CN115206328A

CN115206328A - Data processing method and device and customer service robot

Info

Publication number: CN115206328A
Application number: CN202210877181.0A
Authority: CN
Inventors: 刘安平; 张宝华
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-07-25
Filing date: 2022-07-25
Publication date: 2022-10-18

Abstract

The specification provides a data processing method and device and a customer service robot, and is applied to the technical field of artificial intelligence. The customer service robot monitors environmental sounds, acquires and determines the current business service type according to first target data of a target customer under the condition that the current condition meets a preset trigger condition; determining a matched target processing rule from preset processing rules according to the current business service type; according to the target processing rule, acquiring and according to second target data related to the target client, and determining whether the target client has a business service requirement; and under the condition that the target user is determined to have business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user. Therefore, different business service scenes can be effectively and comprehensively covered, customers with business service requirements can be accurately detected and identified, and active interaction is performed, so that the customers can obtain better service experience.

Description

Data processing method and device and customer service robot

Technical Field

The specification belongs to the technical field of artificial intelligence, and particularly relates to a data processing method and device and a customer service robot.

Background

In the field of artificial intelligence technology, with the development and popularization of robotics, more and more robots are put into customer service applications. For example, in a business hall of an organization such as a bank, a service robot is often put in order to solve a problem that a client consults or help the client handle related business.

However, based on the existing method, the customer service robot needs to be woken up to serve the customer when the customer speaks a keyword or is touched by the customer. Based on the existing method, the customer service robot cannot actively and accurately identify customers with business service requirements, actively interacts with the customers, and further influences the service experience of the customers.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The specification provides a data processing method, a data processing device and a customer service robot, which can effectively and comprehensively cover different business service scenes, accurately detect and identify customers with business service requirements, and actively interact with the customers on the premise of not waking up the customers so as to intelligently provide relevant business services for the customers and enable the customers to obtain better service experience.

The present specification provides a data processing method applied to a customer service robot, including:

monitoring environmental sounds to determine whether preset triggering conditions are met currently;

under the condition that the preset triggering condition is determined to be met currently, first target data about a target client are obtained;

determining the current service type of the business according to the first target data;

determining a matched target processing rule from preset processing rules according to the current business service type;

acquiring second target data about the target client according to the target processing rule;

determining whether the target client has business service requirements or not by processing the second target data according to the target processing rule;

and under the condition that the target user has business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user.

In one embodiment, monitoring ambient sounds to determine whether a preset trigger condition is currently met includes:

collecting current environment sound, and carrying out voice detection on the current environment sound to determine whether voice exists in the current environment sound;

under the condition that the current environment sound is determined to have the human voice, extracting human voice audio from the current environment sound;

detecting whether the human voice audio is interference sound;

and under the condition that the human voice audio is determined not to be the interference sound, determining that the target client exists in the current environment, and determining that the preset trigger condition is met.

In one embodiment, the disturbing sound comprises at least one of: broadcast sounds, voice sounds of workers, meaningless human voices.

In one embodiment, determining the current type of business service according to the first target data includes:

processing first audio data in the first target data by using a preset voice recognition model to obtain a corresponding first text;

detecting whether a preset keyword or a relevant word related to the preset keyword exists in the first text;

under the condition that a preset keyword or a relevant word related to the preset keyword exists in the first text, determining that the current business service type is a first-class business service type; the first type of business service type is a business service type that a client consults a business question to wait for a response.

In one embodiment, obtaining second targeting data for the target customer based on the targeting process rules comprises:

acquiring audio data in a first time period after the first audio data according to a target processing rule, wherein the audio data is used as second audio data in second target data;

and/or the presence of a gas in the gas,

determining the current position of a target client by using the first audio data according to a target processing rule; and shooting a plurality of images towards the current position of the target client according to a preset time interval to be used as second image data in the second target data.

In one embodiment, determining whether the target client has a business service requirement by processing the second target data according to the target processing rule comprises:

processing second audio data in the second target data by using a preset voice recognition model to obtain a corresponding second text;

detecting whether a reply text related to a preset keyword or associated word exists in the second text;

and in the case that the answer text is determined not to exist in the second text, determining that the target client has business service requirements.

detecting whether a worker exists at the current position of the target client according to second image data in the second target data;

and determining that the target client has business service requirements under the condition that no staff exists at the current position of the target client.

In one embodiment, determining the current type of the business service according to the first target data further includes:

detecting whether a target client uses a self-service machine to handle self-service business currently or not according to first image data in first target data;

under the condition that the target client is determined to be currently transacting self-service business by using the self-service machine, determining the current business service type as a second type business service type; the second type of business service type is a business service type for a client to use the self-service machine to handle self-service business.

and according to the target processing rule, recording the video data in a second time period after the first image data towards the position direction of the self-service machine as second image data in second target data.

detecting whether a problem occurs when a target client uses the self-service machine to handle self-service business or not according to second image data in second target data;

and under the condition that the target client is determined to have a problem when the target client uses the self-service machine to handle the self-service business, determining that the target client has business service requirements.

