CN113886540A

CN113886540A - A passenger service system and method for urban rail transit

Info

Publication number: CN113886540A
Application number: CN202111150991.8A
Authority: CN
Inventors: 戚广杰; 方文玉
Original assignee: Grg Intelligent Technology Solution Co ltd; GRG Banking Equipment Co Ltd
Current assignee: Grg Intelligent Technology Solution Co ltd; GRG Banking Equipment Co Ltd
Priority date: 2021-09-29
Filing date: 2021-09-29
Publication date: 2022-01-04

Abstract

The application relates to a passenger service system of urban rail transit, this system includes: the voice processing module is used for receiving voice information of passengers; the FAQ intelligent question-answering module is connected with the voice processing module and used for outputting voice response based on the voice information; the service controller is connected with the voice processing module and used for generating a calling instruction according to the voice response; and the business service module is connected with the business controller and used for calling the sub business service module according to the calling instruction. Through the method and the device, the problems of high cost and high and uneven service quality of manual customer service are solved, the pressure of the staff for the station service customer service is greatly reduced, the service cost of passengers is saved, and the satisfaction degree of the passengers is improved.

Description

Passenger service system and method for urban rail transit

Technical Field

The application relates to the field of urban rail transit operation, in particular to a passenger service system and a passenger service method for urban rail transit.

Background

In traditional urban rail transit, a manual customer service center is usually arranged at each station, and customer service staff provide one-to-one service all the time on duty. The work related to the station service post comprises ticketing, exception handling, electronic invoice making, lost article finding, passenger inquiry and answer and the like, and the station service post is a necessary post for maintaining the normal operation of the subway. The working level of the station service staff represents the public service level of the subway company and the external propaganda image of the city where the station service staff is located, and has very important function

However, the station service customer service generally has the characteristics of high operation repeatability, dull content, poorer working environment and the like. If the staff is on duty for a long time, the staff is easy to generate work fatigue and lacked, and can not continuously keep higher working enthusiasm, thereby influencing the quality of site customer service work. In addition, the mobility of customer service personnel is high, and the training cost is high, so that the manual customer service needs to invest high operation cost.

Disclosure of Invention

The embodiment of the application provides a passenger service system and a passenger service method for urban rail transit, and aims to at least solve the problems of low reliability and high cost of manual railway station service customer service in the related technology.

In a first aspect, an embodiment of the present application provides a passenger service system for urban rail transit, where the system includes:

the voice processing module is used for receiving voice information of passengers;

the FAQ intelligent question-answering module is connected with the voice processing module and used for outputting voice response based on the voice information;

the service controller is connected with the FAQ intelligent question-answering module and used for generating a calling instruction according to the voice response;

and the business service module is connected with the business controller and used for calling the sub business service module according to the calling instruction.

In some of these embodiments, the speech processing module comprises:

the voice acquisition module is used for receiving voice information of passengers and converting the voice information into digital signals;

and the voice recognition module is connected with the voice acquisition module and used for converting the digital signals into text information.

In some of these embodiments, the speech recognition module comprises: a feature extraction module, an acoustic model, a language model and a speech decoding module, wherein,

the feature extraction module is used for converting the voice information from a time domain to a frequency domain to obtain a feature vector;

the acoustic model is used for calculating scores of the feature vectors on the acoustic features according to acoustic characteristics;

the language model is used for predicting and determining a phrase sequence corresponding to the feature vector;

and the voice decoding module is used for decoding the phrase sequence based on a voice dictionary to obtain the text information.

In some embodiments, the speech processing module further comprises a pre-processing module configured to:

and acquiring the voice information for the feature extraction by performing a preprocessing step on the voice information, wherein the preprocessing step comprises one or more combinations of filtering, framing, frame shifting, windowing and noise reduction.

In some embodiments, the speech processing module further includes a speech training module, connected to the preprocessing module, for training an acoustic model and the language model based on the preprocessed simulated speech, where the simulated speech includes: simulated speech of different dialect types, simulated speech of different language types, and simulated speech of different noise backgrounds.

