RU2673001C1 - Method and system of identification and classification of causes of user claims in self-service devices - Google Patents

Abstract

FIELD: data processing.SUBSTANCE: invention relates to systems and methods for identifying the causes of claims and incidents in the network of self-service devices. In a method for identifying and classifying the causes of user complaints in self-service devices, receive a set of user complaints in chronological order. Allocate a group of claims for analysis based on the requirements for the type and number of operations. Operation is obtained that corresponds to a claim from the group of claims outlined in the previous step, and the operation is analyzed by applying text syntax. Perform line-by-line reading operations and determine the user's session of the user based on the operation. Identify the cause of the error by the user operation and carry out the classification of user complaints on the basis of user operations for which errors occurred in the self-service device.EFFECT: technical results are improving the quality of analysis of customer requests, improving the accuracy and speed of analysis of claims of users of self-service devices.10 cl, 4 dwg

Description

FIELD OF TECHNOLOGY

[001] This technical solution, in General, relates to the field of computer technology, and in particular to systems and methods for identifying the causes of claims and incidents in the network of self-service devices.

BACKGROUND

[002] Banking self-service devices (hereinafter referred to as SS) quickly played a key role in the implementation of financial transactions. Therefore, the importance of effective management of such CSS with the ability to identify and classify the causes of user complaints continues to grow. CSS allows customers to carry out various financial transactions, including deposits, transfers between accounts, payments on accounts, balance requests, cash withdrawals, etc.

[003] CSSs are usually located in places where customers of the CMs can quickly and conveniently complete transactions, including money transfers. In some cases, the CA is owned by a legal entity (for example, a financial institution) and is managed by another entity, such as a service provider, who has contracted with a financial institution for services. In this case, the service provider is the operator of CSS.

[004] Operators place DCs in locations where customers can quickly and conveniently complete transactions, for a number of reasons. For example, the owner of a restaurant may purchase a CSS for placement in a restaurant in order to increase profits in a restaurant bar. Financial institutions usually operate large US networks that allow customers of financial institutions to have more freedom in making financial transactions. Clients of a financial institution that provides such a large network of CSS consider a large number of CSS as an advantage of doing business with a specific financial institution. Financial institutions see CSS as another source of potential revenue.

[005] ATM operators (sometimes ATM from the English Automated teller machine), which are a type of CSS, must effectively manage each ATM in order to justify the reason for the location of the ATM in a particular place and to monitor for the absence of failures. The operated ATM must function correctly (i.e. without mechanical or electrical failures) and contain a sufficient amount of money to process each transaction requested by the ATM client. If the ATM does not work, the client usually finds the ATM of another financial institution and uses this ATM to complete the transaction. A non-working ATM operator may lose income related to future transactions if the client does not return to this ATM operator due to negative operating experience, and therefore, identifying and classifying the causes of user complaints in the ATM channel is a very important task in the prior art.

[006] Modern CSS management methods are expensive to implement and are limited in functionality. Additionally, these CSS management methods are often performed by third-party service providers, which complicates the work of processing user complaints.

[007] The patent application US 20020082994 A1 “Method and apparatus for managing automated banking machines”, patent holder: Efunds Corporation, publication date: 06/27/2002 is known in the prior art. In this technical solution, the ATM management application is used to provide a complete set of ATM operator ATM management information. This ATM management information can enable an ATM operator to increase the profitability of ATMs by increasing accessibility and reducing ATM facilities. The ATM management application can include any number of the following modules: cash management module, transaction status request module, courier services module, automatic balance check module, deposit check module, website management module and profit management module.

SUMMARY OF THE INVENTION

[008] The technical solution aims to eliminate the disadvantages inherent in existing solutions from the prior art.

[009] The technical task set in this technical solution is to identify and classify the causes of user complaints in self-service devices.

[0010] The technical result manifested in solving the above problem is to improve the quality of analysis of user complaints arising from errors in the operation of self-service devices.

[0011] An additional technical result achieved in solving the above problem is to increase the accuracy of the analysis of user complaints and the speed of analysis of user complaints through the use of an automated parser to analyze failed operations.

[0012] This technical result is achieved through the implementation of a method for identifying and classifying the causes of user complaints in the channel of the self-service device, in which a set of user complaints are received in chronological order that arose when using the self-service device; allocating a group of user complaints for analysis based on at least one requirement for the type and number of transactions, with each claim corresponding to at least one operation; receive at least one operation corresponding to at least one claim from the group of claims highlighted in the previous step; analyze at least one operation by applying parsing of the text, and perform line-by-line reading of at least one operation; determining at least one user client session based on at least one operation; identify at least one cause of the error on the user's operation; then, user claims are classified based on user operations for which errors have occurred in the self-service device.

