CN115310827A

CN115310827A - Data processing method and device, electronic equipment and storage medium

Info

Publication number: CN115310827A
Application number: CN202210964037.0A
Authority: CN
Inventors: 师小凯; 张政
Original assignee: Beijing Elite Road Technology Co ltd
Current assignee: Beijing Elite Road Technology Co ltd
Priority date: 2022-08-11
Filing date: 2022-08-11
Publication date: 2022-11-08

Abstract

The present disclosure provides a data processing method, an apparatus, an electronic device and a storage medium, and relates to the technical field of computers, in particular to the technical field of intelligent transportation and big data. The specific implementation scheme comprises the following steps: acquiring an entry/departure event uploaded by front-end equipment and an audit result of the entry/departure event fed back by audit equipment; and determining the abnormal problem existing in the front-end equipment or the auditing equipment according to the in/out-of-position event of at least one auditing result. According to the scheme, based on the entry/exit event and the audit result thereof, the abnormal problems of the front-end equipment or the audit equipment forming the parking management system are actively discovered, the abnormal problems are not discovered manually, the efficiency of discovering the abnormal problems is improved, and the parking management system is upgraded and improved subsequently according to the abnormal problems discovered in time.

Description

Data processing method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, particularly to the field of intelligent transportation and big data technologies, and in particular, to a data processing method and apparatus, an electronic device, a storage medium, and a computer program product.

Background

As vehicles increase, urban traffic becomes congested more and more frequently. The parking mode of road parking spaces is adopted in many places, so that the problems of difficult parking and the like are relieved to a certain extent, and the opportunity is created for traffic jam. Therefore, how to effectively manage the urban public parking spaces is very important.

At present, parking management systems are mainly developed to manage parking spaces. Although the parking management system can manage parking spaces, how to find out the problems existing in the parking management system becomes a technical problem which needs to be solved urgently.

Disclosure of Invention

The present disclosure provides a data processing method, an apparatus, an electronic device, a storage medium, and a computer program product.

According to an aspect of the present disclosure, there is provided a data processing method including:

acquiring an entry/departure event uploaded by front-end equipment and an audit result of the entry/departure event fed back by audit equipment;

and determining the abnormal problem existing in the front-end equipment or the auditing equipment according to the in/out-of-position event of at least one auditing result.

According to an aspect of the present disclosure, there is provided a data processing apparatus including:

the acquisition module is used for acquiring the entry/departure events uploaded by the front-end equipment and auditing results of the entry/departure events fed back by the auditing equipment;

and the abnormal problem determining module is used for determining the abnormal problem existing in the front-end equipment or the auditing equipment according to the in/out event of at least one auditing result.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the data processing method of any of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a data processing method of any embodiment of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the data processing method of any of the embodiments of the present disclosure.

According to the technology disclosed by the invention, based on the entry/exit event and the audit result thereof, the abnormal problems of the front-end equipment or the audit equipment forming the parking management system are actively discovered, and the abnormal problems are not discovered manually, so that the efficiency of discovering the abnormal problems is improved, and the upgrading and improvement of the parking management system are completed subsequently according to the abnormal problems discovered in time.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic flow chart of a data processing method provided by an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart diagram illustrating a further data processing method provided by an embodiment of the present disclosure;

FIG. 3 is a schematic flow chart diagram illustrating a further data processing method provided by an embodiment of the present disclosure;

FIG. 4 is a schematic flow chart diagram illustrating a further data processing method provided by an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present disclosure;

