Parking lot guard method and device based on artificial intelligence technology

Abstract

The invention discloses a parking lot guarding method and device based on an artificial intelligence technology. An unattended system in the method comprises the following steps: receiving voice information; converting the voice information into text information through a voice recognition algorithm; extracting scenes and elements based on the character information; sending the scene and the elements to a cloud platform; if the response information of the scene and all the elements is not obtained from the cloud platform, generating a reply voice based on the text information, and sending the reply voice to the terminal; and if the response information of the scene and all the elements is obtained, sending a release instruction to a barrier gate end. Through the method and the device, the problem of no answering in the calling process is solved, the response efficiency is improved, and the labor cost is saved.

Description

Technical Field

[0001] The present invention belongs to the technical field of parking lot duty, and particularly relates to a parking lot duty method and device based on artificial intelligence technology. Background Art

[0002] With the acceleration of the urbanization process, cars are constantly popularized in the public life. The rapid growth of the car ownership has brought great challenges to urban traffic. "Difficult parking and disorderly parking" has become one of the main reasons for urban traffic congestion. The traditional way of managing the traffic flow by relying on manual and mechanical gates can no longer meet the increasing load of cars. This way not only has low efficiency, but also easily leads to problems such as low efficiency of charging and passing, lack of supervision resulting in missing parking fees, and dangerous events such as hitting people and cars caused by improper manual operation. In case of abnormalities at the parking lot entrance and exit, if the duty personnel are busy or not on duty and the car owner's call is not answered, it will seriously affect the customer experience.

[0003] Traditional parking lot management usually adopts the manual charging method, which has disadvantages such as low efficiency, opaque information, potential safety hazards, difficult management, and poor user experience. There is an urgent need for intelligent transformation to improve the management level and user experience.

[0004] Therefore, a parking lot duty method based on artificial intelligence technology has emerged as the times require. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above problems, and provide a parking lot duty method and device based on artificial intelligence technology, which solves the problem of no answer during the call process, improves the response efficiency and saves labor costs.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is:

[0007] A parking lot duty method based on artificial intelligence technology, the unattended system includes the following steps:

[0008] Receive voice information, where the voice information includes initial voice information and response information;

[0009] Convert the voice information into text information through a voice recognition algorithm;

[0010] Extract the scene and elements based on the text information;

[0011] Send the scene and elements to the cloud platform;

[0012] If receiving the response information from the cloud platform that the scene and all elements are not obtained, then generate a reply voice based on the text information and send the reply voice to the terminal;

[0013] If the response information of the scene and all the elements is obtained, a release instruction will be sent to the barrier terminal.

[0014] As a further improvement, in the extraction of the scene and elements based on text information, when the information of the element received from the cloud platform is not found, the element will be stored in the database of the unattended system.

[0015] As a further improvement, the elements at least include:

[0016] Lane information or / and access object or / and car owner's phone number or / and departure time.

[0017] As a further improvement, the terminal includes the following steps:

[0018] Receive the reply voice;

[0019] Based on the reply voice, make a response;

[0020] Send the response information to the unattended system.

[0021] As a further improvement, the terminal further includes the following steps:

[0022] When the channel is not released and unattended within the set threshold range, receive the automatic connection information of the unattended system and send the initial voice information to the unattended system.

[0023] As a further improvement, when the terminal calls the cloud call center and exceeds the threshold time, the unattended system will automatically connect to the terminal.

[0024] On the other hand, the present invention also provides a parking lot management method based on artificial intelligence technology. The cloud platform includes the following steps:

[0025] Receive the scene and elements;

[0026] Judge whether the received scene and elements are complete; wherein,

[0027] If the scene and all the elements are obtained, send the response information of the scene and all the elements to the unattended system;

[0028] If the scene and all the elements are not obtained, send the response information of not obtaining the scene and all the elements to the unattended system.

[0029] As a further improvement, in the judgment of whether the received scene and elements are complete, when the received element is not stored in the database, the element will be stored in the database, and the information that the element is not found will be sent to the unattended system.

[0030] As a further improvement, the barrier end includes the following steps:

[0031] Receive a vehicle release instruction from the unattended system;

[0032] Based on the received vehicle release instruction from the unattended system, release the vehicle.

[0033] On the other hand, the present invention also provides a parking lot attendant device based on artificial intelligence technology. The device includes at least one processor and a memory that stores instructions. When the instructions are executed by at least one processor, the method in the above technical solution is implemented.