[0013] In some embodiments, a user’s photo or video image is received in conjunction with a set of user claims.

[0014] In some embodiments, the resulting set of user complaints is filtered based on the type of transactions that have occurred.

[0015] In some embodiments, when a set of user complaints is received, a user’s voice biometric identification is used to record their claim.

[0016] In some embodiments, upon receipt of a set of user complaints, user operations are automatically recorded in the event log.

[0017] In some embodiments, a group of user complaints related to failed operations is allocated based on the proportion of affected users or products, or the degree of malfunction.

[0018] In some embodiments, a group of user complaints related to failed operations are allocated based on their criticality.

[0019] In some embodiments, the cause of the error is determined by a character or numeric identifier that uniquely corresponds to the type of operation and / or type of error.

[0020] In some embodiments, the claims are classified based on errors found by the operational days of the self-service device and / or by the types of operations and / or types of self-service devices and / or types of event logs.

BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The features and advantages of this technical solution will become apparent from the following detailed description of the invention and the accompanying drawings, in which:

[0022] In FIG. 1 is a flowchart of a method for identifying and classifying the causes of user complaints in a channel of a self-service device;

[0023] In FIG. 2 shows a diagram of the interaction of the nodes of the system for identifying and classifying the causes of user complaints in the channel of the self-service device;

[0024] In FIG. Figure 3 shows an exemplary claim analysis framework by applying text parsing;

[0025] In FIG. 4 shows an embodiment when several claims and errors in them correspond to one user’s claim.

DETAILED DESCRIPTION OF THE INVENTION

[0026] Below will be described the concepts and terms necessary for understanding this technical solution.

[0027] In this technical solution, a system is meant, including a computer system, a computer (electronic computer), CNC (numerical control), PLC (programmable logic controller), computerized control systems, and any other devices that can perform a given , clearly defined sequence of operations (actions, instructions).

[0028] An instruction processing device is understood to mean an electronic unit or an integrated circuit (microprocessor) executing machine instructions (programs).

[0029] An instruction processing device reads and executes machine instructions (programs) from one or more data storage devices. Hard disk drives (HDD), flash memory, ROM (read only memory), solid state drives (SSD), optical drives can be used as storage devices.

[0030] A program is a sequence of instructions for execution by a computer control device or an instruction processing device.

[0031] ATM (Automated Teller Machine) or automated teller machine is a software and hardware complex designed for the automated issuance and / or reception of cash with or without payment cards, as well as other operations, including payment for goods and services, preparation of documents confirming the relevant operations.

[0032] An event log is a standard way for applications and an operating system to record and centrally store information about important software and hardware events. The event log service stores events from various sources in a single event log, which allows the user to monitor the event log, a program interface (API) allows applications to log information and view existing entries.

[0033] A parser (aka parser) is a program or part of a program that performs parsing. During parsing, the source text is converted to a data structure, usually a tree, which reflects the syntactic structure of the input character sequence and is well suited for further processing.

[0034] A self-service terminal banking device is the most general definition of all machines that allow a client to perform various banking operations without the participation of bank employees. Banking self-service devices are divided into two types, depending on whether they support the function of issuing cash or not. If the cash withdrawal function is supported, then these self-service devices are called ATM (English automated teller mashines), or ATMs, in another case -NCS (English non-cash systems), or terminals for non-cash transactions.

[0035] In some embodiments, the method for identifying and classifying the causes of user complaints in self-service devices shown in FIG. 1 includes the following steps.

[0036] Step 101: receive a set of user complaints in chronological order that arose when using the self-service device;

[0037] Pre-user 200, as shown in FIG. 2, accesses the self-service device, which may be ATM 201, and carries out the banking operations it needs.

[0038] As a banking transaction, there may be, but not limited to, a cash deposit to a card account, payment for services in cash, cash disbursement.

[0039] During the cash deposit operation to the card account, unrecognized banknotes are returned to the customer. If the client did not pick up / could not pick up the returned unrecognized banknotes within a timeout of N seconds, the recognized money is stored in the cassette. In the ERL event log 206, the error is recorded as follows:

[0040] If a malfunction occurs in the operation of the ATM 201, for example, errors or incorrect operations, or a hardware malfunction when accepting banknotes, the user 200 usually leaves a complaint about the operation of the ATM 201 and the system as a whole.

