Automatic ticketing interaction method and system and storage medium

Abstract

The invention provides an automatic ticketing interaction method and system and a storage medium. The method comprises the following steps: performing face recognition detection on an image acquired by a user; if the face recognition detection is qualified, controlling the ticket vending machine to carry out voice acquisition on the user to obtain ticket selling interaction voice, and carrying out semantic recognition on the ticket selling interaction voice to obtain user semantics; if the semantic type of the user semantics is a question and answer type, feedback information is determined according to the user semantics, and the ticket vending machine is controlled to execute question and answer feedback according to the feedback information; if the semantic type of the user semantics is a ticketing type, determining a ticketing jump interface according to the user semantics, and controlling the ticket vending machine to display ticketing according to the ticketing jump interface; and if a ticket card purchase instruction for the ticket selling jump interface is received, controlling the ticket vending machine to execute ticket selling operation according to the ticket card purchase instruction. According to the embodiment of the invention, automatic ticketing can be carried out in a voice interaction mode, and the diversity of automatic ticketing modes is met.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an automatic ticket vending interaction method, system and storage medium. Background Art

[0002] In order to relieve the ticketing pressure of manual ticket windows, solve the problems of crowding and queuing, and improve ticketing efficiency, a large number of public service places such as cinemas, subway stations, railway stations, and long-distance bus stations are equipped with a large number of automatic ticket machines for people to buy tickets by themselves. Automatic ticket machines can be used immediately after purchase, and there will be no problem of needing to refund tickets due to temporary changes in itineraries.

[0003] When using existing automatic ticket vending machines, ticket selling services are generally performed by touch screen operation, resulting in a single ticket selling method. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide an automatic ticket selling interactive method, system and storage medium to solve the problem of single ticket selling method in the prior art.

[0005] The embodiment of the present invention is implemented as follows: an automatic ticket vending interactive method, the method comprising:

[0006] Acquire user-collected images, and perform face recognition detection on the user-collected images;

[0007] If the face recognition detection is qualified, the automatic ticket vending machine is controlled to collect the user's voice to obtain the ticket selling interactive voice, and the ticket selling interactive voice is semantically recognized to obtain the user's semantics;

[0008] If the semantic type of the user semantics is a question-and-answer type, feedback information is determined according to the user semantics, and the automatic ticket vending machine is controlled to perform question-and-answer feedback according to the feedback information;

[0009] If the semantic type of the user semantics is a ticketing type, determining a ticketing jump interface according to the user semantics, and controlling the automatic ticket vending machine to display tickets according to the ticketing jump interface;

[0010] If a ticket purchase instruction for the ticket sales jump interface is received, the automatic ticket vending machine is controlled to perform a ticket sales operation according to the ticket purchase instruction.

[0011] Preferably, semantic recognition is performed on the ticket selling interactive voice to obtain user semantics, including:

[0012] If the number of face images in the detection result of the face recognition detection is less than the number threshold, directly performing semantic recognition on the ticketing interactive voice to obtain the user semantics;

[0013] If the number of images is greater than or equal to the number threshold, performing user analysis on the face images, and determining a target user according to the user analysis results;

[0014] In the ticket selling interactive voice, the voice corresponding to the target user is determined as the target interactive voice, and semantic recognition is performed on the target interactive voice to obtain the user semantics.

[0015] Preferably, performing user analysis on the facial image and determining the target user according to the user analysis result includes:

[0016] Acquire the image area of ​​the face image, and delete the face image whose image area is smaller than an area threshold;

[0017] If the number of the facial images after the image deletion is greater than or equal to the number threshold, acquiring facial features of the facial images, and determining the user's age based on the facial features;

[0018] Acquire the user distance between the user corresponding to the face image and the automatic ticket vending machine, and numerically map the user distance and the user age to obtain a mapped distance and a mapped age;

[0019] Performing a weighted operation on the mapping distance and the mapping age to obtain a user weighted value, and determining the face image corresponding to the maximum user weighted value as a target face;

[0020] The user corresponding to the target face is determined as the target user.

