What can chat bot
First, we outlined the main office processes. About the chat bot, we did not even talk. Here, for example, the order of travel. Now I have to write to the employee of the business travel service in the mail: “I am going on a business trip to Surgut on the 5th day for three days”, and he: “Such a plane and such a hotel - everything fits?”, And I: “ Come on". Then he will go to coordinate with the management, book the tickets himself, after some send me a confirmation that everything is OK. All the same can do the bot.
Or if you need a certificate for a visa, the bot will knock on the tire, the tire will knock on the personnel subsystem and take the PDF, then send it to the personnel department printer and write a letter that you need to print there. Then notify me that you can come in a couple of hours. If you need to issue a pass to a guest or book a meeting for a meeting, then it is enough to entrust the bot with this task, and he will perform it.
')
Now let's show an example a little more difficult.
In 3 weeks:
In our travel dialogue, a typical business process is used. The employee (his F. I. O. is in the authentication data) indicates the city of the trip and the date. Bot writes a ticket in the accounting department and a letter to the specialist responsible for purchasing tickets and booking on trips. When the ticket is closed, the bot receives its result and then processes it according to the script. A specialist bot handles letters or messages to Telegrams until he issues documents with tickets and reservations. He then searches for a user using the Wi-Fi hotspot in the office to determine the nearest available printer. Sends documents to print. On the day of departure, it reminds you of the trip, takes the weather from one of the external sites via its open API, then begins to interrogate the airport’s online scoreboard for the flight schedule (the flight itself is in the tickets). After the trip, he will ask for an accountancy report (send the form and tell you how to fill it out), plus ask for useful tips for the knowledge base. In addition, he can order a taxi to the airport, order a car on the spot and pick up travel data in order to deposit the sums immediately into the advance report.
As you can see, each step is quite simple, but together they create a bit of magic. The only moment is a lot of messing around with documents, various exceptions and logging in to the systems that are not yet ready for such a digital transformation. A lot of functionality is still in beta, alpha, or just at the integration stage in general - development and testing take a very long time to work with documents so that a woodpecker who has accidentally flown in will not bring down the entire office. But everything looks quite simple and logical.
Colloquial speech
Bots are able to learn the syntax of users. Here is a simple example of what a call to the Help Desk looks like through a bot:
And this is a screenshot of the application in ITSM:
The process now is this: the user sends a more or less structured ticket, and then the helpdesk employee breaks it down into type and subtype, after which the deadline for the incident and the responsible one are set. Next you need to specify the type of treatment - the incident. Service - printing devices. Employee - Voronova. Responsible - Petrov. Office - 1105.
In just a few years, quite a few pairs of verbal requests in free form and correctly completed forms of the ITSM system have accumulated. Then everything is simple: a little machine learning from this sample, and then the bot, along with the user's ticket, sends the type and subtype of the application to the system. Naturally, he can make mistakes, so the process has so far changed slightly - just the helpdesk employee gets the fields already filled in (correctly filled in 80% of cases), but, of course, can change their values.
The administrator can also use the bot in his work, for example, for this:
IVR systems are the same chat bots with a slightly modified interface. When you connect synthesis systems and voice recognition ( such , there are examples of dialogues), you can get the same chat in voice form. Many users like it a lot, and now some of the office automation functions work through IVR. This will be especially true for those customers where users are not very familiar with computers.
We showed a bot at the exhibition, and the idea of ​​tight integration with the bus office has already gone to customers. For example, one of them wants to launch telegram messages to negotiate server restarts. The idea is this: the request is coordinated by a number of people, when the mass of “OK” answers is gathered, the server restarts. In general, it is quite realistic. The same can be done posting the document. But this is a very distant future.
For example, a chat bot, a person or an IVR is the data interface, the user task is “order a chat at 15:00”. Connector - authorization link. The bus performs the implementation task.
Another quite banal example of how a bot works is the recovery of the account. Users (and there are about two thousand of them in the office) regularly forget their passwords. Either they activate the accounts on several devices - a phone, a tablet, a workstation ... And then either I forgot to update the password somewhere, or the tablet was trivially at home and the child locked the account. In general, the moment of changing the password is a headache for both the employees themselves and for technical support, which they often call (especially in the morning). Now the bot helps to reset the password, more precisely, unlock the account. In this case, the operation is absolutely routine.
Address Book Search:
Here is a complex analysis of the phrase-request to find a contact within the company. Next is a request to the inside of the HR service, where we have carefully rewritten all the useful skills of people in case of new projects and urgent appeals. “Pikaniska” is a rare word, so a search on it is very relevant and no refinement is required. The bot unloads the data of the employee who understands the question. If he was online, he could immediately write to him. It is offline, and judging by the documents of the same personnel department - on a business trip in Surgut. The bot checks its time zone and provides data.