In one embodiment, interacting with the target customer according to preset interaction rules includes:

generating a matched interactive text according to a preset interactive rule;

generating corresponding interactive audio according to the interactive text;

and playing the interactive audio to the target client.

In one embodiment, while playing the interactive audio to the target customer, the method further comprises:

and according to a preset interaction rule, flashing an indicator light according to the matched frequency to prompt a target customer.

This specification also provides a data processing apparatus applied to a customer service robot, including:

the monitoring module is used for monitoring environmental sounds to determine whether the preset triggering conditions are met or not currently;

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first target data related to a target client under the condition that a preset trigger condition is determined to be met currently;

the first determining module is used for determining the current business service type according to the first target data;

the second determining module is used for determining a matched target processing rule from the preset processing rules according to the current business service type;

the second acquisition module is used for acquiring second target data about the target client according to the target processing rule;

the third determining module is used for determining whether the target client has business service requirements or not by processing the second target data according to the target processing rule;

and the interaction module is used for interacting with the target customer according to a preset interaction rule under the condition that the target customer is determined to have business service requirements so as to provide matched business service for the target customer.

The specification also provides a customer service robot, which comprises a processor and a memory for storing processor executable instructions, wherein the processor executes the instructions to realize the relevant steps of the data processing method.

The present specification also provides a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, carry out the steps associated with the data processing method.

Based on the data processing method and device and the customer service robot provided by the specification, the customer service robot monitors environmental sounds, acquires and determines the current business service type through multi-mode fusion by utilizing multi-dimensional data according to first target data of a target client under the condition that the current condition meets a preset trigger condition; determining a matched target processing rule from preset processing rules according to the current business service type; according to the target processing rule, acquiring and according to second target data related to the target client, and determining whether the target client has a business service requirement or not by multi-mode fusion by utilizing multi-dimensional data; and under the condition that the target user has business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user. Distinguishing different service types according to first target data; and then aiming at different business server types, according to the matched target processing rule, acquiring and utilizing second target data, and accurately judging whether the target client really has business service requirements at present. Therefore, different business service scenes can be effectively and comprehensively covered, customers with business service requirements can be accurately detected and identified, and the customers can actively interact with the customers on the premise of not waking up the customers, so that related business services are intelligently provided for the customers, and the customers can obtain better service experience.

Drawings

In order to more clearly illustrate the embodiments of the present description, the drawings needed for the embodiments will be briefly described below, the drawings in the following description are only some of the embodiments described in the present description, and other drawings may be obtained by those skilled in the art without inventive efforts.

FIG. 1 is a flow diagram illustrating a data processing method according to an embodiment of the present disclosure;

FIG. 2 is a diagram illustrating an embodiment of a data processing method according to an embodiment of the present disclosure;

FIG. 3 is a diagram illustrating an example of a scenario in which an embodiment of the data processing method provided by the embodiments of the present specification is applied;

FIG. 4 is a diagram illustrating an embodiment of a data processing method according to an embodiment of the present disclosure;

FIG. 5 is a diagram illustrating an embodiment of a data processing method according to an embodiment of the present disclosure;

FIG. 6 is a schematic structural component diagram of a customer service robot provided in an embodiment of the present disclosure;

fig. 7 is a schematic structural component diagram of a data processing apparatus according to an embodiment of the present specification.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

Referring to fig. 1, an embodiment of the present disclosure provides a data processing method, where the method is specifically applied to a side of a customer service robot. In specific implementation, the method may include the following:

s101: monitoring environmental sounds to determine whether preset triggering conditions are met currently;

s102: under the condition that the preset triggering condition is determined to be met currently, first target data about a target client are obtained;

s103: determining the current service type of the business according to the first target data;

s104: determining a matched target processing rule from preset processing rules according to the current service type;

s105: acquiring second target data about the target client according to the target processing rule;

s106: determining whether the target client has business service requirements or not by processing the second target data according to the target processing rule;

s107: and under the condition that the target user has business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user.

Based on the embodiment, under the condition that the preset triggering condition is met, the current business service type is obtained and determined according to the first target data; then, different business service types are distinguished, and whether the target client really has business service requirements or not is accurately determined according to second target data related to the target client based on matched target processing rules aiming at the current different business service types; and further, under the condition that the target client is determined to have business service requirements, the client can actively interact with the client without waking up, and related business services are intelligently provided for the client, so that the client can obtain better service experience.

In some embodiments, the data processing method can be specifically applied to the side of the customer service robot. The customer service robot may specifically include an intelligent robot disposed in a business hall of an organization such as a bank, and configured to provide diversified business services related to the organization such as the bank for a customer.

It should be understood that the above-mentioned exemplary service hall of an organization such as a bank is only an exemplary illustration. In specific implementation, the customer service robot can be put in and applied to other suitable places according to specific situations and business requirements. For example, the customer service robot can be applied to hotel lobbies or shopping malls to provide more diversified business services for customers.

In some embodiments, referring to fig. 2, the customer service robot at least includes a processor, a display screen, a radio, a camera, and a voice player. Specifically, in order to better monitor the environmental sound and collect the audio data, the radio may be a microphone array.