[0041] All user complaints left at ATM 201 or by telephone to the hotline operator are received from the ATM 201 or from the remote server 202 from the user or hotline operator to the customer complaints and complaints registration system 203.

[0042] In some embodiments, a user’s 200 biometric voice identification is used to record his claim. [0043] The communication methods described above allow multiple users / clients to access the system 203 through a communication network directly from an ATM or connect from a remote server 202, which may be a web server. The remote server 202 can be connected to a variety of servers 202a, including, but not limited to, a database server, a file server, an e-commerce server, a content management server, a directory server, an FTP server, a print server, and a proxy server with or without a firewall .

[0044] In some embodiments, together with the claim of the user 200, a photo or video image of the user is received from one of the cameras installed on the ATM 201 (in the event that a video surveillance system is installed on the ATM).

[0045] Step 102: allocating a group of user complaints for analysis based on at least one requirement for the type and number of transactions, each claim having at least one operation; [0046] At least one operation in which an error occurred (in other words, a malfunctioning operation), as shown in FIG. four.

[0047] This compliance may include recording the claim and transaction in one file, using it with the same numerical or symbol identifier, in one database record, etc.

[0048] All failed operations are automatically recorded in the event log 206 or a log, log file, which is a system message generated as a result of the operations that occurred as a result of the actions of the user 200 (Fig. 2) in the ATM 201, and this data can filtered based on the type of operations that occurred.

[0049] Filter criteria may include predetermined conditions and / or conditions developed using machine learning or other adaptive methods. Filter criteria can be implemented on server 204 of system 203 based on production rules that are automatically configured by the user or dynamically configured using software based on machine learning methods (for example, using an artificial neural network).

[0050] The event log 206 consists of entries stored in the database 205. As an event log 206, PRJ, PRR, PRF, PRF, and ERL files may be used. In some embodiments, the event log 206 consists of one or more files, each of which includes a particular type of operation or error.

[0051] Event logs 206, for example, in the * .rrr and * .prj formats are stored in files corresponding to the operational days of the ATM, in the form of text files with the names YYYYMMDD, where YYYY is the year, MM is the month, and DD is the opening day of the corresponding operational day. * .Erl journal can be created every day with the name of the same type YYYYMMDD. For example, the file 20170411.rrr contains a copy of customer checks for the transaction day of the ATM opened on April 11, 2017. The storage periods of the event logs, the printed forms used, trace levels and other characteristics of the event logs are the configuration parameters of the ATM software and can be changed by the user, who is, for example, the operator.

[0052] Records of operations for which errors have occurred can be stored for a predetermined time and then archived.

[0053] A brief summary of the event logs can be presented in tabular form.

[0054] In some implementations, they may store internal fault conditions in an event log 206 that is not related to a user’s complaint for further analysis, even if the failure conditions are never transmitted as a failure signal. ATM 201 may transmit failure signals corresponding to failure conditions that do not meet the criterion

filter to the remote control server 204 in response to a request for these fault signals or on a periodic basis (for example, daily, weekly, monthly, etc.).

[0055] A server 204 hosted on the system aggregates information from all testing and user clients that have been configured to use server 204. In one embodiment, one server 204 serves all clients. In another embodiment, multiple servers 204 serve a subset of clients. Server 204 also implements functional logic that provides the user with access to the network to provide detailed information about new events and errors, as well as to analyze existing errors.

[0056] A claim group is distinguished based on operations, for example, on the basis of their criticality. For example, operations can be grouped into the following categories:

- the operation cannot be performed;

- the operation can be partially performed;

- the operation can be performed on paper, but requires subsequent manual entry into the system;

- the operation can be performed completely using a workaround;

- the operation can be performed completely, the speed of the bank employee is reduced;

- operation is available - request for revision, consultation, etc.

[0057] In some embodiments of the technical solution, operations can be grouped based on the proportion of affected users or products, or the degree of malfunction, not limited to.

[0058] Based on the fact that operations are grouped, the most priority claims of users related to failed operations are identified based on predefined requirements.

[0059] A claim group is also allocated based on a predetermined requirement for the number of related transactions.

[0060] Step 103: receive at least one operation corresponding to at least one claim from the group of claims highlighted in the previous step;

[0061] The system 203 for recording and registering user complaints and complaints uses the published API 206. Using this API, which has a graphical interface, complaints, claims, as well as errors in the ATM that caused claims, are efficiently downloaded from system 203. Advantage of API lies in the fact that if the user needs the system 203 of accounting and registration of complaints and claims of customers to support other types of devices (such as processors or other testers), the manufacturer of a particular device only needs to publish Search for your own configuration file. This configuration file for system 203 contains various types of events, errors that occur, and their attributes.