[0034] A computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the steps of the above technical solution.

[0035] A computer program product includes a computer program, and when the computer program is executed by a processor, the method described in the steps of the above technical solution is implemented.

[0036] The beneficial effects of the present invention are:

[0037] Through this method and device, the problem of no one answering during the call is solved, the response efficiency is improved, and the labor cost is saved; voice intercom, voice recognition, and human-computer dialogue are introduced into the parking lot management business, artificial intelligence is combined with parking lot management, and the data in the parking lot operation process is used to train the dialogue model to achieve high-efficiency unmanned management of the parking lot; the present invention provides strong support for the intelligent management of the parking lot by introducing AI technology, especially voice intercom and semantic recognition; on the basis of realizing functions such as automatic identification, automatic charging, and toll release of vehicles entering and leaving the parking lot, the handling of other abnormal situations is increased, greatly improving the operation efficiency and management level of the parking lot; through the parking lot attendant method and device introducing artificial intelligence technology, the problem of no one answering during the call is mainly solved, the response efficiency is significantly improved, and the labor cost is effectively saved; this innovation not only integrates advanced technologies such as voice intercom, voice recognition, and human-computer dialogue into the parking lot management business, but also makes full use of the data generated during the parking lot operation process to continuously optimize the dialogue model, thus realizing high-efficiency management of the parking lot, not only improving the user experience and satisfaction, but also laying a solid foundation for the sustainable development of the parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention has the following drawings:

[0039] Figure 1 It is a topology diagram of a parking lot attendant method and device based on artificial intelligence technology in some specific embodiments of the present invention;

[0040] Figure 2 is a flowchart of a parking lot duty method based on artificial intelligence technology in some specific embodiments of the present invention;

[0041] Figure 3 is a schematic structural diagram of a parking lot duty device based on artificial intelligence technology in some specific embodiments of the present invention;

[0042] Figure 4 Schematic diagram of a parking lot duty system based on artificial intelligence technology of the present invention. Detailed implementation manners

[0043] The following embodiments further illustrate the content of the present invention, but should not be construed as limiting the present invention. Without departing from the spirit and essence of the present invention, any modification or replacement made to the methods, steps or conditions of the present invention shall fall within the scope of the present invention.

[0044] As Figure 1 、 2 shown, the present invention provides a parking lot duty method based on artificial intelligence technology. The unattended system includes the following steps:

[0045] Step S100: Receive voice information, where the voice information includes initial voice information and response information;

[0046] Step S101: Convert the voice information into text information through a voice recognition algorithm;

[0047] Step S102: Extract the scene and elements based on the text information;

[0048] Step S103: Send the scene and elements to the cloud platform;

[0049] Step S104: If receiving a response information from the cloud platform that the scene and all the elements have not been obtained, generate a reply voice based on the text information and send the reply voice to the terminal;

[0050] Step S105: If obtaining the response information of the scene and all the elements, send a release instruction to the gate end.

[0051] In some embodiments of the present invention, in the extraction of the scene and elements based on the text information, when receiving the information that the element has not been found from the cloud platform, the element is stored in the database of the unattended system.

[0052] For example, when querying the content where the scene and elements do not exist from the cloud platform, the elements that do not exist in the cloud platform can be stored in the database of the unattended system or the cloud platform.

[0053] In some embodiments of the present invention, the elements at least include: lane information or / and access object or / and vehicle owner's phone number or / and departure time.

[0054] For example, the scenario dialogue between A: intelligent customer service and B: vehicle owner when entering an open area is as follows:

[0055] A: Hello, how can I help you?

[0056] B: Open the door for me.

[0057] A: I'm very sorry, temporary vehicles are not allowed to pass through the park. After confirming your identity, you will be registered and released. Please tell me your contact person in the park.

[0058] B: I'm in a hurry. Someone called a car and asked me to come here quickly to pick her up.

[0059] A: I'm very sorry, temporary vehicles are not allowed to pass through the park. After confirming your identity, you will be registered and released. Please tell me your contact person in the park.

[0060] B: Ma Dongmei.

[0061] A: Okay, may I ask what your phone number is?

[0062] B: Do I need to provide my phone number just to pick someone up? How troublesome.

[0063] A: Sorry, we are registering your information. May I ask what your phone number is?