Further, in order to cope with a relatively more complex customer service interaction scene, the customer service robot may be further configured with a signal transceiver. As shown in fig. 3, the customer service robot may further perform data interaction with a cloud server through a signal transceiver. Therefore, the customer service robot can only be responsible for collecting environmental sound, audio data, image data and the like, and transmitting the collected data to the cloud server. The server is responsible for processing the data to obtain a corresponding data processing result; and then the data processing result is transmitted to the customer service robot. The customer service robot can interact with the customer correspondingly according to the received data processing result.

The cloud server may specifically include a background server applied to one side of the cloud computing platform and capable of implementing functions such as data transmission and data processing. Specifically, the cloud server may be, for example, an electronic device having data operation, storage function, and network interaction function. Alternatively, the cloud server may also be a software program that runs in the electronic device and provides support for data processing, storage, and network interaction. In this embodiment, the number of servers included in the cloud server is not specifically limited. The cloud server may specifically be one server, may also be several servers, or a server cluster formed by several servers.

In some embodiments, referring to fig. 4, the monitoring the environmental sound to determine whether the preset trigger condition is currently met may include the following steps:

s1: acquiring current environment sound, and carrying out voice detection on the current environment sound to determine whether voice exists in the current environment sound;

s2: under the condition that the current environment sound is determined to have the human voice, extracting human voice audio from the current environment sound;

s3: detecting whether the human voice audio is interference sound;

s4: and under the condition that the human voice audio is determined not to be the interference sound, determining that the target client exists in the current environment, and determining that the preset trigger condition is met.

The target customer may be specifically understood as a customer that may have a business service requirement and is to be further confirmed. For the target customer, the customer service robot can further track follow-up to confirm whether there is a real business service requirement.

Based on the embodiment, the customer service robot can set the radio to be in a normally open state, and detect whether a target customer possibly having business service requirements exists in the current environment by monitoring the environmental sound so as to determine whether the preset triggering condition is met.

In some embodiments, when implemented, VAD detection (voice activity detection) techniques may be employed to monitor the ambient sounds for the presence of human voice. In the case where the human voice existing in the current environmental sound is detected, audio data including the human voice may be extracted from the current environmental sound as human voice audio.

In some embodiments, the disturbing sound may specifically include at least one of: broadcast sounds, voice sounds of workers, meaningless human voices, and the like.

In the above environment, there are often meaningless speech sounds such as a broadcast sound of a called number, a speech sound of a worker in the service hall, and a word spoken by the customer or the worker during an interaction, in addition to the sound of the customer, taking a service hall of an organization such as a bank as an example. Although the voice is also a human voice, the customer service robot cannot determine whether the customer has a business service requirement based on the human voice. On the contrary, the human voice interferes with the judgment of the customer service robot.

Based on the embodiment, by considering and finely distinguishing the interference sound in the environment, the judgment error of the customer service robot can be effectively reduced, and whether the preset triggering condition is met or not is judged more accurately.

In some embodiments, the detecting whether the human voice audio is an interfering sound may include the following steps:

s1: matching the voice audio according to a preset voice sample library to obtain a corresponding matching result;

s2: and determining whether the human voice is interference sound according to the matching result.

The preset sound sample library can specifically store voiceprint samples of workers, common meaningless human voice audio samples, common broadcast sound samples and the like.

Before specific implementation, voiceprint data of workers can be collected, voiceprint samples corresponding to the workers respectively are constructed and stored in a preset voice sample library; a large number of historical environmental sound records can be collected, meaningless voice frequencies with high occurrence frequency are screened out from the large number of historical environmental sound records, and the meaningless voice frequencies are used as common meaningless voice frequency samples and stored in a preset voice sample library; broadcast sound frequency with high occurrence frequency can be screened from a large amount of historical environmental sound records to be used as broadcast sound samples of Yangtze river and stored in a preset sound sample library.

In specific implementation, sound features can be extracted from human voice audio; and respectively matching the sound characteristics with samples stored in a preset sound sample library. If the matching is successful, the extracted voice audio can be determined to be interference sound, and then the current condition that the preset triggering condition is not met can be determined. On the contrary, if the matching fails, the extracted voice audio can be determined to be the voice sent by the client, and then it can be determined that the preset trigger condition is currently met.

In some embodiments, the detecting whether the human voice audio is an interfering sound may further include, in specific implementation, the following: and processing the human voice audio by using a preset interference sound identification model to determine whether the human voice audio is interference sound.

The preset interference sound identification model may be specifically understood as an algorithm model that can identify whether the audio is an interference sound based on the input audio.

Before specific implementation, a large amount of interference sound audio (for example, voice audio of a worker, broadcast sound audio, meaningless human voice audio and the like) can be collected as positive samples, and a large amount of voice audio of a client can be collected as negative samples; combining the positive sample and the negative sample to obtain a training set; and obtaining a preset interference sound recognition model through model training by utilizing the training set.

