[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2016122294A1 - Evolutionary decision-making system and method operating according to criteria with automatic updates - Google Patents

Evolutionary decision-making system and method operating according to criteria with automatic updates Download PDF

Info

Publication number
WO2016122294A1
WO2016122294A1 PCT/MX2015/000017 MX2015000017W WO2016122294A1 WO 2016122294 A1 WO2016122294 A1 WO 2016122294A1 MX 2015000017 W MX2015000017 W MX 2015000017W WO 2016122294 A1 WO2016122294 A1 WO 2016122294A1
Authority
WO
WIPO (PCT)
Prior art keywords
classification
emotion
operator
growth
call
Prior art date
Application number
PCT/MX2015/000017
Other languages
Spanish (es)
French (fr)
Inventor
Mario Manuel VELEZ VILLA
Dino Alejandro Pardo Guzman
Raquel PERALTA TORRES
Fernando SOTO CAMACHO
Original Assignee
Velez Villa Mario Manuel
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Velez Villa Mario Manuel filed Critical Velez Villa Mario Manuel
Priority to PCT/MX2015/000017 priority Critical patent/WO2016122294A1/en
Publication of WO2016122294A1 publication Critical patent/WO2016122294A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state

Definitions

  • Figure 1 shows a flow chart of automatic verification when the Database (BD) has grown more than 10 percent.
  • Figure 2 is a block diagram of call processing by a system that determines the emotions of the interlocutors (client or operator).
  • Figure 3 shows a decision diagram where the probability calculation processes and the classifications involving models.
  • Figure 4 illustrates the classification of customers based on payment response.
  • Figure 5 shows the classification of users according to emotion / personality.
  • - Status or classification refers to customer compliance according to their history) and other criteria that vary according to the company's turn.
  • This invention complements the selection criteria of the customer to call with the information of the operators available at that time, so that the selection of the customer and the assignment to the operator is done so that the chances of success are greater, according to the result previously observed.
  • Client 1 meets all the requirements according to the traditional criteria of the company to be required with a call. Operators A, B and C are available. The process that determines whether the customer is called or not is the following:
  • the objective is to decide if the client is called or not according to. the operators available to assist you. In this case, looking at the numbers with the naked eye we could conclude that Operator A is a good option and that it has a good radius of success with the client. Operator 2 however has not been as successful, while Operator C has not had contact with Client 1 once. Getting carried away by the percentage of successful calls over total calls can be a mistake, as these numbers will not always give us a clear view of the client-operator relationship.
  • the key is then in the relationship between the operator and the customer. This is determined with a series of factors based mainly on the interaction during calls by means of software that determines the emotions in audio for each interlocutor.
  • the representation of each call for these purposes is then a chain of labels that indicate emotion (joy, sadness, anger and neutral) and the interlocutor (operator, client).
  • a time series algorithm then classifies the transition of the call from the beginning to the end and determines whether the call had a good, bad or neutral interaction. Each tag has a probability.
  • the probability that the call has had a good interaction is 78% and is qualified as such, without discarding the numbers for the other labels, which are stored in a table for future processes.
  • the call is processed by a system that determines the emotions of the partners (client or operator).
  • a time series algorithm classifies the transition of the call from the beginning to the end and determines whether the call had a good, bad or neutral interaction.
  • the selection of clients and operators is preferably made in a personalized way, that is, there is a list of specific operators for each client.
  • the staff is constantly rotated and it is convenient to have a relationship between the characteristics of the operators that are successful with a specific customer or, the characteristics of the clients for a particular operator.
  • Figure 3 shows a diagram of decisions where the probability calculation processes and the classifications that involve models (in blue background) are updated automatically when the growth of the records that intervene equals or exceeds 10%.
  • Customer history is evaluated against operator history and a list of customers with a higher probability of committing to pay is obtained. The blocks are modified according to the growth of the operator-client records in the database.
  • Figure 4. Classification of customers based on payment response. Classification / prediction models are re-trained or updated automatically when customer history increases by 10%. It shows the general structure of the customer classification process based on payment response. In this case, when automatic monitoring detects a 10% or greater growth in customer history, the prediction models are trained, so that the new information becomes part of the system's knowledge.
  • the class assignment according to the emotion is updated when the history growth meets the established criteria (growth of at least 10%).
  • the update consists in recalculating the emotion label when the number of instances or calls exceeds or equals 10%.
  • the established criteria for re-training can be modified without altering the functioning of the system components.
  • the update is a measure that requires constant monitoring that consumes resources, in the long run it will result in greater accuracy in predicting the response of customers, which will allow assigning operators according to each case.
  • the classification models of the operators and all the indicators that are calculated based on histories are kept in this form constantly updated.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Computational Linguistics (AREA)
  • Psychiatry (AREA)
  • Hospice & Palliative Care (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Computer Interaction (AREA)
  • Game Theory and Decision Science (AREA)
  • Child & Adolescent Psychology (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to components of an evolutionary decision-making system which adjusts to the changes presented by the data feeding the components thereof over time. The advantage of this type of system is that, over time, they become more precise, such that the more cases evaluated, the greater the amount of information available for training classification or predictive models.