In some embodiments, the FAQ intelligent question-answering module comprises a question corpus, a question matching module, and a response module, wherein;

the question corpus is used for classifying and storing answer sentences corresponding to the common questions of the passengers;

the question matching module comprises a retrieval module and a selection module, wherein the retrieval module is used for acquiring a sentence set similar to the text information from the question corpus, the selection module is used for acquiring a target sentence with the highest similarity from the sentence set and judging whether the confidence coefficient of the target sentence is greater than a preset confidence coefficient threshold value, and if yes, the target sentence is judged to be a synonymous sentence corresponding to the voice information of the passenger;

the response module is used for acquiring the reply sentences corresponding to the synonymous sentences and returning the reply sentences to the passengers.

In some embodiments, the service controller is further connected to a visual menu module, the visual menu module is configured to obtain menu selection information of the passenger, and the service controller is configured to generate a call instruction according to the menu selection information.

In some embodiments, the sub-business service module comprises: the system comprises at least one of a ticketing module, an abnormal card ticket processing module, an electronic invoice module, a line inquiry module, an in-station inquiry module and a lost and found module.

In some embodiments, the ticketing module is configured to provide ticketing functionality to the passenger;

the abnormal card ticket processing module is used for providing a card ticket abnormal processing function for the passenger;

the electronic invoice module is used for generating an electronic invoice according to the passenger's travel order within a preset time limit;

the route query module is used for generating an optimal route according to the passenger target station information and the current station information;

the inquiry module is used for outputting an inquiry result according to the inquiry information of the passenger, wherein the inquiry information comprises menu selection information and voice information;

the lost and found module is used for providing lost article filing and lost article identification functions for the passenger.

In a second aspect, an embodiment of the present application provides a passenger service method for urban rail transit, where the method includes:

receiving voice information of passengers through a voice processing module;

outputting a voice response based on the voice information through an FAQ intelligent question answering module;

generating a call instruction from the voice reply by the service controller,

and calling the sub-business service module according to the calling instruction through the business service module.

Compared with the related art, the passenger service system for urban rail transit provided by the embodiment of the application has the following beneficial effects:

1. the limited human resources are liberated from heavy repeated station service customer service work, so that the consumption of the subway human resources is reduced, and the cost is reduced;

2. based on voice recognition, an intelligent FAQ question and answer technology, an AI technology and an Internet technology, the station service customer service equipment directly provides services for passengers, and service efficiency and user experience in a rail transit environment are improved;

3. through FAQ question answering module, the passenger can obtain necessary information and obtain the service through the form of directly conversing with equipment, and its service efficiency is higher and be applicable to old user.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a schematic application environment diagram of a passenger service method of urban rail transit according to an embodiment of the application;

fig. 2 is a block diagram of a passenger service system for urban rail transit according to an embodiment of the present application;

FIG. 3 is a flow chart of a passenger service method for urban rail transit according to an embodiment of the present application;

fig. 4 is a schematic view of an application scenario of a passenger service method for urban rail transit according to an embodiment of the application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.

It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.

The passenger service method for the urban rail transit, provided by the embodiment of the application, can be applied to an application environment shown in fig. 1, fig. 1 is an application environment schematic diagram of the passenger service method for the urban rail transit according to the embodiment of the application, and as shown in fig. 1, intelligent customer service terminals are deployed at various subway stations of the urban rail transit, and related hardware includes but is not limited to an audio device, a display device, a camera device, a card making device, an arithmetic processing device, a key and the like. The intelligent customer service terminal can replace manual handling of some common problems in subway customer service business, such as: route inquiry, ticket selling, invoice making, lost and found, etc. The passenger can perform man-machine interaction with the intelligent customer service terminal in a conversation mode to obtain services.