In some embodiments, taking a business hall of an organization such as a bank as an example, by combining a specific business service scenario and performing statistical analysis on questionnaire survey results of a large number of customers, business service types that need to be covered by a customer service machine can be divided into three categories, which are: a first type of service type, a second type of service type and a third type of service type.

The first type of service type may be a service type in which a client consults a service question to wait for a response. For the first type of business service type, after a client presents a business problem which the client wants to consult, the client does not always obtain a desired response for some reasons within a longer time period, and the client can be considered to have business service requirements; accordingly, the customer service robot can actively interact with the customer, solve relevant business problems for the customer, or guide the customer to obtain required answers.

The second type of business service type may be a business service type in which a customer uses a kiosk to handle self-service business. For the second type of business service type, when a client uses a self-service machine to handle self-service business, difficulty or problem occurs, and in a longer time period, the difficulty or problem cannot be solved, so that the self-service business cannot be smoothly handled, and the client can be considered to have business service requirements; correspondingly, the customer service robot can actively interact with the customer to assist or prompt the customer to smoothly use the self-service machine to handle self-service business.

The third type of business service type may be a business service type in which a customer actively seeks help from a customer service robot. For the third type of business service, when the customer has a tendency to actively seek help from the customer service robot, but no explicit indication is given directly, the customer service robot may actively interact with the customer in advance before the customer gives the explicit indication, so as to improve the service experience of the customer.

In some embodiments, prior to implementation, a large number of historical service records may be collected; distinguishing different service types according to the historical service records to obtain the historical service records of all the service types; and respectively learning the historical service records of each business service type to construct and obtain a preset processing rule corresponding to each business service type.

The preset processing rule may at least include an acquisition mode of the audio data and/or the image data and a limitation of the processing mode. The influence data may specifically include: image data and/or video data.

In some embodiments, in specific implementation, when it is determined that a preset trigger condition is met, the position information of the target client may be determined by using environmental sounds based on a sound positioning technology; and acquiring first target data related to the target client according to the position information.

In some embodiments, the first target data may specifically include first audio data and/or first image data about the target client. During specific implementation, according to specific situations and processing needs, the first audio data can be independently collected as the first target data, the first image data can be independently collected as the first target data, and the first audio data and the first image data can be simultaneously collected as the first target data.

In some embodiments, the determining a current service type according to the first target data may include the following steps:

s1: processing first audio data in the first target data by using a preset voice recognition model to obtain a corresponding first text;

s2: detecting whether a preset keyword or a relevant word related to the preset keyword exists in the first text;

s3: under the condition that a preset keyword exists in the first text or a relevant word related to the preset keyword is determined, determining that the current business service type is a first class business service type; the first type of business service type is a business service type that a client consults a business question to wait for a response.

Based on the embodiment, whether the current business service type is the first type business service type can be accurately determined through multi-mode fusion according to the first target data.

In some embodiments, the preset speech recognition model may be specifically understood as an algorithm model that is constructed based on a speech recognition technology and is capable of recognizing and converting input audio data into corresponding text data.

The preset keywords may be specifically understood as keywords related to business services.

Before specific implementation, a keyword of a service problem with relatively high consultation frequency of a client can be screened out as the preset keyword by combining a specific service scene. The related words related to the preset keywords may specifically include phrases similar to the semantics of the preset keywords or phrases in close relation. Specifically, after the preset keywords are determined, semantic expansion and semantic relation can be performed on the preset keywords by using technologies such as a natural language model, so as to determine associated words related to the preset keywords. And combining the preset keywords and the associated words to obtain a keyword list. The customer service robot may hold the keyword list.

Correspondingly, in specific implementation, the customer service robot may search the first text according to the keyword list to determine whether a preset keyword or a related word related to the preset keyword exists in the first text.

In some embodiments, the second target data may specifically include second audio data and/or second image data about the target client. During specific implementation, according to specific situations and processing needs, the second audio data may be separately acquired as the second target data, the second image data may be separately acquired as the second target data, and the second audio data and the second image data may be simultaneously acquired as the second target data.

In some embodiments, the obtaining of the second target data about the target client according to the target processing rule may include, in specific implementation, the following: acquiring audio data in a first time period after the first audio data according to a target processing rule, wherein the audio data is used as second audio data in second target data; and/or determining the current position of the target client by using the first audio data according to the target processing rule; and shooting a plurality of images towards the current position of the target client according to a preset time interval to serve as second image data in the second target data.

Based on the embodiment, the second target data with relatively good effect aiming at the first type of business service type can be collected and obtained in a targeted manner, so that whether the target client under the first type of business service type has business service requirements or not can be determined more accurately.

The first time period may be 2 minutes, and the preset time interval may be 20 seconds. Of course, the first time period and the preset time interval listed above are only illustrative.

In some embodiments, the determining whether the target client has a business service requirement by processing the second target data according to the target processing rule may include the following steps:

s1: processing second audio data in the second target data by using a preset voice recognition model to obtain a corresponding second text;

s2: detecting whether a reply text related to a preset keyword or associated word exists in the second text;

s3: and in the case that the answer text is determined not to exist in the second text, determining that the target client has business service requirements.