Here, too, everything is relatively simple. Bot can say “remind me about lunch with Ivanov,” and he will set it in tasks to remind you in time. The rest of the data is available on the bus.
It all started with an idea to find out what digital transformation is, digitalization, etc., and there is a lot of noise in the market, but nothing concrete. In order to understand what it is, we decided to start with ourselves and understand what can be “digitized” in our company. In the course of “digging up the topic,” we worked out a bunch of case studies for digitalization, found solutions, but at the same time we were not bothered by the idea of ​​the “right” interface for office business processes. About the chat bot, we did not even talk, in principle, not even discussed. At some point, we realized that the approach to interaction with office business processes also needs to be changed, everything must be convenient and necessarily mobile, and since 100 mobile applications are not done, it became clear that the future is natural interfaces, in particular chat rooms. In particular, there is an incredible Chinese example of WeChat - initially analogue of ICQ, which has now become a social network, a trading platform, a bulletin board, and e-mail, and in general everything.
More bots can tell basic things from the corporate training knowledge base, look for training materials, show the nearest internal courses and seminars, play a list of newcomers with newbies (“Got my stationery”, “Found the kitchen”, “Checked in the gym” and so on) , book a rest room or queue up to a game console in the same place, get a password for guest Wi-Fi, find out the DMS number, clinics on it, emergency phone, inform the office medical service about the injury, sign up for an office medical service, book a simulator, report sweat A lost or found thing (a bot then connects people or throws off the log to the secretary), send corporate news, give different information to new employees how to live, warn about the birthdays of your contacts. In the distant plans - check the queue length in the dining room by video analytics (usually from 1 to 15 minutes, now it is implemented by a separate informer in our office), find out the menu for today in the dining room or order pizza to the office, find travel companions, transfer documents. From the technical service in the plans - to replace the corporate SIM-card, change the tariff, take bug reports for any things like “the lamp is not on the fifth floor here”, send the bug report to the economic department or to the cleaners.
Of course, the main stumbling block for all customers with this approach is the digital transformation of the office - it is the security (authorization) of users, and the second is the place where all this correspondence is stored. In the case of our bot, the correspondence is stored in the KROK cloud, on the bot server, that is, in our internal infrastructure. All integration between the bot and the company's systems goes through a single integration bus. The bus connection is through a universal connector, which allows you to divide access rights into three parts: public parts (public), for all employees, and for certain employees.
About authorization, the story is long and rich in adventure, so if you're interested, I'll tell you separately. Well, if there are questions not for comments - write: digital@croc.ru.
Or if you need a certificate for a visa, the bot will knock on the tire, the tire will knock on the personnel subsystem and take the PDF, then send it to the personnel department printer and write a letter that you need to print there. Then notify me that you can come in a couple of hours. If you need to issue a pass to a guest or book a meeting for a meeting, then it is enough to entrust the bot with this task, and he will perform it.
')
Now let's show an example a little more difficult.
In 3 weeks:
In our travel dialogue, a typical business process is used. The employee (his F. I. O. is in the authentication data) indicates the city of the trip and the date. Bot writes a ticket in the accounting department and a letter to the specialist responsible for purchasing tickets and booking on trips. When the ticket is closed, the bot receives its result and then processes it according to the script. A specialist bot handles letters or messages to Telegrams until he issues documents with tickets and reservations. He then searches for a user using the Wi-Fi hotspot in the office to determine the nearest available printer. Sends documents to print. On the day of departure, it reminds you of the trip, takes the weather from one of the external sites via its open API, then begins to interrogate the airport’s online scoreboard for the flight schedule (the flight itself is in the tickets). After the trip, he will ask for an accountancy report (send the form and tell you how to fill it out), plus ask for useful tips for the knowledge base. In addition, he can order a taxi to the airport, order a car on the spot and pick up travel data in order to deposit the sums immediately into the advance report.
As you can see, each step is quite simple, but together they create a bit of magic. The only moment is a lot of messing around with documents, various exceptions and logging in to the systems that are not yet ready for such a digital transformation. A lot of functionality is still in beta, alpha, or just at the integration stage in general - development and testing take a very long time to work with documents so that a woodpecker who has accidentally flown in will not bring down the entire office. But everything looks quite simple and logical.
Some more magic
Colloquial speech
Bots are able to learn the syntax of users. Here is a simple example of what a call to the Help Desk looks like through a bot:
And this is a screenshot of the application in ITSM:
The process now is this: the user sends a more or less structured ticket, and then the helpdesk employee breaks it down into type and subtype, after which the deadline for the incident and the responsible one are set. Next you need to specify the type of treatment - the incident. Service - printing devices. Employee - Voronova. Responsible - Petrov. Office - 1105.
