Patents by Inventor Mustafa Levent Arslan
Mustafa Levent Arslan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240061874Abstract: A summarization performance evaluation method, and a summarization system sensitive to text categorization using the evaluation method is provided. The summarization system includes a database for storing the text to be summarized, a learning module which performs learning with machine learning in order to identify the categories and extract the summary of the text uploaded to the database, a categorization unit which identifies the categories of the text as a result of machine learning of the learning module, and is provided in the learning module, a sentence unit which summarizes the text as a result of machine learning of the learning module, and is provided in the learning module, a text summarization performance evaluation module for comparing the topic scores.Type: ApplicationFiled: December 2, 2021Publication date: February 22, 2024Applicant: SESTEK SES VE ILETISIM BILGISAYAR TEK.SAN.TIC.A.S.Inventors: Mustafa Levent ARSLAN, Murat SARACLAR, Mustafa ERDEN, Abdullah Samil GUSER
-
Patent number: 11501656Abstract: An interactive and automated training system, including a training portal having a training database, a training material creating module including a recorder and a dialogue identifier, a training and practicing module for training and practicing interactively with a trainee user, and a testing module for providing test case scenarios and grading a performance level of the trainee user. The recorder records real time interaction between an employee and a customer. The dialogue identifier differentiates the real time interaction into an employee dialogue and a customer dialogue, and provides indexing of subparts of the real time interaction. The training material creating module stores the real time interaction into the training database along with indexing data of the subparts of the real time interaction. The training material creating module categorizes a plurality of real time interactions stored in the training database into a plurality of training scenarios.Type: GrantFiled: October 29, 2018Date of Patent: November 15, 2022Assignee: SESTEK SES VE ILETISIM BILGISAYAR TEK. SAN VE TIC A.S.Inventors: Mustafa Levent Arslan, Anil Ayhan
-
Patent number: 11288682Abstract: An analytics system to analyze and report customer experience, comprising a customer interface device, an analysis server which analyzes data from a customer and a machine, and the database which is connected to the customer interface device and to the analysis server wherein the database receives data from the customer interface device, and/or the analysis server. The analytics system analyzes and reports customer experience.Type: GrantFiled: May 5, 2019Date of Patent: March 29, 2022Assignee: SESTEK SES VE ILETISIM BILG. TEKN. SAN. VE TIC. A.S.Inventors: Mustafa Levent Arslan, Tülin Ebcio{hacek over (g)}lu
-
Publication number: 20200349583Abstract: An analytics system to analyze and report customer experience, comprising a customer interface device, an analysis server which analyzes data from a customer and a machine, and the database which is connected to the customer interface device and to the analysis server wherein the database receives data from the customer interface device, and/or the analysis server. The analytics system analyzes and reports customer experience.Type: ApplicationFiled: May 5, 2019Publication date: November 5, 2020Applicant: SESTEK Ses ve Ìletisim Bilg. Tekn. San. Ve Tic. A.S.Inventors: Mustafa Levent ARSLAN, Tülin Ebcioglu
-
Publication number: 20200135041Abstract: An interactive and automated training system, including a training portal having a training database, a training material creating module including a recorder and a dialogue identifier, a training and practicing module for training and practicing interactively with a trainee user, and a testing module for providing test case scenarios and grading a performance level of the trainee user. The recorder records real time interaction between an employee and a customer. The dialogue identifier differentiates the real time interaction into an employee dialogue and a customer dialogue, and provides indexing of subparts of the real time interaction. The training material creating module stores the real time interaction into the training database along with indexing data of the subparts of the real time interaction. The training material creating module categorizes a plurality of real time interactions stored in the training database into a plurality of training scenarios.Type: ApplicationFiled: October 29, 2018Publication date: April 30, 2020Applicant: SESTEK SES VE ILETISIM BILGISAYAR TEK. SAN VE TIC A.S.Inventors: Mustafa Levent ARSLAN, Anil AYHAN