[0064] B: 13322332233.

[0065] A: May I ask when you expect to leave?

[0066] B: I'll leave right after picking her up. It won't take long.

[0067] A: May I ask when you expect to leave?

[0068] B: Just over ten minutes.

[0069] A: Okay, you have been registered and released. Wish you a pleasant visit.

[0070] The extracted elements are:

[0071] Access object: Ma Dongmei

[0072] Vehicle owner's phone number: 13322332233

[0073] Departure time: Just over ten minutes

[0074] In some embodiments of the present invention, when the terminal calls the cloud call center and exceeds the threshold time, the unattended system automatically connects to the terminal.

[0075] In some embodiments of the present invention, when within the set threshold range, the channel does not release and is unattended, receive the automatic connection information of the unattended system and send the initial voice message to the unattended system.

[0076] On the other hand, a parking lot attendance method based on artificial intelligence technology is provided. The terminal (the vehicle owner calls the device) includes the following steps:

[0077] Step S200: Receive the reply voice;

[0078] Step S201: Make a response based on the reply voice;

[0079] Step S203: Send the response information to the unattended system.

[0080] The terminal further includes the following steps:

[0081] Step S204: When the channel does not release and is unattended, send the initial voice message to the unattended system.

[0082] On the other hand, a parking lot attendance method based on artificial intelligence technology is also provided. The cloud platform includes the following steps:

[0083] Step S300: Receive the scene and elements;

[0084] Step S301: Determine whether the received scene and elements are complete; wherein,

[0085] Step S3010: If the scene and all elements are obtained, send the response information of the obtained scene and all elements to the unattended system;

[0086] Step S3012: If the scene and all elements are not obtained, send the response information of not obtaining the scene and all elements to the unattended system.

[0087] In some embodiments of the present invention, in the determination of whether the received scene and elements are complete, when the received element is not stored in the database, store the element in the database and send the information that the element is not found to the unattended system.

[0088] On the other hand, a parking lot attendance method based on artificial intelligence technology is also provided at the same time. The gate end includes the following steps:

[0089] Step S400: Receive the vehicle release instruction of the unattended system;

[0090] Step S401: Based on the vehicle release instruction received from the unmanned system, release the vehicle.

[0091] In the present invention, the technical solution process of the present invention is described by taking visitor registration as an example. The traffic rules of the parking lot are that temporary vehicles are not allowed to pass, and the car owner wants to enter the parking lot by registering as a visitor. The car owner enters the mini program by scanning the code to call the attendant, and the unattended system automatically intervenes to connect the call. And through the accompanying information of the call, the system can automatically determine the parking lot channel where the car owner is located, so as to query the current traffic information. During the call, the unattended system collects the car owner's voice information in real time and sends it to the voice recognition system, converts the voice into text information through voice interaction and recognition technology, and generates voice to send to the car owner. During the conversation, the system uses natural language processing technology to understand the owner's intentions and semantics, perform scene judgment, extract key elements, and guide the car owner to provide key information through question and answer. When it is necessary to query and verify information, the unattended system initiates a request to the cloud platform to obtain relevant information. When the conditions are met, the unattended system registers the visitor information to the cloud platform and controls the gate to lift the bar to release.

[0092] like Figure 3 As shown, the present invention provides a parking lot guarding device based on artificial intelligence technology, and the unmanned system includes:

[0093] A first receiving module, used for receiving voice information, wherein the voice information includes initial voice information and response information;

[0094] A text conversion module is used to convert voice information into text information through a voice recognition algorithm;

[0095] A first extraction module, used for extracting scenes and elements based on text information;

[0096] A first sending module, used to send scenes and elements to a cloud platform;

[0097] A second receiving module is configured to generate a reply voice based on the text information if the response information of the cloud platform indicating that the scene and all the elements have not been obtained is received, and send the reply voice to the terminal;

[0098] The third receiving module is used to send a release instruction to the gate end if the response information of the scene and all the elements is obtained.

[0099] In some embodiments of the present invention, when extracting scenes and elements based on text information, if the elements received from the cloud platform are not found, the elements are stored in the database of the unattended system. For example, these elements can be stored in the database of this server or in the cloud server.

[0100] In some embodiments of the present invention, the elements at least include: lane information or / and access object or / and vehicle owner's phone number or / and departure time.