fig. 6 is a block diagram of an electronic device for implementing a data processing method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The parking management system mainly comprises front-end equipment, a data center platform and auditing equipment; the auditing equipment comprises automatic auditing equipment and manual auditing equipment. The front-end equipment is responsible for monitoring the real-time scene of the parking space accessory, and can analyze the captured image to determine whether an in/out-of-position event is generated or not as the front-end equipment has certain information processing capacity; the entrance/exit event refers to an event that a vehicle is parked in a parking space or leaves the parking space, and specifically includes an original image (which may be a single image or multiple images) of the entrance/exit event, time of event generation, a parking space identifier, an identifier of a front-end device (which is used for determining a device generating the entrance/exit event), vehicle information (for example, a vehicle brand and a license plate number recognized by the front-end device by using a universal license plate recognition model), and the like. And after the front-end equipment generates the in/out-of-position event, the in/out-of-position event is sent to the data center platform. The data center platform may be formed by a central server, and after receiving an entry/exit event sent by the front-end device, the data center platform may store the entry/exit event and forward the entry/exit event to the automatic auditing device. The automatic auditing device is optionally a GPU (Graphics Processing Unit) server device, and an automatic auditing service based on an auditing algorithm is deployed on the automatic auditing device, so that the automatic auditing device calls the automatic auditing service to audit after receiving an in/out event sent by the data center platform, and then feeds back an auditing result to the data center platform. And if the result fed back by the automatic auditing equipment cannot be determined, the data center platform sends the in/out-of-position event to manual auditing equipment so as to be audited manually, and finally, corresponding auditing results are obtained from the manual auditing equipment. After the parking management system of the present disclosure is introduced, the specific flow of the data processing method of the present disclosure can be referred to as the following embodiments.

Fig. 1 is a schematic flow chart of a data processing method according to an embodiment of the present disclosure, which is applicable to mining a situation of an abnormal problem existing in a parking management system by using an entry/exit event and an audit result thereof stored on a data center platform. The method can be performed by a data processing device implemented in software and/or hardware and integrated on an electronic device, for example on a data center platform of a parking management system.

Specifically, referring to fig. 1, the data processing method is as follows:

s101, acquiring an entry/departure event uploaded by front-end equipment and an auditing result of the entry/departure event fed back by auditing equipment.

In the embodiment of the disclosure, the front-end equipment is deployed near the parking spaces and is used for monitoring scenes around one or more parking spaces, so that scene graphs of parking space accessories can be captured in real time; in addition, the front-end device has a certain information processing capability, and can analyze whether to generate an in/out event according to the captured image, where the in/out event refers to an event that the vehicle is parked in a parking space or leaves the parking space, and specifically includes an original image of the in/out event, time generated by the event, a parking space identifier, an identifier of the front-end device, vehicle information (such as a vehicle brand and a license plate number), and the like. It should be noted that a universal license plate recognition model is deployed in the front-end device, and the front-end device recognizes the license plate number of the vehicle based on the license plate recognition model. After the in/out-of-position event is generated, the front-end device uploads the in/out-of-position event to the data center platform.

After acquiring the in/out-of-position event uploaded by the front-end equipment, the data center platform stores the in/out-of-position event and simultaneously sends the in/out-of-position event to the auditing equipment for auditing. The auditing equipment is divided into automatic auditing equipment and manual auditing equipment. During specific implementation, the in/out-of-position event is firstly sent to the automatic auditing equipment for auditing, and the in/out-of-position event which cannot be audited by the automatic auditing equipment is sent to the manual auditing equipment for manual auditing. And finally, the automatic auditing equipment and the manual auditing equipment feed back the auditing result to the data center platform. Therefore, the audit results received by the data center platform can be divided into two major categories, namely automatic audit results and manual audit results, and specifically, the automatic audit results include automatic audit pass and automatic audit discard; the manual checking result comprises that the manual checking is passed, the license plate is manually modified to pass (the license plate number identified by the front-end equipment in the event is inaccurate, and the license plate number is manually modified according to the original image of the event and then passes), and the manual checking is abandoned. Wherein, the approved event is effective, and the abandoned event is ineffective. It should be noted that the event auditing results are specifically divided into a plurality of categories, so as to provide guarantee for determining the abnormal problem existing in the front-end device or the auditing device.

Through the step S101, the data center platform can obtain a large number of entry/exit events and their audit results, and can perform classified statistics on the entry/exit events according to the audit results, so as to mine the abnormal problem existing in the front-end device or the audit device of the parking management system according to the step S102.

S102, according to the in/out-of-position event of at least one type of auditing result, determining an abnormal problem existing in the front-end equipment or the auditing equipment.