Description

SISTEMA Y MÉTODO EVOLUTIVO DE TOMA DE DECISIONES QUE FUNCIONA POR CRITERIOS CON  SYSTEM AND EVOLUTIVE METHOD OF DECISION MAKING THAT WORKS BY CRITERIA WITH
ACTUALIZACIONES AUTOMATICAS  AUTOMATIC UPDATES
ANTECEDENTES Aunque la primera monografía sobre la expresión de las emociones en los animales y los seres humanos fue escrito por Charles Darwin en el siglo pasado los psicólogos han acumulado gradualmente los conocimientos en el campo de la detección de la emoción y el reconocimiento de voz, que ha atraído a una nueva ola de interés recientemente por dos psicólogos y especialistas de inteligencia artificial. Hay varias razones para este interés renovado: el progreso tecnológico de registro, almacenamiento y procesamiento de información de audio y visual; el desarrollo de sensores no invasivos; la llegada de las computadoras portátiles; y la necesidad de enriquecer la interfaz hombre-máquina. Mas alia, un nuevo campo de investigación en inteligencia artificial conocida como computación afectiva recientemente ha sido identificado. En cuanto a la investigación sobre el reconocimiento de las emociones en el habla, por un lado, los psicólogos han hecho muchos experimentos y sugerido teorías. Por otro lado, investigadores de inteligencia artificial hicieron contribuciones en las siguientes áreas: la síntesis de voz emocional, reconocimiento de las emociones y el uso de agentes para la decodificación y que expresan emociones. Se han hecho progresos similares con reconocimiento de voz. BACKGROUND Although the first monograph on the expression of emotions in animals and humans was written by Charles Darwin in the last century, psychologists have gradually accumulated knowledge in the field of emotion detection and voice recognition, which It has attracted a new wave of interest recently by two psychologists and artificial intelligence specialists. There are several reasons for this renewed interest: the technological progress of recording, storage and processing of audio and visual information; the development of non-invasive sensors; the arrival of laptops; and the need to enrich the man-machine interface. Furthermore, a new field of research in artificial intelligence known as affective computing has recently been identified. As for research on the recognition of emotions in speech, on the one hand, psychologists have done many experiments and suggested theories. On the other hand, artificial intelligence researchers made contributions in the following areas: emotional voice synthesis, recognition of emotions and the use of agents for decoding and expressing emotions. Similar progress has been made with voice recognition.
A pesar de la investigación sobre el reconocimiento de las emociones en el habla, el arte ha sido desprovisto de métodos y aparatos que utilizan el reconocimiento de emociones y reconocimiento de voz para fines comerciales. Despite research on the recognition of emotions in speech, art has been devoid of methods and devices that use emotion recognition and voice recognition for commercial purposes.
Las necesidades actuales exigen el uso máximo de los recursos y encontrar ventajas competitivas que permitan no solo mantenerse en el mercado, sino destacar y superar a sus competidores. Las tecnologías de hoy en día ofrecen una variedad de soluciones que se pueden aprovechar en diversos rubros. Los equipos de cómputo de alto rendimiento y los complejos algoritmos de inteligencia artificial permiten crear soluciones dinámicas que precisamente dan la ventaja competitiva con sistemas inteligentes capaces de "aprender" de la "experiencia", reduciendo cada vez más la necesidad de supervisión humana. Current needs demand the maximum use of resources and find competitive advantages that allow not only to remain in the market, but to highlight and surpass their competitors. Today's technologies offer a variety of solutions that can be used in various areas. High performance computing equipment and complex artificial intelligence algorithms allow to create dynamic solutions that precisely give the competitive advantage with intelligent systems capable of "learning" from "experience", increasingly reducing the need for human supervision.