[0021] Preferably, in the ticket selling interactive voice, determining the voice corresponding to the target user as the target interactive voice includes:

[0022] Performing zero-crossing detection on the ticket-selling interactive voice, and performing voice segmentation on the ticket-selling interactive voice according to the zero-crossing detection result to obtain segmented voice;

[0023] Extracting speech features of the segmented speech, and classifying the segmented speech according to the speech features to obtain a speech classification set;

[0024] Determining a speech standard feature according to the user information of the target user, and calculating a feature similarity between the speech feature and the speech standard feature;

[0025] The speech feature corresponding to the maximum feature similarity is determined as the target feature, and the speech in the speech classification set corresponding to the target feature is determined as the target interactive speech.

[0026] Preferably, after semantic recognition is performed on the ticket selling interactive voice to obtain the user semantics, the method further includes:

[0027] Acquire a ticketing vocabulary set, and perform vocabulary matching between preset words in the ticketing vocabulary set and the user semantics;

[0028] If the preset vocabulary matches the vocabulary of the user semantics successfully, determining the semantic type of the user semantics as the ticketing type;

[0029] If the preset vocabulary fails to match the vocabulary of the user semantics, the semantic type of the user semantics is determined to be the question and answer type.

[0030] Preferably, after controlling the automatic ticket vending machine to display tickets according to the ticket jump interface, the method further comprises:

[0031] Obtaining a display identifier of the ticket sales jump interface, and determining ticket sales prompt information according to the display identifier;

[0032] Obtaining the plug-in position of the interactive plug-in on the automatic ticket vending machine, and matching the ticket sales prompt information with the plug-in position;

[0033] The interactive plug-in is pointed to and prompted according to the prompt matching result.

[0034] Preferably, determining the feedback information according to the user semantics includes:

[0035] Performing vector conversion on the user semantics to obtain a semantic vector, and performing similarity calculation between the semantic vector and the question-answer vector in the question-answer database to obtain vector similarity;

[0036] The question-and-answer vector corresponding to the maximum vector similarity is determined as a target vector, and the question-and-answer information corresponding to the target vector is determined as the feedback information.

[0037] Another object of an embodiment of the present invention is to provide an automatic ticket vending interactive system, the system comprising:

[0038] A face recognition module is used to obtain user-collected images and perform face recognition detection on the user-collected images;

[0039] A semantic recognition module is used to control the automatic ticket vending machine to collect the user's voice if the face recognition detection is qualified, obtain the ticket selling interactive voice, and perform semantic recognition on the ticket selling interactive voice to obtain the user's semantics;

[0040] A question feedback module, for determining feedback information according to the user semantics if the semantic type of the user semantics is a question-and-answer type, and controlling the automatic ticket vending machine to perform question-and-answer feedback according to the feedback information;

[0041] A ticket display module, for determining a ticket jump interface according to the user semantics if the semantic type of the user semantics is a ticket type, and controlling the automatic ticket vending machine to display tickets according to the ticket jump interface;

[0042] The ticket execution module is used to control the automatic ticket vending machine to execute the ticket selling operation according to the ticket purchase instruction if a ticket purchase instruction for the ticket jump interface is received.

[0043] Preferably, the semantic recognition module is also used for:

[0044] If the number of face images in the detection result of the face recognition detection is less than the number threshold, directly performing semantic recognition on the ticketing interactive voice to obtain the user semantics;

[0045] If the number of images is greater than or equal to the number threshold, performing user analysis on the face images, and determining a target user according to the user analysis results;

[0046] In the ticket selling interactive voice, the voice corresponding to the target user is determined as the target interactive voice, and semantic recognition is performed on the target interactive voice to obtain the user semantics.