Based on the embodiment, whether the target client in the first type of business service type really has the business service requirement or not can be accurately and efficiently determined according to the second audio data.

In specific implementation, in the case that it is determined that there is no reply text in the second text, it may be determined that the target client has not obtained a reply within a first long time period after presenting a business question. At this time, in order to avoid affecting the service experience of the target customer, the target customer may be determined as a customer with a business service requirement, and the customer service robot may automatically wake up and actively interact with the target customer.

In contrast, in the case where it is determined that there is a reply text in the second text, it can be determined that there has been a business problem that a worker is replying to the target customer. Accordingly, the target customer can be determined to be a customer without business requirements, and does not need to actively interact with the target customer. Further, the client robot may continue monitoring.

s1: detecting whether a worker exists at the current position of the target client or not according to second image data in the second target data;

s2: and determining that the target client has business service requirements under the condition that no staff exists at the current position of the target client.

Based on the embodiment, whether the target customer in the first type of business service type really has the business service requirement can be accurately and efficiently determined according to the second image data.

In specific implementation, when it is determined that no staff exists at the current position of the target client according to the second image data, it may be determined that no staff is available to serve the target client within a longer first time period after the target client proposes a business problem. At this time, in order to avoid affecting the service experience of the target customer, the target customer may be determined as a customer with a business service requirement, and the customer service robot may automatically wake up and actively interact with the target customer.

In contrast, in the case where it is determined that there is a worker at the current location of the target client based on the second image data, it can be determined that there is a worker serving the target client and answering the business problem posed by the target client. Accordingly, the target customer can be determined to be a customer without business requirements, and does not need to actively interact with the target customer. Further, the client robot may continue to monitor.

In some embodiments, the processing manner for determining whether the target client has a business service requirement based on the second audio data may be combined with the processing manner for determining whether the target client has a business service requirement based on the second image data; by utilizing the two modes to carry out mutual verification, multi-mode fusion is carried out, so that whether a target customer really has business service requirements or not can be determined more accurately.

In some embodiments, the detecting whether there is a staff member at the current location of the target client according to the second image data in the second target data may include the following steps:

s1: performing image recognition on a plurality of images contained in the second image data to obtain a plurality of image recognition results;

s2: detecting whether the figure objects of the uniform with the identification characteristics exist in each image or not according to the identification result of each image;

s3: in a case where it is determined that there is a human object of a uniform that is wearing an identification feature in at least one of the plurality of images, it is determined that there is a worker.

In particular, it is considered that most workers are required to be uniform uniforms. E.g., black business suits, etc. Therefore, representative identification characteristics can be determined according to payment of workers in advance; therefore, whether staff exists in the image can be judged quickly only by detecting whether the person object with the identification characteristic exists in the image.

In some embodiments, in a case where it is determined that the staff member is present at the current location of the target customer, the method may further include, when embodied, the following:

s1: screening out a target image with a worker from the plurality of images;

s2: performing action recognition on the staff in the target image to obtain an action recognition result;

s3: and according to the action recognition result, determining that the target client has no business service requirement under the condition of determining that the action of the staff is the service action.

Specifically, human body key point detection can be performed on the staff in the target image to obtain a corresponding key point detection result; and matching the key point detection result with the key point of the template behavior action to obtain a corresponding action identification result. Therefore, the action recognition result of the worker can be accurately obtained.

In some embodiments, the determining a current service type according to the first target data may further include the following steps in specific implementation:

s1: detecting whether a target client uses a self-service machine to handle self-service business currently or not according to first image data in first target data;

s2: under the condition that the target client is determined to handle the self-service business by using the self-service machine at present, determining that the current business service type is a second type business service type; the second type of business service type is a business service type for a client to use the self-service machine to handle self-service business.

Based on the above embodiment, it can be obtained and accurately determine whether the current service type is the second type service type according to the first target data.

In some embodiments, the obtaining second target data about the target client according to the target processing rule may include, in specific implementation: and according to the target processing rule, recording the video data in a second time period after the first image data towards the position direction of the self-service machine as second image data in second target data.

Based on the embodiment, the second target data with relatively good effect on the second type of business service type can be collected and obtained in a targeted manner, so that whether the target client under the second type of business service type has business service requirements or not can be determined more accurately.

The second time period may be ten minutes. Of course, in specific implementation, other time periods may be set as the second time period according to specific situations and processing requirements.

s1: detecting whether a problem occurs when a target client uses the self-service machine to handle self-service business or not according to second image data in second target data;

s2: and under the condition that the target client is determined to have a problem when the target client uses the self-service machine to handle the self-service business, determining that the target client has business service requirements.

Based on the embodiment, whether the target customer really has the business service requirement under the second type of business service type can be accurately and efficiently determined according to the second image data.

In some embodiments, the detecting, according to the second image data in the second target data, whether a problem occurs when the target client uses the kiosk to handle the self-service business may include: analyzing the face change expression of the target client in the second time period according to the second image data to determine an emotion change result of the target client; and determining whether the target client has a problem when using the self-service machine to handle self-service business or not according to the emotion change result of the target client. When it is determined that a problem occurs in the target client when the target client uses the self-service machine to handle the self-service business, it may be determined that the target client has a business service requirement.