Las relaciones interpersonales evolucionan constantemente, y debemos considerar que los operadores establecen varias veces al día relaciones con los clientes y por lo mismo comprueban que la fórmula para conseguir el compromiso del cliente varía dependiendo del cliente mismo, su estado de ánimo y otros factores desconocidos. Este sistema evalúa las relaciones entre el cliente y el operador y decide a cuál de los clientes llamar, de acuerdo a la disponibilidad de los operadores, valiéndose de modelos de clasificación/predicción. Los modelos se actualizan cada que la base de datos crece en un 10%. La verificación del crecimiento, así como el re-entrenamiento de los modelos se realiza de forma automática, sin supervisión manual humana. Interpersonal relationships are constantly evolving, and we must consider that operators establish relationships with customers several times a day and therefore prove that the formula for achieving customer engagement varies depending on the customer himself, his mood and other unknown factors. This system evaluates the relationships between the client and the operator and decides which of the clients to call, according to the availability of the operators, using classification / prediction models. The models are updated every time the database grows by 10%. Growth verification, as well as re-training of models is done automatically, without human manual supervision.
DESCRIPCION DETALLADA DE LA INVENCIÓN Breve descripción de figuras: DETAILED DESCRIPTION OF THE INVENTION Brief description of figures:
Figura 1 muestra un diagrama de flujo de la verificación automática cuando la Base de Datos (BD) ha crecido más del 10 por ciento. Figura 2 es un diagrama de bloques del procesamiento de llamadas por un sistema que determina las emociones de los interlocutores (cliente u operador). Figure 1 shows a flow chart of automatic verification when the Database (BD) has grown more than 10 percent. Figure 2 is a block diagram of call processing by a system that determines the emotions of the interlocutors (client or operator).
Figura 3 muestra un diagrama de decisiones donde los procesos de cálculo de probabilidad y las clasificaciones que involucran modelos. Figure 3 shows a decision diagram where the probability calculation processes and the classifications involving models.
Figura 4 ilustra la clasificación de clientes en base a respuesta de pago. Figura 5 muestra la clasificación de usuarios de acuerdo a la emoción / personalidad. Figure 4 illustrates the classification of customers based on payment response. Figure 5 shows the classification of users according to emotion / personality.
Asignación del par cliente-operador Assignment of the client-operator pair
Los métodos tradicionales de asignación de operadores a los clientes (deudores) involucran sólo las características del cliente y las necesidades de la empresa a la hora de hacer la llamada:  Traditional methods of assigning operators to customers (debtors) involve only the characteristics of the client and the needs of the company when making the call:
- Disponibilidad del cliente (horario, de modo que pueda atender la llamada)  - Customer availability (schedule, so that you can answer the call)
- Monto  - Amount
- Fecha de vencimiento  - Due date
- Status o clasificación (se refiere al cumplimiento del cliente de acuerdo a su historial) y demás criterios que varían de acuerdo al giro de la empresa.  - Status or classification (refers to customer compliance according to their history) and other criteria that vary according to the company's turn.
Este invento complementa los criterios de selección del cliente a llamar con la información de los operadores disponibles en ese momento, de modo que la selección del cliente y la asignación al operador se hace de manera que las probabilidades de éxito sean mayores, de acuerdo al resultado observado previamente. This invention complements the selection criteria of the customer to call with the information of the operators available at that time, so that the selection of the customer and the assignment to the operator is done so that the chances of success are greater, according to the result previously observed.