[0047] The embodiments of the present invention can automatically detect whether there is a user who needs to buy a ticket in front of the automatic ticket vending machine by performing face recognition detection on the user's captured image, and can effectively identify the user's semantics by performing semantic recognition on the ticket selling interactive voice. When it is detected that the user's semantics is of the question and answer type, the automatic ticket vending machine can be automatically controlled to perform voice question and answer feedback based on the feedback information. If the user's semantics is detected to be of the ticket selling type, the ticket selling jump interface can be effectively determined based on the user's semantics, and the ticket selling jump interface can be controlled to display the ticket selling, which effectively facilitates the user's choice of ticket purchase. The automatic ticket vending machine is controlled to perform the ticket selling operation through the ticket card purchase instruction to achieve the effect of automatic ticket selling. The embodiments of the present invention can use voice interaction to perform automatic ticket selling, which meets the diversity of automatic ticket selling methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a flow chart of the automatic ticketing interactive method provided by the first embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of the structure of an automatic ticket vending interactive system provided by a second embodiment of the present invention;

[0050] Figure 3 is a module wiring diagram of the automatic ticket vending interactive system provided by the second embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of an automatic ticket vending machine provided by a second embodiment of the present invention;

[0052] Figure 5 It is a schematic diagram of the structure of a terminal device provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] In order to illustrate the technical solution of the present invention, a specific embodiment is provided below for illustration.

[0055] Embodiment 1

[0056] See also Figure 1 , is a flow chart of an automatic ticketing interactive method provided by a first embodiment of the present invention. The automatic ticketing interactive method can be applied to any device or system. The automatic ticketing interactive method comprises the steps of:

[0057] Step S10, obtaining a user-collected image, and performing face recognition detection on the user-collected image;

[0058] Among them, the ticket vending machine is equipped with an image acquisition device, which captures the image in front of the ticket vending machine in real time to obtain a user-captured image. By performing face recognition detection on the user-captured image, it is possible to detect in real time whether there is a user who needs automatic ticket vending service in front of the ticket vending machine.

[0059] Step S20: If the face recognition detection is qualified, the automatic ticket vending machine is controlled to collect the user's voice to obtain the ticket selling interactive voice, and semantic recognition is performed on the ticket selling interactive voice to obtain the user's semantics;

[0060] Among them, when a face image is detected in the image collected by the user, the face recognition detection is judged to be qualified, and the voice collection device on the automatic ticket vending machine is controlled to collect voice to obtain the ticket selling interaction voice. By performing semantic recognition on the ticket selling interaction voice, the user's semantic needs can be effectively identified, and the semantic needs include question and answer needs and ticket selling needs.

[0061] Optionally, semantic recognition is performed on the ticket selling interactive voice to obtain user semantics, including:

[0062] If the number of face images in the detection result of the face recognition detection is less than the number threshold, semantic recognition is directly performed on the ticketing interactive voice to obtain the user semantics; wherein the number threshold can be set according to demand, for example, when the number of face images detected is less than 2, semantic recognition is directly performed on the ticketing interactive voice to obtain the user semantics;

[0063] If the number of images is greater than or equal to the number threshold, user analysis is performed on the face images, and a target user is determined according to the user analysis result; wherein, when the number of images is greater than or equal to the number threshold, it is necessary to determine the target user among the detected users. In this step, the target user can be automatically determined by performing user analysis on the face images;

[0064] In the ticket selling interactive voice, the voice corresponding to the target user is determined as the target interactive voice, and semantic recognition is performed on the target interactive voice to obtain the user semantics; wherein, by determining the voice corresponding to the target user in the ticket selling interactive voice as the target interactive voice, the accuracy of semantic recognition is effectively improved.

[0065] Further, performing user analysis on the face image and determining the target user according to the user analysis result includes:

[0066] Acquire the image area of ​​the face image, and delete the face image whose image area is smaller than an area threshold; wherein the area threshold can be set according to demand, and when the image area is smaller than the area threshold, it is determined that the user corresponding to the face image is not standing within the ticket vending range of the automatic ticket vending machine;

[0067] If the number of images of the face image after the image is deleted is greater than or equal to the number threshold, the face features of the face image are obtained, and the user age is determined based on the face features; wherein the number threshold can be set according to demand, the face features include face key points and / or texture features, the face features are similarity calculated with the preset features to obtain the face similarity, and the age value of the preset feature corresponding to the maximum face similarity is determined as the user age;

[0068] The user distance between the user corresponding to the face image and the automatic ticket vending machine is obtained, and the user distance and the user age are numerically mapped to obtain a mapping distance and a mapping age; wherein the automatic ticket vending machine is provided with a distance sensor, and the distance sensor is used to detect the user distance between the user and the automatic ticket vending machine. In this step, the user distance and the user age are respectively normalized according to a preset mapping relationship to obtain a mapping distance and a mapping age;

[0069] A weighted operation is performed on the mapping distance and the mapping age to obtain a user weighted value, the facial image corresponding to the maximum user weighted value is determined as the target face, and the user corresponding to the target face is determined as the target user; wherein the weighted coefficients of the mapping distance and the mapping age in the weighted operation process can be set according to needs.