Further, the process of the passenger obtaining the service based on the intelligent customer service terminal includes: the personnel speak out interactive voice in the area around the terminal; the terminal collects voice information of passengers through the audio device and outputs reply information corresponding to the voice information through the operation processing device. Furthermore, the reply information is fed back to the passenger through hardware equipment such as an audio device, a display device or a card making device, and the whole process realizes the customer service flow. It should be noted that the user may also perform touch operations such as clicking and sliding on the display screen to realize interaction with the intelligent customer service device, or may also perform interaction with the intelligent customer service device through a button. In addition, the algorithm program for calculating and processing the passenger voice information can be deployed on the terminal device, and can also be arranged in a cloud or a public network machine room.

Fig. 2 is a block diagram of a passenger service system for urban rail transit according to an embodiment of the present application, and as shown in fig. 2, the system includes: the system comprises a voice processing module 10, an FAQ intelligent question answering module 11, a business controller 12 and a business service module 13;

and the voice processing module 10 is used for receiving the voice information of the passenger and converting the format of the voice information to obtain text information. The speech processing module 10 includes hardware devices such as a microphone and an amplifier, and also includes software programs such as a speech recognition algorithm and an encoder.

And the FAQ intelligent question answering module 11 is used for generating a voice response according to the voice information. The FAQ intelligent question-answering module 11 is in communication connection with the voice processing module 10, and can match the text information converted by the voice processing module 10 with the question corpus 110 to obtain an answer to the corresponding question, which is the voice response.

It should be noted that FAQ (Frequently Asked Questions, abbreviated as FAQ) is also colloquially called "Frequently Asked question answer". The FAQ is the main means for providing online help on the current network, and provides consulting services for users by organizing some possible common question-answer pairs in advance and storing the pairs in a database.

The range of questions that the FAQ can solve depends on the number of common question pairs stored in the database, and in the embodiment of the present application, the questions and answers stored in the FAQ intelligent question-answering module 11 are frequently asked and encountered by passengers in a rail transit scene, and actually verified that at least 80% of the general questions can be answered. Further, in order to ensure the effectiveness of the FAQ intelligent question-answering module 11, the question pairs in the FAQ intelligent question-answering module need to be updated in time to adapt to newly-appeared hot-spot questions.

The service controller 12 is connected with the FAQ intelligent question-answering module 11 and used for generating a calling instruction according to the voice response; (ii) a Wherein the call instruction is used for calling the sub-service module 14. Before actual application, registration of each sub-business service module 14 is performed on the business controller 12; in the registration process, for each sub-business service module 14, a corresponding guide key word is assigned in the business controller 12, for example, "buy ticket" is registered as a key word for the ticketing module 140, and "invoice" is registered as a key word for the electronic invoice module 142. When the call instruction is subsequently generated, the call instruction corresponding to the passenger voice information can be generated by comparing the keyword included in the voice information with the existing guide keyword in the service controller 12.

And the business service module 13 is connected with the business controller 12 in a communication way and is used for calling the sub business service module 14 according to the calling instruction. Since the call instruction is generated according to the voice information of the user and the call instruction is determined according to the preset keyword, the business service module 13 can call the sub-business service module 14 to be used by the user according to the call instruction.

It should be noted that after the call instruction is distributed to each sub-business service module 14, that is, the call instruction enters into the sub-business service module 14, the subsequent business process is executed in the sub-business service module 14, and the business controller 12 is not required to participate.

The passenger service system for urban rail transit provided by the embodiment collects voice information through the voice processing module 10 and converts the voice information into text information; and further, automatically outputting a voice response according to the text information through the FAQ intelligent module voice information. Finally, the sub-business service module 14 matched with the requirement of the passenger can be called according to the voice response, and more detailed services can be provided for the user in the sub-business service module 14. Through the system provided by the embodiment of the application, the convenience is brought to passengers, the pressure of station service staff is greatly reduced, the service cost of the passengers is saved, and the satisfaction degree of the passengers is improved.