In addition, the detecting whether a problem occurs when the target client uses the self-service machine to handle self-service business according to the second image data in the second target data may further include: detecting whether the staying time of the target customer in the self-service machine exceeds the reference time or not according to the second image data; in the case where it is determined that the reference time period is exceeded, it may be determined that the target customer has a business service demand.

s1: detecting whether a target client has a trend of seeking help from a customer service robot according to the first target data; (e.g., the target customer's line of sight is focused on the robot, or the target customer approaches the service robot)

S2: under the condition that the target client is detected to have a trend of seeking help from the customer service robot, determining the current business service type as a third business service type; the third type of business service is a business service type that the customer actively seeks help from the customer service robot.

Specifically, according to the first target data, through data analysis, it is found that: the target client may determine that the target client has a tendency to seek help from the service robot, and/or the target client may determine that the target client is approaching the service robot.

In some embodiments, the obtaining of the second target data about the target client according to the target processing rule may include, in specific implementation, the following: and acquiring the first image data and/or audio data and/or image data in a third time period after the first image data as second target data according to the target processing rule. The third time period may be specifically five minutes. Of course, in specific implementation, other suitable time periods may be set as the third time period according to specific situations.

s1: confirming whether the target client is seeking help from the customer service robot or not according to the second target data;

s2: and under the condition that the target client is confirmed to seek help from the customer service robot, determining that the target client has business service requirements.

Specifically, for example, according to the second target data, it is detected that the target client further approaches the customer service robot, and the distance between the target client and the customer service robot is smaller than a preset distance threshold; and/or the target client is detected to speak towards the position where the customer service robot is located, and the like, so that the target client can be determined to have the business service requirement.

In some embodiments, the above interacting with the target customer according to the preset interaction rule may include the following steps:

s1: generating a matched interactive text according to a preset interactive rule;

s2: generating corresponding interactive audio according to the interactive text;

s3: and playing the interactive audio to the target client.

Based on the embodiment, when the customer service robot determines that the target customer really has the service requirement, the customer service robot can automatically wake up and generate the matched interactive text, and actively interacts with the target customer by playing the interactive audio based on the interactive text to the target customer, so that the target customer can obtain better service experience.

In specific implementation, for example, referring to fig. 5, the second audio data and the second video data may be subjected to speech recognition and image recognition respectively to obtain corresponding speech recognition results and image recognition results; combining the voice recognition result and the image recognition result to obtain a target recognition result; and processing the target recognition result by utilizing a preset matching model to screen out a matched preset verbal text from the preset verbal text set to serve as an interactive text.

Further, a corresponding interactive image (including an interactive video and/or an interactive image) can be generated according to the interactive text; and then playing the interactive image to the target client.

In some embodiments, when the method is implemented while the interactive audio is played to the target client, the method may further include: and according to a preset interaction rule, flashing an indicator light according to the matched frequency to prompt a target customer.

Based on the embodiment, the target client can notice the customer service robot more easily by flashing the indicator light according to the matched frequency, so that the client service robot can be more effectively helped, and the service experience of the client is further improved.

As can be seen from the above, in the data processing method provided in the embodiments of the present specification, the customer service robot monitors the environmental sounds, and acquires and determines the current business service type according to the first target data related to the target customer when it is determined that the preset trigger condition is currently satisfied; determining a matched target processing rule from preset processing rules according to the current business service type; according to the target processing rule, acquiring and according to second target data related to the target client, and determining whether the target client has a business service requirement; and under the condition that the target user has business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user. Distinguishing different service types according to first target data; and then aiming at different business server types, acquiring and utilizing second target data according to the matched processing rule, and accurately judging whether the target client really has business service requirements at present. Therefore, different business service scenes can be effectively and comprehensively covered, customers with business service requirements can be accurately detected and identified, and the customers can actively interact with the customers on the premise of not waking up the customers, so that related business services are intelligently provided for the customers, and the customers can obtain better service experience.

The embodiment of the present specification further provides a customer service robot, including a processor and a memory for storing processor executable instructions, where the processor, when implemented specifically, may perform the following steps according to the instructions: monitoring environmental sounds to determine whether preset triggering conditions are met currently; under the condition that the preset triggering condition is determined to be met currently, first target data about a target client are obtained; determining the current service type of the business according to the first target data; determining a matched target processing rule from preset processing rules according to the current business service type; acquiring second target data about the target client according to the target processing rule; determining whether the target client has business service requirements or not by processing the second target data according to the target processing rule; and under the condition that the target user is determined to have business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user.

In order to complete the above instructions more accurately, referring to fig. 6, the embodiment of the present specification further provides another specific customer service robot, where the customer service robot may specifically include a network communication port 601, a processor 602, and a memory 603, and the structures are connected by an internal cable, so that the structures may perform specific data interaction.

The network communication port 601 may be specifically configured to receive a start instruction.