[0070] Furthermore, in the ticket selling interactive voice, determining the voice corresponding to the target user as the target interactive voice includes:

[0071] Performing zero-crossing detection on the ticketing interactive voice, and performing voice segmentation on the ticketing interactive voice according to the zero-crossing detection result to obtain segmented voice; wherein the zero-crossing detection is used to determine the interval between voice segments in the ticketing interactive voice, and based on the zero-crossing detection, the silent segment in the ticketing interactive voice can be effectively removed, and the voice after removing the silent segment is segmented to obtain segmented voice;

[0072] Extracting speech features of the segmented speech, and classifying the segmented speech according to the speech features to obtain a speech classification set; wherein the speech features include fundamental frequency, formant, sound intensity, intonation and other features, and the segmented speech corresponding to the same speech feature is classified into the same speech classification set, and one speech classification set corresponds to one speaking user;

[0073] Determine the standard voice feature according to the user information of the target user, and calculate the feature similarity between the voice feature and the standard voice feature; wherein the age and gender in the user information are matched with the feature query table to obtain the standard voice feature;

[0074] The speech feature corresponding to the maximum feature similarity is determined as the target feature, and the speech in the speech classification set corresponding to the target feature is determined as the target interactive speech.

[0075] Preferably, after semantic recognition is performed on the ticket selling interactive voice to obtain the user semantics, the method further includes:

[0076] Obtain a ticketing vocabulary set, and perform vocabulary matching between preset vocabulary in the ticketing vocabulary set and the user semantics; wherein the preset vocabulary can be set according to demand, for example, the preset vocabulary can be set to vocabulary such as "ticket purchase", "platform", and "concert";

[0077] If the preset vocabulary matches the vocabulary of the user semantics successfully, the semantic type of the user semantics is determined to be the ticket sales type; if the preset vocabulary matches the vocabulary of the user semantics unsuccessfully, the semantic type of the user semantics is determined to be the question and answer type.

[0078] Step S30, if the semantic type of the user semantics is a question-and-answer type, determining feedback information according to the user semantics, and controlling the automatic ticket vending machine to perform question-and-answer feedback according to the feedback information;

[0079] Among them, controlling the automatic ticket vending machine to execute question and answer feedback through feedback information can effectively provide users with automatic question and answer effects, making it convenient for users to inquire about ticket-related issues.

[0080] Optionally, determining feedback information according to the user semantics includes:

[0081] Performing vector conversion on the user semantics to obtain a semantic vector, and performing similarity calculation between the semantic vector and the question-answer vector in the question-answer database to obtain vector similarity; wherein the distance between the semantic vector and the question-answer vector can be calculated using the Euclidean distance formula to obtain the vector similarity;

[0082] The question-and-answer vector corresponding to the maximum vector similarity is determined as the target vector, and the question-and-answer information corresponding to the target vector is determined as the feedback information; wherein the question-and-answer database stores the correspondence between different question-and-answer vectors and corresponding question-and-answer information.

[0083] Step S40, if the semantic type of the user semantics is a ticketing type, determining a ticketing jump interface according to the user semantics, and controlling the automatic ticket vending machine to display tickets according to the ticketing jump interface;

[0084] Among them, the similarity between user semantics and preset semantics is calculated to obtain semantic similarity, the preset semantics corresponding to the maximum semantic similarity is determined as the target semantics, and the interface corresponding to the target semantics is determined as the ticket jump interface. The ticket jump interface is displayed by controlling the automatic ticket vending machine, which effectively facilitates the user's choice of ticket purchase.