In some embodiments, the speech processing module 10 in this embodiment includes: a voice acquisition module 100 and a voice recognition module 102, wherein;

the voice collecting module 100 is used for receiving voice information of passengers and converting the voice information into digital signals. The voice collecting module 100 is composed of a microphone, an encoder, an amplifier, and the like. Since the signal for machine processing needs to be a digital signal, after the microphone collects the voice information of the passenger, the conversion of the sound signal from an analog signal to a digital signal needs to be completed through the encoder. Optionally, a communication network is further used to upload the digital signal to the speech recognition module 102.

It should be noted that the speech recognition module 102 is a speech recognition application running on the server side, and the speech acquisition module 100 is a software and hardware module running on the device side. The speech recognition module 102 is communicatively connected to the speech acquisition module 100, and is configured to convert speech information in the form of digital signals into text information.

In some of these embodiments, the speech recognition module 102 includes: feature extraction module 1021, acoustic model 1020, language model 1023, and speech decoding module 1022, wherein:

the feature extraction module 1021 is configured to convert the digital speech information from a time domain to a frequency domain, and obtain a feature vector applicable to the acoustic model 1020;

the acoustic model 1020 is used for calculating scores of feature vectors on survival features according to the acoustic features, and it should be noted that the acoustic model 1020 has no fixed prediction effect on different scenes because background environments of customer service sites are different and noise interference is also different; therefore, the purpose of calculating the feature vector score is to determine the prediction effect of the model, and further to select the acoustic model 1020 with the best effect and most suitable for the subway service station based on the prediction effect.

The language model 1023 is used to predict and determine the phrase sequence corresponding to the feature vector. The language model 1023 includes all common phrase sequences, and the language model 1023 sequentially judges the probability that each feature vector corresponds to each phrase sequence according to linguistic related knowledge (such as a leading-predicate structure) and selects the phrase sequence with the maximum probability as the phrase sequence corresponding to the feature vector finally.

The speech decoding module 1022 is configured to decode the phrase sequence based on the existing speech dictionary to obtain the final text information corresponding to the passenger speech information.

In some embodiments, in consideration of interference of environmental noise such as people flow and traffic flow in a subway station, processing steps such as filtering and framing need to be performed on collected voice information to obtain pure effective voice data without noise interference. Therefore, the speech processing module 10 further comprises a pre-processing module 101, wherein the pre-processing module 101 is configured to perform one or more steps of filtering, framing, frame shifting, windowing and noise reduction on the collected speech information, thereby obtaining sound data for speech recognition.

In some embodiments, in order to further improve the recognition accuracy of the speech recognition module 102, the speech processing module 10 in the system further includes a speech training module 103, where the speech training module 103 is connected to the preprocessing module 101, and is configured to train the acoustic model 1020 and the language model 1023 based on a large number of preprocessed simulated speeches (for example, considering that various pedestrian flow and traffic flow environmental noises exist in a subway scene, the background noise interference is continuously filtered and tuned by the training module), so as to further improve the recognition accuracy of the speech recognition module 102, and obtain the best use effect after the actual subway station is released. Optionally, because subway passengers have complex personnel components and different pronunciation levels of Mandarin, simulated voices of different dialect types can be collected for model training. Similarly, in order to adapt to more scenes and obtain better model recognition effect, simulated voices with different language types and different noise backgrounds can be selected to participate in model training.

In some embodiments, the FAQ intelligent question-answering module 11 includes a question corpus 110, a question matching module 111, and a response module 112, wherein;

in the question corpus 110, reply sentences corresponding to the common questions of the passengers are stored according to different types;

the question matching module 111 comprises a retrieval module 1110 and a selection module 1111, wherein the retrieval module 1110 is used for selecting a part of sentences most similar to the text information of the query from the question corpus 110 to form a sentence set, and the limited sentences in the sentence set are called candidate similar sentences. Further, the selecting module 1111 is configured to query a sentence with the highest similarity as a target sentence from the candidate similar sentences, and further determine whether a confidence of the target sentence is greater than a preset confidence threshold, if so, the selecting module 1111 determines that the target sentence is the synonymous sentence corresponding to the voice information of the passenger.