[0062] In an exemplary embodiment, the user complaints and claims registration system 203 uses a “web service”, a well-known universal standard that supports interoperability between devices and components on a network. In one embodiment, the Web service front end description language (WSDL) is used in conjunction with the messaging protocol (SOAP) and markup language (XML) to provide web services over the Internet. The WSDL describes an open web service interface.

[0063] Step 104: analyzing at least one operation by applying text parsing;

[0064] In this step, the event log 206 is pre-checked for

completeness: are all necessary 206 event log files received, contain

whether claim transaction information. For custom claims,

for which the set of magazines 206 was not received / received in incomplete volume

ATM events, request re-collection of event logs.

[0065] Step 104 a: Perform at least one row reading

operations;

[0066] As shown in FIG. 3, the event log 206 is transmitted to the parser 301, which processes the event log 206 to generate a final file, for example, in XML format. It should be noted that the parser 301 can also be implemented using the Java programming language. The event log 206 often includes compilation and execution information that is used in debugging and other ATM maintenance operations. The parser 301 processes this information by using additional information to create a generated report file in XML format. In addition, the parser 301 can extract control characters that are not used during further steps of the method.

[0067] The parser 301 is a universal tool that can execute SQL queries for source files (ie, event logs). In addition, SQL queries allow the import, parsing, presentation, and export of a variety of different data from input event logs in various formats (for example, CSV, XML, txt, W3C, IIS, database table, and other data formats). In addition, the parser 301 provides filtering of event log entries, searching for data and templates in files of various data formats. The parser 301 also converts event logs from one data format to another data format, creates formatted reports and XML files containing data received from different log sources, and exports data (all or some parts of event logs) to database tables (for example , SQL tables), data mining, etc.

[0068] In addition, the parser 301 supports aggregated functions SUM, COUNT, AVG, MIN, and MAX. It supports the most common operators, such as more (>), IS NULL, LIKE, and IS IN. The 301 parser also supports most standard SQL queries: SELECT, WHERE, GROUP BY, HAVING, and ORDER BY.

[0069] In some embodiments, the parser 301 allows third-party software developers to add plug-ins to the parser 301. For example, to read and analyze the event log 206 of a particular data format, the parser 301 will interact with a plug-in, such as a user-defined reader.

[0070] Step 104 b: determining at least one user client session based on at least one operation;

[0071] In the next step, the user client session and its parameters are determined by the parser 301 based on at least one operation. The parameters of the client session can be the beginning of the client session (time of the beginning of the session), the end of the client session (time of the end of the session). Moreover, the termination of the client session can be caused due to the fact that the operation is terminated (forced termination of the session) and due to the fact that there was a forced completion of the transaction (forced termination of the session).

[0072] Additionally, at this step, using the parser 301, identify the ATM number 201 in which the failed operation occurred and a customer complaint arose, as well as the user's bank card number.

[0073] The table below shows what the event log 206 in PRJ format might look like:

[0074] Step 104 c: identifying at least one cause of the error in a user operation;

[0075] To generate a parsing file, the parser 301 may perform any combination of various operations in the event log 206. These can be filtering, searching for data and / or templates in files of various data formats, grouping and / or organizing the extracted information in accordance with the conditions specified in the request of the parser 301. The parser 301 detects at least one user operation, by which there were errors in the ATM, and generates output based on the results of the request. The output may be the final results of converting the event log 206 from one data format to another data format. It can also be the creation of formatted reports and XML files containing data obtained from various sources of event logs 206.

[0076] The parser 301 presents the result of its work to end users (for example, through the display module 303), writes the detected operations to one or more database tables, and / or writes the detected operations to a data file of the specified data format.

[0077] Analysis of the ATM event logs 206 for each claim with recording the results in a parsing file can be carried out in the following order:

[0078] 4.1 PRJ - on the subject of malfunctioning operations at an ATM;

[0079] 4.2 ERL - for errors and failures on the part of the iron of the ATM;

[0080] 4.3 NDC - for errors and failures recorded during the exchange of ATM host messages;

[0081] 4.4 PRR - optionally - for the contents of the check presented to the user for a failed operation;

[0082] 4.5 HWR - optionally - for example, errors recorded at the ATM, full information is contained in the ERL-log;

[0083] 4.6 PPS is optional;

[0084] 4.7 STF - optionally - to track the conditions that the client went to at the time of the failed operation;

[0085] 4.8. XML is optional.