Tenemos las características del cliente y un registro de operadores que han tenido éxito en sus gestiones con él. Cada operador tiene un historial de clientes exitosos con un indicador de su nivel de influencia sobre el resultado final (outcome), éste puede ser positivo o negativo. Sin embargo, lo que debe determinar la llamada debe ser la relación que se da entre el cliente y el operador, ésta se determina de acuerdo a las emociones durante la interacción al tiempo de la llamada. We have the characteristics of the client and a registry of operators who have succeeded in their efforts with him. Each operator has a history of successful clients with an indicator of their level of influence on the final result (outcome), this can be positive or negative. However, what should determine the call must be the relationship between the client and the operator, this is determined according to the emotions during the interaction at the time of the call.
Ejemplo 1:  Example 1:
El Cliente 1 reúne todos los requisitos de acuerdo a los criterios tradicionales de la empresa para ser requerido con una llamada. Los operadores A, B y C están disponibles. El proceso que determina si el cliente es llamado o no es el siguiente:  Client 1 meets all the requirements according to the traditional criteria of the company to be required with a call. Operators A, B and C are available. The process that determines whether the customer is called or not is the following:
" * -, ·· · ;'. - > "* -, ·· ·; '. ->
Operador A Operador B Operador C |  Operator A Operator B Operator C |
NumLLam 15 25 0 NumLLam 15 25 0
Exito 12 8 0 Success 12 8 0
Yes 10 6 0 Yes 10 6 0
No 3 11 0 No 3 11 0
NumLLam: Número de veces que el operador ha llamado al cliente NumLLam: Number of times the operator has called the customer
Éxito: Sí pagó  Success: Yes paid
Yes: El cliente se comprometió a pagar  Yes: The client promised to pay
No: El cliente no se comprometió a pagar  No: The client did not agree to pay
El objetivo es decidir si el cliente es llamado o no de acuerdo a. los operadores disponibles para atenderle. En este caso, viendo los números a simple vista podríamos concluir que el Operador A es una buena opción y que tiene un buen radio de éxito con el cliente. El Operador 2 sin embargo no ha sido tan exitoso, mientras el Operador C no ha tenido contacto con el Cliente 1 ni una sola vez. Dejarnos llevar por el porcentaje de llamadas de éxito sobre el total de llamadas puede ser un error, pues no siempre estos números nos darán una visión clara de la relación cliente - operador. The objective is to decide if the client is called or not according to. the operators available to assist you. In this case, looking at the numbers with the naked eye we could conclude that Operator A is a good option and that it has a good radius of success with the client. Operator 2 however has not been as successful, while Operator C has not had contact with Client 1 once. Getting carried away by the percentage of successful calls over total calls can be a mistake, as these numbers will not always give us a clear view of the client-operator relationship.
La explicación es simple: las relaciones entre las personas tiende a cambiar, evoluciona. De modo que el Operador 1 que creemos es el indicado para la llamada, pudo haber tenido éxito en las primeras 12 llamadas y tener una terrible interacción durante las 3 restantes, lo que lo descalifica para atender al cliente. Por otro lado, si las llamadas exitosas y las malas interacciones han sido intercaladas entonces tal vez no se descarte al Operador A del todo. Finalmente, si las llamadas de éxito han sido todas al final, teniendo las negativas al principio, definitivamente el Operador A es una excelente opción y se hace la llamada al Cliente 1.  The explanation is simple: relationships between people tend to change, it evolves. So the Operator 1 that we believe is the one indicated for the call, could have succeeded in the first 12 calls and had a terrible interaction during the remaining 3, which disqualifies him to attend to the client. On the other hand, if successful calls and bad interactions have been interspersed then Operator A may not be discarded at all. Finally, if the success calls have been all at the end, having the negatives at the beginning, definitely the Operator A is an excellent option and the call is made to Client 1.