Further, the response module 112 is configured to query the database for a reply sentence corresponding to the synonymous sentence as reply information, and present the reply sentence to the passenger in the form of audio, video, or hardware action.

In some embodiments, the service controller 12 is further connected to a visual menu module 15, and the passenger may also input text type menu selection information through the visual menu module 15, instruct the service controller 12 to generate a call instruction according to a keyword in the menu selection information, and instruct the service module 13 to call the sub-service module 14 according to the call instruction.

Through the embodiment, the system can call the sub-service module based on the voice information of the user and also based on the character interaction signal of the user on the menu of the display screen, so that the system can be suitable for passengers with different use habits and can meet the requirements of different passengers.

In some of these embodiments, the sub-business service module 14 includes: at least one of the ticketing module 140, the abnormal-card ticket processing module 141, the electronic invoice module 142, the line inquiry module 145, the inquiry module 143, and the lost-and-found module 144;

the ticketing module 140 is configured to provide a ticket purchasing function for the passenger, and the ticketing module 140 can complete an online third party payment electronic ticket purchasing function, specifically including subdivided functions of ticket price calculation, order generation, electronic ticket reimbursement, refund and the like.

The abnormal card ticket processing module 141 is configured to provide a card ticket abnormal processing function for the passenger, and the abnormal card ticket processing module 141 can process abnormal situations such as insufficient card ticket balance, card ticket unable to be swiped, card ticket arrival timeout, and the like.

The electronic invoice issuing module 142 is used for generating an electronic invoice according to a travel order of a passenger within a preset time limit;

the route query module 145 is used for generating an optimal route according to the passenger's target station information and the current station information;

the query module 143 is configured to output a query result according to the question and answer information of the passenger, where the question and answer information may be a text interaction form and a voice message, and the query module 143 is capable of completing the response of the passenger to the questions such as "find exit", "find toilet", and the like;

the lost and found module 144 is configured to provide a function of recording lost articles and finding lost articles for passengers, and further, the lost and found module 144 may be further configured to implement a function of information disclosure, for example, to perform information disclosure on poor riding behaviors at each station, so as to perform warning and guiding functions.

The embodiment also provides a passenger service method for urban rail transit, and fig. 3 is a flowchart of the passenger service method for urban rail transit according to the embodiment of the present application, and as shown in fig. 3, the flowchart includes the following steps:

s301, receiving voice information of passengers through a voice processing module; the voice processing module can convert the format of the voice information to obtain text information, and the text information comprises hardware equipment such as a microphone and an amplifier, and also comprises software programs such as a voice recognition algorithm and an encoder;

s302, outputting a voice response based on the voice information through an FAQ intelligent question answering module; the FAQ intelligent question-answering module is in communication connection with the voice processing module and can match text information obtained through conversion by the voice processing module with a question corpus so as to obtain answers of corresponding questions, wherein the answers are the voice responses;

the range of questions that the FAQ can solve depends on the common question pairs stored in the database, in the embodiment of the application, the questions and answers stored in the FAQ intelligent question-answering module are frequently asked and encountered by passengers in a rail transit scene, and at least 80% of common questions can be answered through actual verification. Furthermore, in order to ensure the effectiveness of the FAQ intelligent question-answering module, the problem pairs in the FAQ intelligent question-answering module need to be updated in time to adapt to newly-appeared hot-spot problems.

And S303, generating a calling instruction according to the voice reply through the service controller, wherein the calling instruction is used for calling the sub-service module. Before actual application, the registration of each sub-business service module is carried out on the business controller; further, in the registration process, for each sub-business service module, a corresponding guiding keyword is assigned in the business controller, for example, "buy ticket" is registered as a keyword for the ticketing module, and "invoice" is registered as a keyword for the electronic invoice module. When the call instruction is generated subsequently, the call instruction corresponding to the voice information can be generated by comparing the keywords contained in the voice information with the existing keywords in the service controller.