[0086] The parser 301 in this step determines at least one cause of the error in user operations.

[0087] The cause of the error is determined by a symbolic or numerical identifier that uniquely corresponds to the type of operation, the type of error.

[0088] An example of displaying a successful cash withdrawal operation in a PRJ journal is as follows:

[0089] Однако при осуществлении операции выдачи наличных в журнале событий могут фиксироваться следующие ошибки: ошибка насчета, аппаратный сбой картридера или карта задержана по таймауту, денежные средства не взяты клиентом в течение таймаута, аппаратный сбой диспенсера, ошибки программного обеспечения, сбой электроэнергии и т.д.

[0089] However, during the cash withdrawal operation, the following errors may be recorded in the event log: error about, a card reader hardware failure or a card delayed by timeout, funds were not taken by the client during the timeout, dispenser hardware failure, software errors, power failure, etc. .d.

[0090] During the deposit operation, unrecognized banknotes are returned to the user. If the user did not pick up / could not pick up the returned unrecognized banknotes within a timeout of N seconds, the recognized money is stored in the cassette. In the ERL log, the error is fixed as follows:

[0091] The timeout is a configurable parameter of the ATM, so the values at different ATMs can be correlated. The average value of a custom parameter is 45 seconds.

[0092] Similarly, in the NDC log, a bill acceptor hardware failure is displayed in command 12. The following error options are possible:

- w3 - device hardware failure;

- w4 - device fatal failure.

[0093] In order to decrypt error codes, it is necessary to further analyze

data on the state of the ATM device.

[0094] In the NDC log, the error is fixed as follows:

[0095] Внутри клиентской сессии синтаксический анализатор 301 осуществляет поиск начала операции, окончания операции, а также поиск строки ошибки по операции.

[0095] Inside the client session, the parser 301 searches for the beginning of the operation, the end of the operation, and also searches for the error string for the operation.

[0096] The error string in exemplary embodiments may be as follows:

- HARDWARE FAILURE AT RECEPTION OF BILLS [date] [time]

- (961) TIME OUT AT THE INVITATION OF THE PAYMENT OF BILLS [date] [time]

- EXCEEDED WAITING TIME FOR EXCHANGE OF BILLS [date] [time]

- THE CARD IS NOT TAKEN BY THE CUSTOMER AND DETAINED [date] [time]

- CUSTOMER CARD CAPTURED [date] [time]

- ERROR INITIALIZATION INSERT BANKNOTES! [date Time]

- NO RESPONSE FROM HOST [date] [time]

- STATE FLOW ERROR [date] [time]

- 268) FAILURE BILL RECEIVER [date] [time]

- RECEPTION TRAY OVERFLOWED [date] [time]

[0097] Step 105: the user claims are classified based on user operations for which errors in the self-service device have occurred.

[0098] In accordance with the present invention, user claims are automatically classified from the event log file based on the initial rules.

[0099] Claims can be classified based on errors found by the operational days of the ATM and / or by types of operations, or types of ATMs, or types of event logs.

[00100] After the classification of user complaints based on user operations, a final or resulting file, for example, csv format, is generated. In some embodiments, the resulting file is archived with or without a password.

[00101] This file may contain the beginning of the client session, the end of the client session, the status of the end of the client session, as well as the date / time, terminal, user’s bank card number, transaction, amount; mistake.

[00102] The format of the resulting file may be as follows:

[00103] In some embodiments, recommendations are made on the basis of the resulting file to resolve the detected errors in the self-service device based on user complaints.

[00104] Aspects of the present invention can also be implemented using a data processing device that is a computer from a system (or tools such as a central / graphics processor or microprocessor) that reads and executes a program recorded on a storage device to perform the functions of the above Embodiment (s) and the method shown in FIG. 1, the steps of which are performed by a computer from a system or device by, for example, reading and executing a program recorded on a storage device to perform the functions of the above-described embodiment (s) of implementation. To this end, the program is provided to a computer, for example, through a network or from a recording medium of various types, serving as a storage device (for example, a computer-readable medium).