La clave está entonces en la relación entre el operador y el cliente. Esta la determinamos con una serie de factores basados principalmente en la interacción durante las llamadas por medio de un software que determina las emociones en audio para cada interlocutor. La representación de cada llamada para estos fines es entonces una cadena de etiquetas que indican la emoción (alegría, tristeza, enojo y neutral) y el interlocutor (operador, cliente). Un algoritmo de series de tiempo entonces clasifica la transición de la llamada desde el inicio hasta el final y determina si la llamada tuvo una interacción buena, mala o neutral. Cada etiqueta tiene una probabilidad. Ejemplo 2:  The key is then in the relationship between the operator and the customer. This is determined with a series of factors based mainly on the interaction during calls by means of software that determines the emotions in audio for each interlocutor. The representation of each call for these purposes is then a chain of labels that indicate emotion (joy, sadness, anger and neutral) and the interlocutor (operator, client). A time series algorithm then classifies the transition of the call from the beginning to the end and determines whether the call had a good, bad or neutral interaction. Each tag has a probability. Example 2:
Llamada: 13  Call: 13
Cliente: 1  Client: 1
Operador: A Buena Mala Neutral  Operator: A Good Bad Neutral
Relación: 0.78 0.12 0.10 Ratio: 0.78 0.12 0.10
En este caso la probabilidad de que la llamada haya tenido una interacción buena es de 78% y se califica como tal, sin descartar los números para las otras etiquetas, que quedan almacenados en una tabla para procesos futuros. In this case the probability that the call has had a good interaction is 78% and is qualified as such, without discarding the numbers for the other labels, which are stored in a table for future processes.
Figura 2. La llamada es procesada por un sistema que determina las emociones de los interlocutores (cliente u operador). Un algoritmo de series de tiempo clasifica la transición de la llamada desde el inicio hasta el final y determina si la llamada tuvo una interacción buena, mala o neutral. Clases de operadores y Clientes Figure 2. The call is processed by a system that determines the emotions of the partners (client or operator). A time series algorithm classifies the transition of the call from the beginning to the end and determines whether the call had a good, bad or neutral interaction. Classes of operators and Clients
La selección de clientes y operadores se hace preferentemente de modo personalizado, esto es, hay una lista de operadores específicos para cada cliente. Sin embargo, el personal se rota constantemente y es conveniente tener una relación entre las características de los operadores que tienen éxito con un cliente específico o bien, las características de los clientes para un operador en especial. Podemos generalizar partiendo del conocimiento obtenido a través de las observaciones y definir niveles de éxito o fracaso entre tipos de clientes y operadores de acuerdo a sus características.  The selection of clients and operators is preferably made in a personalized way, that is, there is a list of specific operators for each client. However, the staff is constantly rotated and it is convenient to have a relationship between the characteristics of the operators that are successful with a specific customer or, the characteristics of the clients for a particular operator. We can generalize based on the knowledge obtained through observations and define levels of success or failure between types of customers and operators according to their characteristics.