The processor 602 may be specifically configured to respond to a start instruction, and monitor an environmental sound to determine whether a preset trigger condition is currently met; under the condition that the preset triggering condition is determined to be met currently, first target data about a target client are obtained; determining the current service type of the business according to the first target data; determining a matched target processing rule from preset processing rules according to the current business service type; acquiring second target data about the target client according to the target processing rule; determining whether the target client has business service requirements or not by processing the second target data according to the target processing rule; and under the condition that the target user has business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user.

The memory 603 may be specifically configured to store a corresponding instruction program.

In this embodiment, the network communication port 601 may be a virtual port bound with different communication protocols, so that different data can be sent or received. For example, the network communication port may be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for mail data communication. In addition, the network communication port can also be a communication interface or a communication chip of an entity. For example, it may be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it may also be a bluetooth chip.

In this embodiment, the processor 602 may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller and embedded microcontroller, and so forth. The description is not intended to be limiting.

In this embodiment, the memory 603 may include multiple layers, and in a digital system, the memory may be any memory as long as binary data can be stored; in an integrated circuit, a circuit without a real form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.

The present specification further provides a computer storage medium based on the above data processing method, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium implements: monitoring environmental sounds to determine whether preset triggering conditions are met currently; under the condition that the preset triggering condition is determined to be met currently, first target data about a target client are obtained; determining the current service type of the business according to the first target data; determining a matched target processing rule from preset processing rules according to the current business service type; acquiring second target data about the target client according to the target processing rule; determining whether the target client has business service requirements or not by processing the second target data according to the target processing rule; and under the condition that the target user is determined to have business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user.

In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.

In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.

Referring to fig. 7, in a software level, an embodiment of the present specification further provides a data processing apparatus, which may specifically include the following structural modules:

the monitoring module 701 may be specifically configured to monitor an environmental sound to determine whether a preset trigger condition is currently met;

a first obtaining module 702, specifically configured to obtain first target data about a target client when it is determined that a preset trigger condition is currently met;

the first determining module 703 may be specifically configured to determine a current service type according to the first target data;

the second determining module 704 may be specifically configured to determine a matching target processing rule from preset processing rules according to the current service type;

the second obtaining module 705 may be specifically configured to obtain second target data about a target client according to a target processing rule;

the third determining module 706 is specifically configured to determine whether the target client has a business service requirement by processing the second target data according to the target processing rule;

the interaction module 707 may be specifically configured to, when it is determined that the target user has a business service requirement, interact with the target user according to a preset interaction rule to provide a matched business service for the target user.

In some embodiments, when the monitoring module 701 is implemented, the environmental sound may be monitored in the following manner to determine whether a preset trigger condition is currently met: collecting current environment sound, and carrying out voice detection on the current environment sound to determine whether voice exists in the current environment sound; under the condition that the current environment sound is determined to have the human voice, extracting human voice audio from the current environment sound; detecting whether the human voice audio is interference sound; and under the condition that the human voice audio is determined not to be the interference sound, determining that the target client exists in the current environment, and determining that the preset trigger condition is met.

In some embodiments, the disturbing sound may include at least one of: broadcast sounds, voice sounds of workers, meaningless human voices, and the like.

In some embodiments, when the first determining module 703 is implemented, the current service type of the service may be determined according to the first target data in the following manner: processing first audio data in the first target data by using a preset voice recognition model to obtain a corresponding first text; detecting whether a preset keyword or a relevant word related to the preset keyword exists in the first text; under the condition that a preset keyword exists in the first text or a relevant word related to the preset keyword is determined, determining that the current business service type is a first class business service type; the first type of business service type is a business service type that a client consults a business question to wait for a response.

In some embodiments, when the second obtaining module 705 is implemented, the second target data about the target client may be obtained according to the target processing rule in the following manner: acquiring audio data in a first time period after the first audio data according to a target processing rule, wherein the audio data is used as second audio data in second target data; and/or determining the current position of the target client by using the first audio data according to the target processing rule; and shooting a plurality of images towards the current position of the target client according to a preset time interval to serve as second image data in the second target data.

In some embodiments, when the third determining module 706 is implemented, it may determine whether the target client has a business service requirement by processing the second target data according to the target processing rule in the following manner: processing second audio data in the second target data by using a preset voice recognition model to obtain a corresponding second text; detecting whether a reply text related to a preset keyword or associated word exists in the second text; and in the case that the answer text is determined not to exist in the second text, determining that the target client has business service requirements.

In some embodiments, when the first determining module 703 is implemented, it may determine whether the target client has a business service requirement by processing the second target data according to the target processing rule in the following manner: detecting whether a worker exists at the current position of the target client according to second image data in the second target data; and determining that the target client has business service requirements under the condition that no staff exists at the current position of the target client.

In some embodiments, when the first determining module 703 is implemented, the current service type may be determined according to the first target data in the following manner: detecting whether a target client uses a self-service machine to handle self-service business currently or not according to first image data in first target data; under the condition that the target client is determined to be currently transacting self-service business by using the self-service machine, determining the current business service type as a second type business service type; the second type of business service type is a business service type for a client to use the self-service machine to handle self-service business.