[00105] The data processing device may have additional features or functionality. For example, the data processing device may also include additional data storage devices (removable and non-removable), such as, for example, magnetic disks, optical disks or tape. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any way or using any technology for storing information, such as machine-readable instructions, data structures, program modules or other data. A storage device, removable storage, and non-removable storage are examples of computer storage media. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact ROM a disc (CD-ROM), universal digital disks (DVDs) or other optical storage devices, magnetic tapes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store the desired information and to which the data processing device can access. Any such computer storage medium can be part of a system for identifying and classifying the causes of user complaints in the ATM channel. The data processing device may also include an input device (s), such as a keyboard, mouse, pen, voice input device, touch input device, and so on. An output device (a), such as a display, speakers, printer, and the like, may also be included in the system.

[00106] The data processing device comprises communication connections that allow the device to communicate with other computing devices, for example over a network. Networks include local area networks and wide area networks along with other large, scalable networks, including, but not limited to, corporate networks and extranets. Communication connection is an example of a communication environment. Typically, a communication medium can be implemented using computer-readable instructions, data structures, program modules or other data in a modulated information signal, such as a carrier wave, or in another transport mechanism, and includes any information delivery medium. The term "modulated information signal" means a signal, one or more of its characteristics are changed or set in such a way as to encode information in this signal. By way of example, but without limitation, communication media include wired media such as a wired network or a direct wired connection, and wireless media such as acoustic, radio frequency, infrared, and other wireless media. The term “machine-readable medium”, as used herein, includes both storage media and communication media. The process sequences described in this document may be performed using hardware, software, or a combination thereof. When processes are performed using software, the program in which the sequence of processes is recorded can be installed and can be executed in the memory of a computer built into specialized hardware, or the program can be installed and can be run on a general-purpose computer that can perform various processes .

[00107] For example, a program may be pre-recorded on a recording medium such as a hard disk or ROM (read-only memory). Alternatively, the program can be temporarily or permanently saved (recorded) on a removable recording medium such as a floppy disk, CD-ROM (compact disc, designed for playback only), MO (magneto-optical) disc, DVD (digital universal disc) , magnetic disk or semiconductor memory. Removable recording media may be distributed as so-called software sold through a retail network.

[00108] The program may be installed from the removable recording medium described above to a computer, or may be transmitted via cable from a download site to a computer, or may be transmitted to a computer via network data channels such as a LAN (local area network) or The Internet. The computer can receive the program transmitted in this way and can install it on a recording medium such as an internal hard drive.

[00109] The processes described herein may be performed sequentially in time, as described, or may be performed in parallel or separately, depending on the processing characteristics of the device performing the processes, or as necessary. The system described in this document is a logical set of multiple devices and is not limited to the structure in which these devices are installed in one enclosure.

Claims (23)

1. A method for identifying and classifying the causes of user complaints in self-service devices, including the following steps: receive a set of user complaints in chronological order that arose when using a self-service device; allocating a group of user complaints for analysis based on at least one requirement for the type and number of transactions, with each claim corresponding to at least one operation; receive at least one operation corresponding to at least one claim from the group of claims highlighted in the previous step; analyze at least one operation by applying parsing of the text, and perform line-by-line reading of at least one operation; determining at least one user client session based on at least one operation; identify at least one cause of the error on the user's operation; carry out the classification of user complaints based on user operations for which errors occurred in the self-service device. 2. The method according to p. 1, characterized in that, together with a set of claims by the user receive a photo or video image of the user. 3. The method according to claim 1, characterized in that the resulting set of user complaints is filtered based on the type of operations that have occurred. 4. The method according to p. 1, characterized in that upon receipt of a set of claims of users using biometric identification of the user by voice to record his claim. 5. The method according to claim 1, characterized in that upon receipt of a set of user complaints, user operations are automatically recorded in the event log. 6. The method according to claim 1, characterized in that they distinguish a group of user complaints related to failed operations based on the proportion of affected users, or products, or the degree of malfunction. 7. The method according to p. 1, characterized in that they allocate a group of user complaints related to failed operations, based on their criticality. 8. The method according to p. 1, characterized in that the cause of the error is determined by a symbolic or numeric identifier, which uniquely corresponds to the type of operation and / or type of error. 9. The method according to claim 1, characterized in that the classification of claims is carried out on the basis of errors found by the operational days of the ATM, and / or by types of operations, and / or types of ATMs, and / or types of event logs. 10. A system for identifying and classifying the causes of user complaints in self-service devices, containing: at least one self-service device; at least one data processing device; at least one data storage device; at least one program where one or more programs are stored on one or more data storage devices and executed on one or more data processing devices, and one or more programs includes instructions for performing the method according to claim 1.

Images