In the embodiment of the disclosure, the entry/exit events of different types of auditing results can be analyzed to determine that the front-end equipment or auditing equipment has an abnormal problem. The abnormal problem of the front-end equipment comprises hardware abnormality of the front-end equipment and software algorithm abnormality of the front-end equipment. For example, if the audit result includes that the license plate is manually modified to pass, it is determined that the recognition effect of the universal license plate recognition model in the front-end device may be abnormal, and further judgment is required. The abnormal problem of the auditing equipment mainly refers to the problem existing in the automatic auditing equipment, such as the automatic auditing service in the automatic auditing equipment does not reach the standard. For example, the determination may be made based on a ratio of the number of events that have passed or have been discarded from the automatic review to the total number of events. It should be noted that, compared with the prior art in which the device abnormality is found manually, the present disclosure can find the abnormality problem existing in the front-end device or the auditing device in time by analyzing the entry/exit events of different auditing results.

According to the scheme, based on the in/out-of-position event and the auditing result thereof, the abnormal problems of the front-end equipment or the auditing equipment forming the parking management system are actively discovered, the abnormal problems are not discovered manually, the timeliness of discovering the abnormal problems is ensured, and the upgrading and improvement of the parking management system are completed according to the abnormal problems discovered in time.

Fig. 2 is a schematic flow chart diagram of yet another data processing method according to an embodiment of the present disclosure. Referring to fig. 2, the data processing method is as follows:

s201, acquiring an entry/departure event uploaded by front-end equipment and an auditing result of the entry/departure event fed back by auditing equipment.

In the embodiment of the disclosure, due to local characteristics and a camera erection mode, captured license plate characters (mainly embodied on Chinese characters) and angles of license plates may have particularity, and a problem of poor license plate recognition effect may exist by using a universal license plate recognition model as a basis, that is, an abnormal problem may exist in a license plate recognition model in front-end equipment. Based on this, the process of determining whether the front-end device has an abnormal problem according to the in/out event of at least one audit result can refer to steps S202-S204.

S202, aiming at an entrance/departure event of manually modifying the passing of the license plate, license plate identification is carried out on an original image captured by front-end equipment and included in the entrance/departure event through license plate iteration service, and a target license plate number is obtained.

In the embodiment of the disclosure, the license plate iteration service can be used for accurately identifying the license plate number in the license plate, and the license plate iteration service can be deployed on a data center platform or an independent GPU server device. If the license plate is deployed in a data center platform, directly calling license plate iteration service, and carrying out license plate recognition on an original image included in an in/out-of-position event which is passed by a manual modified license plate to obtain a target license plate number; if the license plate number correction method is deployed in independent GPU server equipment, the entry/exit event that the license plate is modified manually is sent to the GPU server, then the GPU server calls license plate iteration service, and license plate recognition is carried out on an original image captured by front-end equipment and included in the entry/exit event, so that a target license plate number is obtained. It should be noted that, as long as there is an entry/exit event that the license plate is manually modified to pass through, it indicates that the license plate number identified by the front-end device may be inaccurate.

S203, comparing the similarity of the target license plate number and the manually modified license plate number included in the in/out-of-position event.

After the target license plate number included in the original image is obtained through S202, the target license plate number is compared with the manually modified license plate number included in the entry/exit event that the manually modified license plate passes through, for example, the similarity of the two license plate numbers is solved. Optionally, the similarity of the license plate is calculated by comparing the number of the same characters with the difference number of the similar characters.

S204, if the similarity is larger than a preset threshold value, determining that the license plate recognition model in the front-end equipment has the problem of abnormal recognition effect.

If the similarity is greater than the preset threshold, it indicates that the license plate number actually existing in the original license plate number is consistent with the license plate number after manual modification, so that the license plate number initially identified by the front-end equipment is inaccurate, that is, the problem that the license plate identification model in the front-end equipment has abnormal identification effect is solved.

In the embodiment of the disclosure, based on the entry/exit event of manually modifying the passing license plate, whether the license plate recognition model in the front-end equipment has an abnormal problem can be quickly and accurately found.