In some embodiments, when the second obtaining module 705 is implemented, the second target data about the target client may be obtained according to the target processing rule in the following manner: and recording video data in a second time period after the first image data towards the position direction of the self-service machine according to a target processing rule to serve as second image data in second target data.

In some embodiments, when the third determining module 706 is implemented, it may determine whether the target client has a business service requirement by processing the second target data according to the target processing rule in the following manner: detecting whether a problem occurs when the target client uses the self-service machine to handle self-service business or not according to second image data in the second target data; and under the condition that the target client is determined to have problems when the target client uses the self-service machine to handle self-service business, determining that the target client has business service requirements.

In some embodiments, the interaction module 707, when embodied, may interact with the target customer according to the preset interaction rule in the following manner: generating a matched interactive text according to a preset interactive rule; generating corresponding interactive audio according to the interactive text; and playing the interactive audio to the target client.

In some embodiments, the interaction module 707, while playing the interaction audio to the target customer, may be further configured to flash an indicator light according to a preset interaction rule and at a matching frequency to prompt the target customer.

It should be noted that, the units, devices, modules, etc. illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. It is to be understood that, in implementing the present specification, functions of each module may be implemented in one or more pieces of software and/or hardware, or a module that implements the same function may be implemented by a combination of a plurality of sub-modules or sub-units, or the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

As can be seen from the above, based on the data processing apparatus provided in the embodiment of the present specification, different service types are distinguished according to the first target data; and then aiming at different business server types, acquiring and utilizing second target data according to the matched processing rule, and accurately judging whether the target client really has business service requirements at present. Therefore, different business service scenes can be effectively and comprehensively covered, customers with business service requirements can be accurately detected and identified, and the customers can actively interact with the customers on the premise of not waking up the customers, so that related business services are intelligently provided for the customers, and the customers can obtain better service experience.

Although the present specification provides method steps as described in the examples or flowcharts, additional or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an apparatus or client product in practice executes, it may execute sequentially or in parallel (e.g., in a parallel processor or multithreaded processing environment, or even in a distributed data processing environment) according to the embodiments or methods shown in the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. The terms first, second, etc. are used to denote names, but not any particular order.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts in the embodiments are referred to each other, and each embodiment focuses on differences from other embodiments. The description is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

While the specification has been described with examples, those skilled in the art will appreciate that there are numerous variations and permutations of the specification that do not depart from the spirit of the specification, and it is intended that the appended claims include such variations and modifications that do not depart from the spirit of the specification.

Claims

1. A data processing method is applied to a customer service robot and comprises the following steps:

and under the condition that the target user is determined to have business service requirements, interacting with the target user according to a preset interaction rule to provide matched business service for the target user.

2. The method of claim 1, wherein monitoring the ambient sound to determine whether a preset trigger condition is currently met comprises:

acquiring current environment sound, and carrying out voice detection on the current environment sound to determine whether voice exists in the current environment sound;

detecting whether the human voice audio is interference sound;

3. The method of claim 2, wherein the interfering sound comprises at least one of: broadcast sounds, voice sounds of workers, meaningless human voices.

4. The method of claim 1, wherein determining a current traffic service type based on the first target data comprises:

under the condition that a preset keyword exists in the first text or a relevant word related to the preset keyword is determined, determining that the current business service type is a first class business service type; the first type of business service type is a business service type that a client consults a business question to wait for a response.

5. The method of claim 4, wherein obtaining second targeting data about the target customer based on the targeting process rules comprises:

and/or the presence of a gas in the gas,

determining the current position of a target client by using the first audio data according to a target processing rule; and shooting a plurality of images towards the current position of the target client according to a preset time interval to serve as second image data in the second target data.

6. The method of claim 5, wherein determining whether the target client has a business service requirement by processing the second target data according to the target processing rule comprises:

7. The method of claim 5, wherein determining whether the target client has a business service requirement by processing the second target data according to the target processing rule comprises:

8. The method of claim 1, wherein determining a current traffic service type based on the first target data, further comprises:

9. The method of claim 8, wherein obtaining second targeting data for the target customer based on the targeting process rule comprises:

10. The method of claim 9, wherein determining whether the target customer has a business service requirement by processing the second target data according to the target processing rule comprises:

detecting whether a problem occurs when the target client uses the self-service machine to handle self-service business or not according to second image data in the second target data;

11. The method of claim 1, wherein interacting with the target customer according to the preset interaction rule comprises:

generating a matched interactive text according to a preset interactive rule;

generating corresponding interactive audio according to the interactive text;

and playing the interactive audio to the target client.

12. The method of claim 11, wherein while playing the interactive audio to the target client, the method further comprises:

13. A data processing device, applied to a customer service robot, includes:

a second obtaining module, configured to obtain second target data about the target client according to the target processing rule;

14. A service robot comprising a processor and a memory for storing processor-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 12.

15. A computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, carry out the steps of the method of any one of claims 1 to 12.