La figura 3 muestra un diagrama de decisiones donde los procesos de cálculo de probabilidad y las clasificaciones que involucran modelos (en fondo azul) se actualizan de modo automático cuando el crecimiento de los historiales que intervienen iguala o supera el 10%. El historial de los clientes es evaluado contra el historial de los operadores y se obtiene una lista de clientes con una probabilidad mayor de comprometerse a pagar. Los bloques se modifican conforme el crecimiento de los registros de operadores-clientes en la base de datos. Figura 4. Clasificación de clientes en base a respuesta de pago. Los modelos de clasificación/predicción se re-entrenan o actualizan automáticamente cuando el historial de clientes aumenta en 10%. Muestra la estructura general del proceso de clasificación de clientes en base a respuesta de pago. En este caso, cuando el monitoreo automático detecta un crecimiento del 10% o mayor en el historial de los clientes, los modelos de predicción son re- entrenados, de modo que la nueva información pasa a ser parte del conocimiento del sistema. Figure 3 shows a diagram of decisions where the probability calculation processes and the classifications that involve models (in blue background) are updated automatically when the growth of the records that intervene equals or exceeds 10%. Customer history is evaluated against operator history and a list of customers with a higher probability of committing to pay is obtained. The blocks are modified according to the growth of the operator-client records in the database. Figure 4. Classification of customers based on payment response. Classification / prediction models are re-trained or updated automatically when customer history increases by 10%. It shows the general structure of the customer classification process based on payment response. In this case, when automatic monitoring detects a 10% or greater growth in customer history, the prediction models are trained, so that the new information becomes part of the system's knowledge.
Figura 5. Clasificación de usuarios de acuerdo a la emoción / personalidad. En este caso, la asignación de clase de acuerdo a la emoción se actualiza cuando el crecimiento del historial cumple con el criterio establecido (crecimiento de al menos 10%). En el caso de la clasificación de usuarios de acuerdo a la emoción / personalidad, la actualización consiste en recalcular la etiqueta de emoción cuando el número de instancias o llamadas supera o iguala el 10%. En este proceso los modelos de reconocimiento de emociones y de reconocimiento de voz no vuelven a entrenarse. El criterio establecido para el re-entrenamiento puede ser modificado sin alterar el funcionamiento de los componentes del sistema. Aunque la actualización es una medida que requiere de un monitoreo constante que consume recursos, a la larga redundará en una mayor precisión en la predicción de la respuesta de los clientes, lo que permitirá asignar operadores de acuerdo a cada caso. Los modelos de clasificación de los operadores y todos los indicadores que se calculan en base a historiales se mantienen en esta forma en constante actualización. Figure 5. Classification of users according to emotion / personality. In this case, the class assignment according to the emotion is updated when the history growth meets the established criteria (growth of at least 10%). In the case of the classification of users according to emotion / personality, the update consists in recalculating the emotion label when the number of instances or calls exceeds or equals 10%. In this process the models of emotion recognition and voice recognition are not retrained. The established criteria for re-training can be modified without altering the functioning of the system components. Although the update is a measure that requires constant monitoring that consumes resources, in the long run it will result in greater accuracy in predicting the response of customers, which will allow assigning operators according to each case. The classification models of the operators and all the indicators that are calculated based on histories are kept in this form constantly updated.