[0085] Optionally, after controlling the automatic ticket vending machine to display tickets according to the ticket jump interface, the method further includes:

[0086] Obtaining the display identifier of the ticket jump interface, and determining the ticket prompt information according to the display identifier; wherein the display identifier is matched with an information query table to obtain the ticket prompt information, and the information query table stores the correspondence between different display identifiers and corresponding ticket prompt information;

[0087] Obtain the plug-in position of the interactive plug-in on the automatic ticket vending machine, and match the ticket prompt information with the plug-in position; wherein the interactive plug-in includes plug-ins such as an ID card recognition device, a digital input device, a bank card recognition device, a QR code scanning device, and a ticket output slot, and by matching the ticket prompt information with the plug-in position, detect whether the plug-in position needs to be prompted to the user;

[0088] The interactive plug-in is pointed and prompted according to the prompt matching result; wherein, the position of the interactive plug-in to be used can be pointed and prompted in the form of prompt arrows and text prompts, which facilitates the user to use the interactive plug-in.

[0089] Step S50, if a ticket purchase instruction for the ticket sales jump interface is received, the automatic ticket vending machine is controlled to perform a ticket sales operation according to the ticket purchase instruction;

[0090] Among them, the ticket purchase instruction is used to control the automatic ticket vending machine to perform the ticket selling operation to achieve the effect of automatic ticket selling.

[0091] In this embodiment, voice interaction can be used for automatic ticket sales, which meets the diversity of automatic ticket sales methods. By performing face recognition detection on user-captured images, it can automatically detect whether there is a user who needs to buy a ticket in front of the automatic ticket machine. By performing semantic recognition on the ticket sales interactive voice, the user's semantics can be effectively identified. When it is detected that the user's semantics is a question and answer type, the automatic ticket machine can be automatically controlled to perform voice question and answer feedback based on the feedback information. If the user's semantics is detected to be a ticket sales type, the ticket sales jump interface can be effectively determined based on the user's semantics. By controlling the automatic ticket machine to display the ticket sales on the ticket sales jump interface, the user's choice of ticket purchase is effectively facilitated. The ticket vending machine is controlled to perform the ticket sales operation through the ticket card purchase instruction to achieve the effect of automatic ticket sales.

[0092] Embodiment 2

[0093] See also Figure 2 , is a schematic diagram of the structure of an automatic ticket vending interactive system 100 provided in a second embodiment of the present invention, comprising:

[0094] The face recognition module 10 is used to obtain the user-captured image and perform face recognition detection on the user-captured image.

[0095] The semantic recognition module 11 is used to control the automatic ticket vending machine to collect the user's voice if the face recognition detection is qualified, obtain the ticket selling interactive voice, and perform semantic recognition on the ticket selling interactive voice to obtain the user semantics.

[0096] Optionally, the semantic recognition module 11 is further used to: if the number of face images in the detection result of the face recognition detection is less than the number threshold, directly perform semantic recognition on the ticketing interactive voice to obtain the user semantics;

[0097] If the number of images is greater than or equal to the number threshold, performing user analysis on the face images, and determining a target user according to the user analysis results;

[0098] In the ticket selling interactive voice, the voice corresponding to the target user is determined as the target interactive voice, and semantic recognition is performed on the target interactive voice to obtain the user semantics.

[0099] Furthermore, the semantic recognition module 11 is also used to: obtain the image area of ​​the face image, and delete the face image whose image area is smaller than the area threshold;

[0100] If the number of the facial images after the image deletion is greater than or equal to the number threshold, acquiring facial features of the facial images, and determining the user's age based on the facial features;

[0101] Acquire the user distance between the user corresponding to the face image and the automatic ticket vending machine, and numerically map the user distance and the user age to obtain a mapped distance and a mapped age;

[0102] Performing a weighted operation on the mapping distance and the mapping age to obtain a user weighted value, and determining the face image corresponding to the maximum user weighted value as a target face;

[0103] The user corresponding to the target face is determined as the target user.