Furthermore, after the problem that the license plate recognition model in the front-end equipment has abnormal recognition effect is determined, a training sample of the license plate recognition model can be constructed according to the original image and the license plate number modified manually, and the training sample is added into a sample library; and when the number of the training samples in the sample library is larger than a preset number threshold, performing iterative training on the license plate recognition model by using a license plate iterative service, and redeploying the trained license plate recognition model in the front-end equipment. Therefore, by constructing a new training sample and performing iterative training on the license plate recognition model in the front-end equipment, the problem of abnormal license plate recognition of the front-end equipment can be solved in time, and the effect of improving the parking management system is achieved.

Fig. 3 is a flow diagram of yet another data processing method according to an embodiment of the present disclosure. Referring to fig. 3, the data processing method is as follows:

s301, acquiring the entry/exit event uploaded by the front-end equipment and an auditing result of the entry/exit event fed back by the auditing equipment.

In the embodiment of the present disclosure, a process for determining an abnormal problem existing in the front-end device according to at least one entry/exit event of the audit result may be referred to as S302-S306.

S302, according to the entrance/exit events of different auditing results associated with the front-end equipment, the turnover rate or the abandonment rate of the parking space within a preset time length is determined.

In the embodiment of the present disclosure, the preset duration may be one week, or may be other values. For any front-end equipment, acquiring an entry/departure event uploaded by the front-end equipment every day within a preset time length and an audit result of the entry/departure event from data stored in a data center platform. Determining the turnover rate of the parking spaces every day according to the number of the checked in/out events every day, wherein the turnover rate of the parking spaces every day refers to the average number of times of parking vehicles in each parking space every day; or determining the abandonment rate of the parking spaces every day according to the number of the abandoned entrance/exit events examined every day. After the daily turnover rate or the abandonment rate of the parking space is obtained, the change condition of the turnover rate or the abandonment rate of the parking space within the preset time can be obtained.

And S303, judging whether the turnover rate or the abandonment rate of the parking space is abnormal.

Optionally, within the preset time period, if the parking space turnover rate suddenly increases or suddenly decreases or the abandonment rate suddenly increases, it indicates that the parking space turnover rate or the abandonment rate is abnormal, at this time, the front-end device may have an abnormal problem, and specifically, the specific abnormal problem that may exist may be determined according to the steps of S304-S306.

S304, acquiring a current scene graph acquired by the front-end equipment, and detecting a parking space line in the current scene graph.

And sending an instruction for shooting the scene graph to the front-end equipment, and acquiring the current scene graph afraid of the front-end equipment. After the current scene graph is obtained, the parking space lines existing in the current scene graph can be detected through a parking space line detection algorithm.

S305, comparing the parking space line in the current scene graph with the parking space line in the standard scene graph corresponding to the front-end equipment.

The standard scene graph is a scene graph collected when the front-end equipment is installed; when the standard scene graph is obtained for the first time, carrying out parking space line detection on the standard scene graph to obtain parking space lines existing in the standard scene graph. Therefore, the parking space line in the current scene graph can be compared with the parking space line in the standard scene graph corresponding to the front-end device, for example, the position, the length and the angle of the parking space line in the current scene graph are compared to determine whether the current scene graph has the problems of deviation, scaling and the like.

And S306, judging whether the front-end equipment has abnormal lens shift according to the comparison result.

If the problems of deviation, scaling and the like of the current scene graph are determined through the comparison of the parking space lines, the abnormal lens deviation exists in the front-end broken device. It should be noted that, steps S304-S306 may be implemented by a video diagnostic service, and the video diagnostic service may be deployed in a data center platform, or may be deployed in a separate GPU server, which is not specifically limited herein.

In the embodiment of the disclosure, when the turnover rate or the abandonment rate of the parking space is abnormal, the step of comparing the parking space lines in the current scene graph and the standard scene graph is triggered, so that whether the front-end equipment has the problem of lens deviation or not can be found in time.

Further, if the front-end device does not have lens offset abnormality, performing obstacle segmentation detection on the current scene graph to obtain a first obstacle mask, wherein the first obstacle mask is exemplarily a tree mask; performing obstacle segmentation detection on the standard scene graph to obtain a second obstacle mask, wherein the first obstacle mask is exemplarily a tree mask; and then determining whether the front-end equipment has obstacle shielding abnormity according to the first obstacle mask and the second obstacle mask. Optionally, the sizes of the first obstacle mask and the second obstacle mask are compared, and if the first obstacle mask is larger than the second obstacle mask and an intersection exists between an image area covered by the first obstacle mask and the parking space line, it is determined that an obstacle affects the front-end device lens. Therefore, the influence of the obstacles in the scene on the front-end equipment can be timely found.