S304, calling the sub-business service module through the business service module according to the calling instruction. It should be noted that, since the call instruction is generated according to the voice information of the user, and the call instruction is determined according to the preset keyword, the service module can call the sub-service module to be used by the user according to the call instruction.

Through the steps S301 to S304, compared with manual customer service, the passenger service method for urban rail transit provided by the embodiment can liberate limited human resources from heavy repeated station service customer service work, and reduce the consumption of subway human resources. In addition, the passenger can obtain necessary information and obtain service in a form of directly talking with the device, and the service efficiency is higher.

Fig. 4 is a schematic view of an application scenario of the passenger service method for urban rail transit according to the embodiment of the present application, and as shown in fig. 4, the customer service method for urban rail transit according to the embodiment of the present application is exemplified by combining a specific offline service scenario:

firstly, a passenger converses with a field device and inputs voice information;

and secondly, the device receives voice information of the passenger through a microphone and forwards the voice information to a voice recognition algorithm, the voice recognition algorithm predicts the voice information and obtains a target character corresponding to the voice information, and before the voice recognition algorithm predicts, a large number of different types of simulated voices are adopted to train the algorithm so as to improve the prediction effect of the algorithm.

Thirdly, the FAQ intelligent question answering program understands the semantics of the target characters and extracts the keywords in the target characters. Further, the keywords are put into a corpus for matching to obtain a target instruction.

And fourthly, the business controller generates a calling instruction according to the target instruction, and the business service module calls each sub business service module to provide services for the user according to the calling instruction.

Fifthly, the passenger enters each sub-business service module to obtain services, such as:

opening an invoice in an invoice module;

in the line query module, the line query module speaks 'help me query how to go to Guangzhou tower' to the device, converts the words into texts through the voice recognition module, further obtains response instructions corresponding to the texts through the FAQ intelligent question-answering module, and feeds the response instructions back to passengers in a voice broadcasting or screen display mode.

In the ticketing module, the device first broadcasts a prompt to speak "where is your destination site? "→ passenger voice reply" new zuojiang "→ device continue to announce the prompt voice" do you buy tickets in quantity? "→ passenger voice reply" two sheets "→ device continue announcing prompt voice" do your payment method? "→ passenger voice reply" code scan pay "→ device tickets out after code scan is successful.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A passenger service system for urban rail transit, the system comprising:

2. The system of claim 1, wherein the speech processing module comprises:

3. The system of claim 2, wherein the speech recognition module comprises: a feature extraction module, an acoustic model, a language model and a speech decoding module, wherein,

4. The system of claim 1, wherein the speech processing module further comprises a pre-processing module configured to:

5. The system of claim 4, wherein the speech processing module further comprises a speech training module, connected to the preprocessing module, for training an acoustic model and a language model based on the preprocessed simulated speech, wherein the simulated speech comprises: simulated speech of different dialect types, simulated speech of different language types, and simulated speech of different noise backgrounds.

6. The system according to claim 2, wherein the FAQ smart question-answering module comprises a question corpus, a question matching module, and a response module, wherein;

7. The system of claim 1, wherein the service controller is further connected to a visual menu module, the visual menu module is configured to obtain menu selection information of the passenger, and the service controller is configured to generate a call instruction according to the menu selection information.

8. The system of claim 1, wherein the sub-business service module comprises: the system comprises at least one of a ticketing module, an abnormal card ticket processing module, an electronic invoice module, a line inquiry module, an in-station inquiry module and a lost and found module.

9. The system of claim 8, wherein:

the ticketing module is used for providing a ticket purchasing function for the passenger;

10. A passenger service method for urban rail transit, the method comprising:

receiving voice information of passengers through a voice processing module;

generating a call instruction from the voice reply by the service controller,