[0104] Furthermore, the semantic recognition module 11 is also used to: perform zero-crossing detection on the ticketing interactive speech, and perform speech segmentation on the ticketing interactive speech according to the zero-crossing detection result to obtain segmented speech;

[0105] Extracting speech features of the segmented speech, and classifying the segmented speech according to the speech features to obtain a speech classification set;

[0106] Determining a speech standard feature according to the user information of the target user, and calculating a feature similarity between the speech feature and the speech standard feature;

[0107] The speech feature corresponding to the maximum feature similarity is determined as the target feature, and the speech in the speech classification set corresponding to the target feature is determined as the target interactive speech.

[0108] Preferably, the semantic recognition module 11 is further used to: obtain a ticketing vocabulary set, and perform vocabulary matching between preset words in the ticketing vocabulary set and the user semantics;

[0109] If the preset vocabulary matches the vocabulary of the user semantics successfully, determining the semantic type of the user semantics as the ticketing type;

[0110] If the preset vocabulary fails to match the vocabulary of the user semantics, the semantic type of the user semantics is determined to be the question and answer type.

[0111] The question feedback module 12 is used to determine feedback information according to the user semantics if the semantic type of the user semantics is a question-and-answer type, and control the automatic ticket vending machine to perform question-and-answer feedback according to the feedback information.

[0112] Optionally, the question-answer feedback module 12 is further used to: perform vector conversion on the user semantics to obtain a semantic vector, and perform similarity calculation between the semantic vector and the question-answer vector in the question-answer database to obtain vector similarity;

[0113] The question-and-answer vector corresponding to the maximum vector similarity is determined as a target vector, and the question-and-answer information corresponding to the target vector is determined as the feedback information.

[0114] The ticket display module 13 is used to determine the ticket jump interface according to the user semantics if the semantic type of the user semantics is the ticket type, and control the automatic ticket vending machine to display the ticket according to the ticket jump interface.

[0115] Optionally, the ticket display module 13 is further used to: obtain a display identifier of the ticket jump interface, and determine the ticket prompt information according to the display identifier;

[0116] Obtaining the plug-in position of the interactive plug-in on the automatic ticket vending machine, and matching the ticket sales prompt information with the plug-in position;

[0117] The interactive plug-in is pointed to and prompted according to the prompt matching result.

[0118] The ticket execution module 14 is used to control the automatic ticket vending machine to execute the ticket selling operation according to the ticket purchase instruction if a ticket purchase instruction for the ticket jump interface is received.

[0119] See also Figure 3In this embodiment, the automatic ticket vending machine is provided with a voice recognition unit, which is connected to a camera, a microphone core board, a microphone array, an amplifier and a speaker. The camera is used to detect whether there is someone in front of the automatic ticket vending machine. After detecting a person, the voice recognition unit automatically turns on the microphone to pick up sound and actively greets the passenger. After the passenger expresses his intention, the voice recognition unit calls the relevant service for voice recognition and voice understanding. Finally, the passenger's intention is notified to the TVM main control through the serial port. The TVM main control controls the display page to jump accordingly. At the same time, the voice recognition unit broadcasts the relevant prompt voice through the amplifier board and the speaker. The passenger can achieve the purpose of buying tickets without touching the device. This wiring method is used in the transformation of existing automatic ticket vending machines. It only needs to connect a serial port line to the TVM main control device. All voice interaction related actions are implemented in the voice recognition unit, which can achieve the effect of voice interaction with minimal changes to the existing system of the existing automatic ticket vending machine.

[0120] Since the existing automatic ticket vending machines were not designed to support voice control during their initial production, most of them do not have reserved installation locations for the hardware devices necessary for voice interaction, such as cameras and microphones, in the whole machine panel, and there are no structural conditions for drilling holes to install cameras and microphones on the whole machine panel. Based on the above problems, it is possible to consider installing a bracket on the top of the front cover of the whole machine and fixing the microphone camera on the bracket. Considering that the bracket is installed in a high position, the bracket can be tilted forward by 5° to 10° to form a small bird's-eye view. With a wide-angle camera, it can basically support the interaction needs of passengers with a height of 1.4 meters to 1.85 meters within the normal interaction distance.

[0121] like Figure 4 As shown, after installing the microphone array on the top of the front cover of the whole machine, open a wiring hole on the top of the chassis, and connect the connecting wires of the microphone and camera to the voice recognition unit inside the chassis. This method can avoid the problem that holes cannot be opened on the panel of the ticket vending machine to install microphones and cameras, and can achieve completely lossless installation on the existing ticket vending machine panel.

