think.

Several months of struggle for the third city was unsuccessful. At the moment there everything is let loose. It employs a couple of drivers and 10-30 orders per day. This failure was a very good lesson.

Fourth city


And here we have: 1 city - success and 1 city - failure, and we must go further (the first is not taken into account). The experience gained showed what to do and what not to do. We go further ...

Month of falls


It was such an interesting month when everything fell.


Sometimes I had to come at 3 o'clock in the morning and deal with problems.

Technology and architecture


The basis of the server part of the project was taken by SOA. The main services were highlighted:

Core - work with orders, drivers, passengers. There are various order distribution algorithms and persistent master data storage. (PHP)
Dialog is a service for handling calls in real time, here are various scripts of dialogue with passengers. (Javascript)
Speech is a speech recognition service. (Javascript)
Geo is a geocoding service. (Javascript)
Logger - logging service. (FluetnD, Elastic, Kibana)
Bot - telegram bot for drivers. (Php)
Route is a service for finding the best routes. (Javascript)
It was also decided to use Docker, both for development and for production.

Application for drivers made on the basis of Telegram.

Plans


Small goal: these are 10 cities with a population of up to 100 thousand people. At the moment there is already a plan for how to achieve this and in what time frame. And more specifically, we have 2 plans. The first plan: how to do it all by yourself and with your own money, the second plan is tied to attracting investments (the search for which we are now also actively engaged in).

The big goal is 30% of Russian cities with a population of up to 100 thousand people. But for this purpose we already have a plan with investments only. Here on their own grow a couple of decades.

There are also many plans to improve the service, add new services, access to related industries.

We are slowly developing and preparing a platform for taxis, which allows us to reduce the number of operators and create smaller services with less financial expenses.

And of course, we already have a couple of projects with synthesis and speech recognition in other areas, and we intend to develop them and bring them to the market.

findings


The time has come for new user interfaces, where speech synthesis and some kind of AI are already being applied. Suffice it to recall Alexa's from Amazon. It is very important now to look towards voice interfaces. With the current development of technology, even a small organization can find an application for them that will be profitable.

All concerns about the fact that people will not talk to the robot, as practice shows, are groundless.

PS:
If the community is interested, we can prepare more articles on project technologies, on problems with working with cloud telephony in the periphery, and on what will be interesting and contains enough information for a separate article.

Source: https://habr.com/ru/post/334816/

More articles:


All Articles