-
Patent number: 10282733Abstract: A speech analysis and evaluation system and method where behavioral and conversational features of successful customer representatives are determined. Reference models are obtained by analyzing the voices of the successful customer representatives using the voices' monotony and hesitation acoustic parameters and their respective speech recognition reliability score. A successful customer representative is the one that increases customer's satisfaction as a result of a conversation with a customer. Reference models that are generated by analyzing the voices of successful customer representatives are used for recruitment and training purposes.Type: GrantFiled: October 28, 2015Date of Patent: May 7, 2019Assignee: SESTEK SES VE ILETISIM BILGISAYAR TEKNOLOJILERI SANAYII VE TICARET ANONIM SIRKETIInventor: Mustafa Levent Arslan
-
Patent number: 10026405Abstract: Disclosed is a speaker diarization process for determining which speaker is speaking at what time during the course of a conversation. The entire process can be most easily described in five main parts: Segmentation where speech/non-speech decisions are made; frame feature extraction where useful information is obtained from the frames; segment modeling where the information from the frame feature extraction is combined with segment start and end time information to create segment specific features; speaker decisions when the segments are clustered to create speaker models; and corrections where frame level corrections are applied to the information extracted.Type: GrantFiled: May 3, 2016Date of Patent: July 17, 2018Assignee: SESTEK Ses velletisim Bilgisayar Tekn. San. Ve Tic A.S.Inventors: Mustafa Levent Arslan, Mustafa Erden, Sedat Demirba{hacek over (g)}, Gökçe Sarar
-
Patent number: 9818405Abstract: A dialog management system functioned by a special search algorithm, the search algorithm comprises the rule of recognizing the phrase directly, converting the words into terms, filtering the adjacency terms and recognizing, the dynamic field the Dialog Management System comprises: an application conducting a predefined operation between a user and a terminal; an input unit receiving an utterance from the user; recognition unit recognizing and converting the received utterance from sound into sequential words in a written text; processor; wherein the processor comprises dynamic field recognition unit; conversion unit, filter unit, a matching unit; a database storing a dictionary that includes the all of the definition of words and the word-term list.Type: GrantFiled: March 15, 2016Date of Patent: November 14, 2017Assignee: SAESTEK Ses ve Iletisim Bilgisayar Tekn. San. Ve Tic. A.S.Inventors: Mustafa Levent Arslan, Tülin Ebcio{hacek over (g)}lu, Ça{hacek over (g)}atay Yurdasal, Halil Ibrahim Kalkan, Ayşe Nuran Eyaz, Ibrahim Onat
-
Publication number: 20170323643Abstract: Disclosed is a speaker diarization process for determining which speaker is speaking at what time during the course of a conversation. The entire process can be most easily described in five main parts: Segmentation where speech/non-speech decisions are made; frame feature extraction where useful information is obtained from the frames; segment modeling where the information from the frame feature extraction is combined with segment start and end time information to create segment specific features; speaker decisions when the segments are clustered to create speaker models; and corrections where frame level corrections are applied to the information extracted.Type: ApplicationFiled: May 3, 2016Publication date: November 9, 2017Applicant: SESTEK Ses ve Ìletisim Bilgisayar Tekn. San. Ve Tic. A.S.Inventors: Mustafa Levent Arslan, Mustafa Erden, Sedat Demirbag, Gökçe Sarar
-
Publication number: 20170270921Abstract: A dialog management system functioned by a special search algorithm, the search algorithm comprises the rule of recognizing the phrase directly, converting the words into terms, filtering the adjacency terms and recognizing, the dynamic field the Dialog Management System comprises: an application conducting a predefined operation between a user and a terminal; an input unit receiving an utterance from the user; recognition unit recognizing and converting the received utterance from sound into sequential words in a written text; processor; wherein the processor comprises dynamic field recognition unit; conversion unit, filter unit, a matching unit; a database storing a dictionary that includes the all of the definition of words and the word-term list.Type: ApplicationFiled: March 15, 2016Publication date: September 21, 2017Applicant: SESTEK Ses ve Iletisim Bilgisayar Tekn. San. Ve Tic. A.S.Inventors: Mustafa Levent ARSLAN, Tülin EBCIOGLU, Çagatay YURDASAL, Halil Ibrahim KALKAN, Ayse Nuran EYAZ, Ibrahim ONAT