[0122] This embodiment can give the existing automatic ticket vending machines AI voice interaction capabilities at the lowest cost, and can realize the AI ​​voice interaction function without changing the panel of the existing automatic ticket vending machines and with minimal changes to the overall hardware.

[0123] In this embodiment, voice interaction can be used for automatic ticket sales, which meets the diversity of automatic ticket sales methods. By performing face recognition detection on user-captured images, it can automatically detect whether there is a user who needs to buy a ticket in front of the automatic ticket machine. By performing semantic recognition on the ticket sales interactive voice, the user's semantics can be effectively identified. When it is detected that the user's semantics is a question and answer type, the automatic ticket machine can be automatically controlled to perform voice question and answer feedback based on the feedback information. If the user's semantics is detected to be a ticket sales type, the ticket sales jump interface can be effectively determined based on the user's semantics. By controlling the automatic ticket machine to display the ticket sales on the ticket sales jump interface, the user's choice of ticket purchase is effectively facilitated. The ticket vending machine is controlled to perform the ticket sales operation through the ticket card purchase instruction to achieve the effect of automatic ticket sales.

[0124] Embodiment 3

[0125] Figure 5 2 is a block diagram of a terminal device 2 provided in the third embodiment of the present application. Figure 5 As shown, the terminal device 2 of this embodiment includes: a processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the processor 20, such as a program of the automatic ticketing interactive method. When the processor 20 executes the computer program 22, the steps in each embodiment of the automatic ticketing interactive method described above are implemented.

[0126] Exemplarily, the computer program 22 may be divided into one or more modules, which are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 22 in the terminal device 2. The terminal device may include, but is not limited to, a processor 20 and a memory 21.

[0127] The processor 20 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0128] The memory 21 may be an internal storage unit of the terminal device 2, such as a hard disk or memory of the terminal device 2. The memory 21 may also be an external storage device of the terminal device 2, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device 2. Further, the memory 21 may also include both an internal storage unit of the terminal device 2 and an external storage device. The memory 21 is used to store the computer program and other programs and data required by the terminal device. The memory 21 may also be used to temporarily store data that has been output or is to be output.

[0129] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional unit.

[0130] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium can be non-volatile or volatile. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in computer-readable storage media can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable storage media do not include electrical carrier signals and telecommunication signals.

[0131] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An automatic ticketing interactive method, characterized in that: The method comprises: Acquire user-collected images, and perform face recognition detection on the user-collected images; If the face recognition detection is qualified, the automatic ticket vending machine is controlled to collect the user's voice to obtain the ticket selling interactive voice, and the ticket selling interactive voice is semantically recognized to obtain the user's semantics; If the semantic type of the user semantics is a question-and-answer type, feedback information is determined according to the user semantics, and the automatic ticket vending machine is controlled to perform question-and-answer feedback according to the feedback information; If the semantic type of the user semantics is a ticketing type, determining a ticketing jump interface according to the user semantics, and controlling the automatic ticket vending machine to display tickets according to the ticketing jump interface; If a ticket purchase instruction for the ticket jump interface is received, the automatic ticket vending machine is controlled to perform a ticket sale operation according to the ticket purchase instruction, wherein the ticket purchase instruction includes a touch instruction and / or a voice instruction.

2. The automatic ticket vending interactive method according to claim 1, characterized in that: Performing semantic recognition on the ticketing interactive voice to obtain user semantics includes: If the number of face images in the detection result of the face recognition detection is less than the number threshold, directly performing semantic recognition on the ticketing interactive voice to obtain the user semantics; If the number of images is greater than or equal to the number threshold, performing user analysis on the face images, and determining a target user according to the user analysis results; In the ticket selling interactive voice, the voice corresponding to the target user is determined as the target interactive voice, and semantic recognition is performed on the target interactive voice to obtain the user semantics.