In just a few years, quite a few pairs of verbal requests in free form and correctly completed forms of the ITSM system have accumulated. Then everything is simple: a little machine learning from this sample, and then the bot, along with the user's ticket, sends the type and subtype of the application to the system. Naturally, he can make mistakes, so the process has so far changed slightly - just the helpdesk employee gets the fields already filled in (correctly filled in 80% of cases), but, of course, can change their values.
The administrator can also use the bot in his work, for example, for this:
Vote
IVR systems are the same chat bots with a slightly modified interface. When you connect synthesis systems and voice recognition ( such , there are examples of dialogues), you can get the same chat in voice form. Many users like it a lot, and now some of the office automation functions work through IVR. This will be especially true for those customers where users are not very familiar with computers.
Integration with all processes for many users.
We showed a bot at the exhibition, and the idea of ​​tight integration with the bus office has already gone to customers. For example, one of them wants to launch telegram messages to negotiate server restarts. The idea is this: the request is coordinated by a number of people, when the mass of “OK” answers is gathered, the server restarts. In general, it is quite realistic. The same can be done posting the document. But this is a very distant future.
For example, a chat bot, a person or an IVR is the data interface, the user task is “order a chat at 15:00”. Connector - authorization link. The bus performs the implementation task.
More features
Another quite banal example of how a bot works is the recovery of the account. Users (and there are about two thousand of them in the office) regularly forget their passwords. Either they activate the accounts on several devices - a phone, a tablet, a workstation ... And then either I forgot to update the password somewhere, or the tablet was trivially at home and the child locked the account. In general, the moment of changing the password is a headache for both the employees themselves and for technical support, which they often call (especially in the morning). Now the bot helps to reset the password, more precisely, unlock the account. In this case, the operation is absolutely routine.
Address Book Search:
Here is a complex analysis of the phrase-request to find a contact within the company. Next is a request to the inside of the HR service, where we have carefully rewritten all the useful skills of people in case of new projects and urgent appeals. “Pikaniska” is a rare word, so a search on it is very relevant and no refinement is required. The bot unloads the data of the employee who understands the question. If he was online, he could immediately write to him. It is offline, and judging by the documents of the same personnel department - on a business trip in Surgut. The bot checks its time zone and provides data.
Here, too, everything is relatively simple. Bot can say “remind me about lunch with Ivanov,” and he will set it in tasks to remind you in time. The rest of the data is available on the bus.
How it all began
It all started with an idea to find out what digital transformation is, digitalization, etc., and there is a lot of noise in the market, but nothing concrete. In order to understand what it is, we decided to start with ourselves and understand what can be “digitized” in our company. In the course of “digging up the topic,” we worked out a bunch of case studies for digitalization, found solutions, but at the same time we were not bothered by the idea of ​​the “right” interface for office business processes. About the chat bot, we did not even talk, in principle, not even discussed. At some point, we realized that the approach to interaction with office business processes also needs to be changed, everything must be convenient and necessarily mobile, and since 100 mobile applications are not done, it became clear that the future is natural interfaces, in particular chat rooms. In particular, there is an incredible Chinese example of WeChat - initially analogue of ICQ, which has now become a social network, a trading platform, a bulletin board, and e-mail, and in general everything.
More bots can tell basic things from the corporate training knowledge base, look for training materials, show the nearest internal courses and seminars, play a list of newcomers with newbies (“Got my stationery”, “Found the kitchen”, “Checked in the gym” and so on) , book a rest room or queue up to a game console in the same place, get a password for guest Wi-Fi, find out the DMS number, clinics on it, emergency phone, inform the office medical service about the injury, sign up for an office medical service, book a simulator, report sweat A lost or found thing (a bot then connects people or throws off the log to the secretary), send corporate news, give different information to new employees how to live, warn about the birthdays of your contacts. In the distant plans - check the queue length in the dining room by video analytics (usually from 1 to 15 minutes, now it is implemented by a separate informer in our office), find out the menu for today in the dining room or order pizza to the office, find travel companions, transfer documents. From the technical service in the plans - to replace the corporate SIM-card, change the tariff, take bug reports for any things like “the lamp is not on the fifth floor here”, send the bug report to the economic department or to the cleaners.
Of course, the main stumbling block for all customers with this approach is the digital transformation of the office - it is the security (authorization) of users, and the second is the place where all this correspondence is stored. In the case of our bot, the correspondence is stored in the KROK cloud, on the bot server, that is, in our internal infrastructure. All integration between the bot and the company's systems goes through a single integration bus. The bus connection is through a universal connector, which allows you to divide access rights into three parts: public parts (public), for all employees, and for certain employees.
About authorization, the story is long and rich in adventure, so if you're interested, I'll tell you separately. Well, if there are questions not for comments - write: digital@croc.ru.
Source: https://habr.com/ru/post/335650/
All Articles