[0101] On the other hand, a parking lot duty method based on artificial intelligence technology is provided, and the terminal includes the following steps:

[0102] A third receiving module, configured to receive a reply voice;

[0103] A first answering module, configured to make an answer based on the reply voice;

[0104] A third sending module, configured to send the answer information to the unattended system.

[0105] The terminal further includes the following steps:

[0106] A sending module, configured to send an initial voice message to the unattended system when the passage is not released and there is no one on duty.

[0107] On the other hand, a parking lot duty method based on artificial intelligence technology is further provided, and the cloud platform includes the following steps:

[0108] A fourth receiving module, configured to receive a scene and elements;

[0109] A judging module, configured to judge whether the received scene and elements are complete; wherein,

[0110] A first judging module, if the scene and all elements are obtained, sends the answer information of the obtained scene and all elements to the unattended system;

[0111] A second judging module, configured to send the answer information of not obtaining the scene and all elements to the unattended system if the scene and all elements are not obtained.

[0112] In some embodiments of the present invention, in judging whether the received scene and elements are complete, when an element received is not stored in the database, the element is stored in the database, and the information that the element is not found is sent to the unattended system.

[0113] On the other hand, a parking lot duty method based on artificial intelligence technology is also provided at the same time, and the gate end includes the following steps:

[0114] A fifth receiving module, configured to receive a vehicle release instruction from the unattended system;

[0115] A release module, configured to release the vehicle based on the received vehicle release instruction from the unattended system.

[0116] In some embodiments of the present invention, the voice intercom module: conducts audio calls, and the on-duty personnel can answer the conversation with the car owner, and can also obtain and send audio through the relevant interface provided by it to realize human-computer intercom.

[0117] In some embodiments of the present invention, speech recognition and conversion: converting audio stream into text information (converting the owner's voice into text), and converting text into speech (providing words spoken to the owner).

[0118] In some embodiments of the present invention, the cloud platform: a parking lot business platform, is used to process traffic information and control equipment.

[0119] In some embodiments of the present invention, the unattended system is connected and starts a conversation; if there is a duty officer on duty, the duty officer uses the duty room to directly connect and handle the matter; when there is no duty officer or the duty room is insufficient, the system intervenes and automatically connects, and a threshold for the time of non-connection can be preset.

[0120] In some embodiments of the present invention, the extraction scenarios and elements include at least a visitor registration scenario and an exit license plate recognition error scenario.

[0121] In some embodiments of the present invention, during the human-computer interaction process, when it is necessary to query and verify information, the unattended system initiates a request to the cloud platform to obtain relevant information. Taking the visitor registration scenario as an example, if the background judgment logic requires the user to provide the name and mobile phone number of the person being visited, the system will generate a voice query for relevant information. After the user answers, the system queries the cloud platform to see if the information is consistent. Other scenarios are similar. When no additional information is required, there is no need to query and verify.

[0122] Through this method and device, the problem of no answer during a call is solved, the response efficiency is improved, and labor costs are saved; voice intercom, voice recognition, and human-machine dialogue are introduced into the parking lot management business, combining artificial intelligence with parking lot management, and using the data in the parking lot operation process to train the dialogue model to achieve highly efficient unmanned management of the parking lot; the present invention provides strong support for the intelligent management of the parking lot by introducing AI technology, especially voice intercom and semantic recognition; on the basis of realizing functions such as automatic identification of vehicle entry and exit, automatic charging, and toll release, it adds the handling of other abnormal situations, greatly improving the operation efficiency and management level of the parking lot; the method and device for parking lot duty through the introduction of artificial intelligence technology mainly solve the problem of no answer during a call, significantly improving the response efficiency and effectively saving labor costs; this innovation not only integrates advanced technologies such as voice intercom, voice recognition, and human-machine dialogue into the parking lot management business, but also makes full use of the data generated during the parking lot operation process to continuously optimize the dialogue model, thus realizing highly efficient management of the parking lot, not only improving the user experience and satisfaction, but also laying a solid foundation for the sustainable development of the parking lot.

[0123] In some specific embodiments, such as Figure 4 shown, a parking lot duty system (device) based on artificial intelligence technology, the system (device) includes at least one processor, and a memory that stores instructions to implement a parking lot duty method based on artificial intelligence technology according to any one of the above technical solutions.

[0124] In some specific embodiments, a computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the steps in the above technical solutions.