3. The automatic ticket vending interactive method according to claim 2, characterized in that: Performing user analysis on the face image and determining a target user according to the user analysis result includes: Acquire the image area of ​​the face image, and delete the face image whose image area is smaller than an area threshold; If the number of the facial images after the image deletion is greater than or equal to the number threshold, acquiring facial features of the facial images, and determining the user's age based on the facial features; Acquire the user distance between the user corresponding to the face image and the automatic ticket vending machine, and numerically map the user distance and the user age to obtain a mapped distance and a mapped age; Performing a weighted operation on the mapping distance and the mapping age to obtain a user weighted value, and determining the face image corresponding to the maximum user weighted value as a target face; The user corresponding to the target face is determined as the target user.

4. The automatic ticket vending interactive method according to claim 2, characterized in that: In the ticket selling interactive voice, determining the voice corresponding to the target user as the target interactive voice includes: Performing zero-crossing detection on the ticket-selling interactive voice, and performing voice segmentation on the ticket-selling interactive voice according to the zero-crossing detection result to obtain segmented voice; Extracting speech features of the segmented speech, and classifying the segmented speech according to the speech features to obtain a speech classification set; Determining a speech standard feature according to the user information of the target user, and calculating a feature similarity between the speech feature and the speech standard feature; The speech feature corresponding to the maximum feature similarity is determined as the target feature, and the speech in the speech classification set corresponding to the target feature is determined as the target interactive speech.

5. The automatic ticket vending interactive method according to claim 1, characterized in that: After semantic recognition of the ticketing interactive voice is performed to obtain user semantics, the method further includes: Acquire a ticketing vocabulary set, and perform vocabulary matching between preset words in the ticketing vocabulary set and the user semantics; If the preset vocabulary matches the vocabulary of the user semantics successfully, determining the semantic type of the user semantics as the ticketing type; If the preset vocabulary fails to match the vocabulary of the user semantics, the semantic type of the user semantics is determined to be the question and answer type.

6. The automatic ticket vending interactive method according to claim 1, characterized in that: After controlling the automatic ticket vending machine to display tickets according to the ticket jump interface, the method further includes: Obtaining a display identifier of the ticket sales jump interface, and determining ticket sales prompt information according to the display identifier; Obtaining the plug-in position of the interactive plug-in on the automatic ticket vending machine, and matching the ticket sales prompt information with the plug-in position; The interactive plug-in is pointed to and prompted according to the prompt matching result.

7. The automatic ticket vending interactive method according to claim 1, characterized in that: Determining feedback information according to the user semantics includes: Performing vector conversion on the user semantics to obtain a semantic vector, and performing similarity calculation between the semantic vector and the question-answer vector in the question-answer database to obtain vector similarity; The question-and-answer vector corresponding to the maximum vector similarity is determined as a target vector, and the question-and-answer information corresponding to the target vector is determined as the feedback information.

8. An automatic ticketing interactive system, characterized in that: The system comprises: A face recognition module is used to obtain user-collected images and perform face recognition detection on the user-collected images; A semantic recognition module is used to control the automatic ticket vending machine to collect the user's voice if the face recognition detection is qualified, obtain the ticket selling interactive voice, and perform semantic recognition on the ticket selling interactive voice to obtain the user's semantics; A question feedback module, for determining feedback information according to the user semantics if the semantic type of the user semantics is a question-and-answer type, and controlling the automatic ticket vending machine to perform question-and-answer feedback according to the feedback information; A ticket display module, for determining a ticket jump interface according to the user semantics if the semantic type of the user semantics is a ticket type, and controlling the automatic ticket vending machine to display tickets according to the ticket jump interface; The ticket execution module is used to control the automatic ticket vending machine to execute the ticket selling operation according to the ticket purchase instruction if a ticket purchase instruction for the ticket jump interface is received.

9. The automatic ticket vending interactive system according to claim 8, characterized in that: The semantic recognition module is also used for: If the number of face images in the detection result of the face recognition detection is less than the number threshold, directly performing semantic recognition on the ticketing interactive voice to obtain the user semantics; If the number of images is greater than or equal to the number threshold, performing user analysis on the face images, and determining a target user according to the user analysis results; In the ticket selling interactive voice, the voice corresponding to the target user is determined as the target interactive voice, and semantic recognition is performed on the target interactive voice to obtain the user semantics.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images