Claims

REIVINDICACIONESue se reclama es: CLAIMS that are claimed is:
1. Un sistema y método evolutivo de toma de decisiones que se ajusta a los cambios que presentan los datos que alimentan sus componentes a través del tiempo y que funciona como sigue: a. El sistema verifica automáticamente cuando la Base de Datos (BD) ha crecido más del 10 por ciento, para cuando se cumple esta condición, se lanza un proceso de reentrenamiento de los modelos de clasificación. b. Una llamada es procesada por un sistema que determina las emociones de los interlocutores (cliente u operador). Un algoritmo de series de tiempo clasifica la transición de la llamada desde el inicio hasta el final y determina si la llamada tuvo una interacción buena, mala o neutral. c. Toma de decisiones donde los procesos de cálculo de probabilidad y las clasificaciones que involucran modelos se actualizan de modo automático cuando el crecimiento de los historiales que intervienen iguala o supera el 10%. El historial de los clientes es evaluado contra el historial de los operadores y se obtiene una lista de clientes con una probabilidad mayor de comprometerse a pagar. Los bloques se modifican conforme el crecimiento de los registros de operadores-clientes en la base de datos. d. Clasificación de clientes en base a respuesta de pago. Los modelos de clasificación/predicción se re-entrenan o actualizan automáticamente cuando el historial de clientes aumenta en 10%. Muestra la estructura general del proceso de clasificación de clientes en base a respuesta de pago. e. Clasificación de usuarios de acuerdo a la emoción / personalidad. En este caso, la asignación de clase de acuerdo a la emoción se actualiza cuando el crecimiento del historial cumple con el criterio establecido (crecimiento de al menos 10%). 1. An evolutionary system and method of decision making that adjusts to the changes presented by the data that feed its components over time and that works as follows: a. The system automatically verifies when the Database (BD) has grown by more than 10 percent, by the time this condition is met, a retraining process of the classification models is launched. b. A call is processed by a system that determines the emotions of the partners (client or operator). A time series algorithm classifies the transition of the call from the beginning to the end and determines whether the call had a good, bad or neutral interaction. C. Decision making where the probability calculation processes and the classifications that involve models are updated automatically when the growth of the records that intervene equals or exceeds 10%. Customer history is evaluated against operator history and a list of customers with a higher probability of committing to pay is obtained. The blocks are modified according to the growth of the operator-client records in the database. d. Classification of customers based on payment response. Classification / prediction models are re-trained or updated automatically when customer history increases by 10%. It shows the general structure of the customer classification process based on payment response. and. User classification according to emotion / personality. In this case, the class assignment according to the emotion is updated when the history growth meets the established criteria (growth of at least 10%).
2. El sistema y método de la reivindicación anterior que en el caso de la clasificación de usuarios de acuerdo a la emoción / personalidad, la actualización consiste en recalcular la etiqueta de emoción cuando el número de instancias o llamadas supera o iguala el 10%. En este proceso los modelos de reconocimiento de emociones y de reconocimiento de voz no vuelven a entrenarse. 2. The system and method of the previous claim that in the case of the classification of users according to the emotion / personality, the update consists in recalculating the emotion label when the number of instances or calls exceeds or equals the 10% In this process the models of emotion recognition and voice recognition are not retrained.
El sistema y método de la reivindicación 1 que cuando el monitoreo automático detecta un crecimiento del 10% o mayor en el historial de los clientes, los modelos de predicción son re-entrenados, de modo que la nueva información pasa a ser parte del conocimiento del sistema. The system and method of claim 1 that when automatic monitoring detects a 10% or greater growth in customer history, the prediction models are re-trained, so that the new information becomes part of the knowledge of the system.
PCT/MX2015/000017 2015-01-27 2015-01-27 Evolutionary decision-making system and method operating according to criteria with automatic updates WO2016122294A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/MX2015/000017 WO2016122294A1 (en) 2015-01-27 2015-01-27 Evolutionary decision-making system and method operating according to criteria with automatic updates

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/MX2015/000017 WO2016122294A1 (en) 2015-01-27 2015-01-27 Evolutionary decision-making system and method operating according to criteria with automatic updates

Publications (1)

Publication Number Publication Date
WO2016122294A1 true WO2016122294A1 (en) 2016-08-04

Family

ID=56543812

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MX2015/000017 WO2016122294A1 (en) 2015-01-27 2015-01-27 Evolutionary decision-making system and method operating according to criteria with automatic updates

Country Status (1)