[0125] In some specific embodiments, a computer program product includes a computer program, and when the computer program is executed by a processor, it implements the method of the steps in the above technical solutions.

[0126] The implementation modes and functional operations of the subject matter described in this specification can be implemented in the following: digital electronic circuits, tangibly implemented computer software or firmware, computer hardware, including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of the above. The implementation modes of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or more modules of computer program instructions encoded on one or more tangible non-transitory program carriers, for being executed by a data processing device or controlling the operation of the data processing device.

[0127] As an alternative or in addition, program instructions may be encoded on a propagated signal generated artificially, e.g., a machine-generated electrical, optical, or electromagnetic signal, which is generated as encoded information for transmission to a suitable receiver device that executes with a data processing apparatus. A computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of the foregoing devices.

[0128] A computer program (which may also be referred to or described as a program, software, a software application, a module, a software module, a script, or code) may be written in any form of programming language, including a compiled or interpreted language, or a declarative or procedural language, and the computer program may be deployed in any form, including as a stand-alone program or as a module, a component, a subroutine, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. The program may be stored in a part of a file that holds other programs or data, e.g., in one or more scripts stored in: a markup language document; a single file dedicated to the relevant program; or multiple co-related files, e.g., files that store one or more modules, subroutines, or portions of code. The computer program may be deployed to execute on one computer or on multiple computers, which may be located at one site, or distributed across multiple sites and interconnected by a communication network.

[0129] The content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0130] Although the present invention has been described in detail above with general descriptions, specific embodiments, and experiments, modifications or improvements can be made thereto on the basis of the present invention, which are obvious to those skilled in the art. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope of the present invention claimed.

Claims

1. A parking lot guarding method based on artificial intelligence technology, characterized in that: The unattended system includes the following steps: Receiving voice information, wherein the voice information includes initial voice information and response information; Through speech recognition algorithm, voice information is converted into text information; Extract scenes and elements based on text information; Send the scene and elements to the cloud platform; If the receiving cloud platform fails to obtain the response information of the scene and all the elements, a reply voice is generated based on the text information, and the reply voice is sent to the terminal; If the response information of the scene and all the elements is obtained, the release instruction is sent to the gate end.

2. The parking lot guarding method based on artificial intelligence technology according to claim 1 is characterized in that: In the extraction of scenes and elements based on text information, when no information is found for the elements received from the cloud platform, the elements are stored in the database of the unattended system.

3. The parking lot guarding method based on artificial intelligence technology according to claim 1 is characterized in that: The elements include at least: Lane information and / or visiting object and / or vehicle owner’s phone number and / or departure time.

4. The parking lot guarding method based on artificial intelligence technology according to claim 1 is characterized in that: The terminal comprises the following steps: Receive reply voice; Responding based on the reply voice; The response information is sent to the unattended system.

5. The parking lot guarding method based on artificial intelligence technology according to claim 4 is characterized in that: The terminal further comprises the following steps: When the channel is not released and unattended within the set threshold range, the unattended system automatically receives the information and sends the initial voice message to the unattended system.

6. The parking lot guarding method based on artificial intelligence technology according to claim 1 is characterized in that: When the terminal calls the cloud call center, when the threshold time is exceeded, the unattended system automatically connects to the terminal.

7. The parking lot guarding method based on artificial intelligence technology according to claim 1 is characterized in that: The gate end comprises the following steps: Receive vehicle release instructions from the unmanned system; Based on the vehicle release instruction received from the unmanned system, the vehicle is released.

8. A parking lot guarding method based on artificial intelligence technology, characterized in that: The cloud platform includes the following steps: receiving scenes and elements; Determine whether the received scene and elements are complete; wherein, If the scene and all the elements are obtained, a response message of obtaining the scene and all the elements is sent to the unattended system; If the scene and all the elements are not obtained, a response message indicating that the scene and all the elements are not obtained is sent to the unattended system.

9. The parking lot guarding method based on artificial intelligence technology according to claim 8 is characterized in that: In the determining whether the received scene and the elements are complete, if the received elements are not stored in the database, the elements are stored in the database, and information indicating that the elements are not found is sent to the unattended system.

10. A parking lot guarding device based on artificial intelligence technology, characterized in that: The device includes at least one processor and a memory storing instructions, wherein when the instructions are executed by at least one processor, a parking lot guarding method based on artificial intelligence technology as described in any one of claims 1 to 7 is implemented.

Images