-
Patent number: 9672825Abstract: The present invention relates to implementing new ways of automatically and robustly evaluating agent performance, customer satisfaction, campaign and competitor analysis in a call-center and it is comprising; analysis consumer server, call pre-processing module, speech-to-text module, emotion recognition module, gender identification module and fraud detection module.Type: GrantFiled: January 3, 2013Date of Patent: June 6, 2017Assignee: SESTEK SES ILETISIM BILGISAYAR TEKNOLOJILERI SANAYI VE TICARET ANONIM SIRKETIInventors: Mustafa Levent Arslan, Ali Haznedaro{hacek over (g)}lu
-
Patent number: 9659564Abstract: The present invention relates to a non-standard speech detection system and method whereby a speech is analyzed based on models that are trained using personalized speech for each individual. The model is stored in a database and used to analyze a speech in real time to determine the content and behavior of an individual who is a party to a conversation that produces the speech. The results of the analysis can be used to determine if a conversation takes place under normal circumstances or under extraneous circumstances.Type: GrantFiled: October 22, 2015Date of Patent: May 23, 2017Assignee: SESTEK SES VE ILETISIM BILGISAYAR TEKNOLOJILERI SANAYI TICARET ANONIM SIRKETIInventor: Mustafa Levent Arslan
-
Patent number: 9462134Abstract: A user ID authentication method, wherein it comprises the process step of realization of a call between the phone number recorded previously in the customer information database (5), and the interactive voice response system (IVR) (1) in the case where a user logs over a web browser (4) into a restricted access system requiring high security such as Internet banking.Type: GrantFiled: July 12, 2013Date of Patent: October 4, 2016Assignee: SESTEK SES VE ILETISIM BILGISAYAR TEKNOLOJILERI SANAYII VE TICARET ANONIM SIRKETIInventors: Mustafa Levent Arslan, Ahmet Serdar Karadayi
-
Publication number: 20160125419Abstract: A speech analysis and evaluation system and method where behavioral and conversational features of successful customer representatives are determined. Reference models are obtained by analyzing the voices of the successful customer representatives. A successful customer representative is the one that increases customer's satisfaction as a result of a conversation with a customer. Reference models that are generated by analyzing the voices of successful customer representatives are used for recruitment and training purposes.Type: ApplicationFiled: October 28, 2015Publication date: May 5, 2016Applicant: SESTEK SES VE ILETISIM BILGISAYAR TEKNOLOJILERI SANAYII VE TICARET ANONIM SIRKETIInventor: MUSTAFA LEVENT ARSLAN
-
Publication number: 20160118050Abstract: The present invention relates to a non-standard speech detection system and method whereby a speech is analyzed based on models that are trained using personalized speech for each individual. The model is stored in a database and used to analyze a speech in real time to determine the content and behavior of an individual who is a party to a conversation that produces the speech. The results of the analysis can be used to determine if a conversation takes place under normal circumstances or under extraneous circumstances.Type: ApplicationFiled: October 22, 2015Publication date: April 28, 2016Applicant: SESTEK SES VE ILETISIM BILGISAYAR TEKNOLOJILERI SANAYI TICARET ANONIM SIRKETIInventor: Mustafa Levent ARSLAN
-
Publication number: 20150350438Abstract: The present invention relates to implementing new ways of automatically and robustly evaluating agent performance, customer satisfaction, campaign and competitor analysis in a call-center and it is comprising; analysis consumer server, call pre-processing module, speech-to-text module, emotion recognition module, gender identification module and fraud detection module.Type: ApplicationFiled: January 3, 2013Publication date: December 3, 2015Applicant: SESTEK SES VE ILETISIM BILGISAYAR TEKNOLOJILERI SANAYI VE TICARET ANONIM SIRKETIInventors: Mustafa Levent ARSLAN, Ali HAZNEDAROGLU
-
Publication number: 20150156328Abstract: A user ID authentication method, wherein it comprises the process step of realization of a call between the phone number recorded previously in the customer information database (5), and the interactive voice response system (IVR) (1) in the case where a user logs over a web browser (4) into a restricted access system requiring high security such as Internet banking.Type: ApplicationFiled: July 12, 2013Publication date: June 4, 2015Applicant: SESTEK SES VE ILETISIM BILGISAYAR TEKNOLOJILERIInventors: Mustafa Levent Arslan, Ahmet Serdar Karadayi