Country Link
WO (1) WO2016122294A1 (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040249650A1 (en) * 2001-07-19 2004-12-09 Ilan Freedman Method apparatus and system for capturing and analyzing interaction based content
US20080189171A1 (en) * 2007-02-01 2008-08-07 Nice Systems Ltd. Method and apparatus for call categorization
US20090306967A1 (en) * 2008-06-09 2009-12-10 J.D. Power And Associates Automatic Sentiment Analysis of Surveys
US20110144971A1 (en) * 2009-12-16 2011-06-16 Computer Associates Think, Inc. System and method for sentiment analysis
US20110206198A1 (en) * 2004-07-14 2011-08-25 Nice Systems Ltd. Method, apparatus and system for capturing and analyzing interaction based content
US20130018685A1 (en) * 2011-07-14 2013-01-17 Parnaby Tracey J System and Method for Tasking Based Upon Social Influence
US20140220526A1 (en) * 2013-02-07 2014-08-07 Verizon Patent And Licensing Inc. Customer sentiment analysis using recorded conversation
US20140289253A1 (en) * 2013-03-20 2014-09-25 Infosys Limited System for management of sentiments and methods thereof

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040249650A1 (en) * 2001-07-19 2004-12-09 Ilan Freedman Method apparatus and system for capturing and analyzing interaction based content
US20110206198A1 (en) * 2004-07-14 2011-08-25 Nice Systems Ltd. Method, apparatus and system for capturing and analyzing interaction based content
US20080189171A1 (en) * 2007-02-01 2008-08-07 Nice Systems Ltd. Method and apparatus for call categorization
US20090306967A1 (en) * 2008-06-09 2009-12-10 J.D. Power And Associates Automatic Sentiment Analysis of Surveys
US20110144971A1 (en) * 2009-12-16 2011-06-16 Computer Associates Think, Inc. System and method for sentiment analysis
US20130018685A1 (en) * 2011-07-14 2013-01-17 Parnaby Tracey J System and Method for Tasking Based Upon Social Influence
US20140220526A1 (en) * 2013-02-07 2014-08-07 Verizon Patent And Licensing Inc. Customer sentiment analysis using recorded conversation
US20140289253A1 (en) * 2013-03-20 2014-09-25 Infosys Limited System for management of sentiments and methods thereof

Similar Documents

Publication Publication Date Title
US9349100B2 (en) Method for providing a prompt for real-time cognitive assistance
Lieder et al. Overrepresentation of extreme events in decision making reflects rational use of cognitive resources.
US20210118424A1 (en) Predicting personality traits based on text-speech hybrid data
US20190213522A1 (en) System and method for determining user metrics
US20220245557A1 (en) Analyzing agent data and automatically delivering actions
CA3052106A1 (en) Psychotherapy triage method
US12073323B2 (en) System and method for intelligent service intermediation
CN108363745A (en) The method and apparatus that robot customer service turns artificial customer service
CN113196314A (en) Adapting a prediction model
Campo et al. Retreatment predictions in odontology by means of CBR systems
US20230388420A1 (en) Adaptive cloud conversation ecosystem
CN112488437A (en) Human resource management system and method thereof
WO2016122294A1 (en) Evolutionary decision-making system and method operating according to criteria with automatic updates
US12062229B2 (en) Identification process of a dental implant visible on an input image by means of at least one convolutional neural network
KR101640867B1 (en) A method and a system for providing user-customized learning course based on machine learning
US20240330336A1 (en) Method for Collaborative Knowledge Base Development
Gupta et al. Enhancing complex wound care by leveraging artificial intelligence: an artificial intelligence chatbot software study
US11556720B2 (en) Context information reformation and transfer mechanism at inflection point
Petric et al. Towards a robot-assisted autism diagnostic protocol: Modelling and assessment with POMDP
US20180293318A1 (en) Methods And Systems For Determining People You Should Know and Autonomous Social Coaching
US20210004769A1 (en) Automated event coordination
Chifu et al. Exploring the selection of the optimal web service composition through ant colony optimization
Bittar et al. Surrogate gradient spiking neural networks as encoders for large vocabulary continuous speech recognition
Madhuravani et al. Prediction exploration for coronary heart disease aid of machine learning
KR102652693B1 (en) Artificial intelligence-based makeup kit recommendation system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15880310

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 04/10/2017)

122 Ep: pct application non-entry in european phase

Ref document number: 15880310

Country of ref document: EP

Kind code of ref document: A1