Further, if the obstacle does not affect the front-end device, the current scene graph is subjected to fuzzy detection, whether the front-end device has image blurring abnormality or not is judged according to the detection result, and for example, if the blurring degree value in the detection result is greater than a preset blurring threshold value, it is determined that the front-end device has image blurring abnormality. All possible abnormal problems can be detected once in this way. It should be noted that, if the lens of the front-end device does not shift, no obstacle blocks the lens, and no image blurring abnormality is present, it indicates that the front-end device is normal, and it is determined that the abnormal parking space turnover rate may be caused by a change in the parking environment, for example, caused by rainy days.

Fig. 4 is a flow chart diagram of yet another data processing method according to an embodiment of the present disclosure. Referring to fig. 4, the data processing method is as follows:

s401, acquiring the entry/departure event uploaded by the front-end equipment and an auditing result of the entry/departure event fed back by the auditing equipment.

In the embodiment of the present disclosure, a process for determining an abnormal problem existing in the auditing device according to at least one entry/exit event of the auditing result may be referred to S402-S404.

S402, determining the number of the events of the entry/exit events needing manual review in the preset time length according to the number of the events of the entry/exit events generated in the preset time length and the number of the events of the entry/exit events automatically reviewed in the preset time length.

The preset time length can be a time period with a length of one hour which is determined at will. Because each in/out-of-position event has event generation time, the number A of the in/out-of-position events generated in the preset time can be counted by combining the preset time. And the event number B of the in/out-of-place events which are automatically audited within the preset time length is the number of the events which are fed back by the automatic audit equipment within the preset time length and are automatically audited to pass or be discarded. And the difference value of the event quantity A and the event quantity B is the event quantity of the in/out-of-position events needing manual examination in the preset time length.

And S403, determining the target parking number managed by a single person within a preset time according to the number of events, the number of active parking spaces and a preset manual capacity value parameter.

The manual capability value parameter is used to represent the number of the check-in/out event data that a single person should have in a preset time period, and is 400 as an example. The active parking space number N2 is equal to the parking space number of the event data generated in the preset time length, and the active parking space number is less than or equal to the total parking space number N1. It should be noted that, when a vehicle is parked in a parking space or drives out of the parking space, an event data is generated correspondingly in the parking space. Optionally, the target parking space number M1=400 × n 2/(a-B) managed by a single person within a preset time period.

S404, determining whether the automatic checking capability of the checking device is abnormal or not according to the preset parking stall number demand threshold and the target parking stall number of the single manual management device.

The parking space number demand threshold value M2 of the single manual management is a preset demand value, and if the calculated target parking space number M1 is larger than M2, the parking space number of the manual management is larger than the demand value, namely, the automatic auditing capability of the auditing equipment does not reach the standard, so that the automatic auditing capability of the auditing equipment is abnormal. It should be noted here that the stronger the automatic auditing capability of the auditing device is, the fewer events need to be audited manually, and the fewer parking spaces need to be managed manually.

In the embodiment of the disclosure, through performing statistical analysis on the in/out-of-position events, whether the automatic auditing capability of the auditing equipment is abnormal or not can be accurately judged.

Furthermore, the process of auditing the in/out-of-position events by auditing equipment is performed in steps, each step corresponds to one reason code, and for any step, if the condition of the step cannot be judged whether the event meets the condition of the step, the reason code corresponding to the step is fed back to the data center platform. Namely, the data center platform obtains the reason code fed back by the auditing equipment because the in/out-of-position event cannot be automatically audited; wherein the reason code is used for indicating a position where the automatic audit service cannot make an automatic determination. Furthermore, when the automatic auditing capability of the auditing platform is abnormal, the reason code and the information of the abnormal automatic auditing capability are reported, so that a responsible person can understand the direction needing to be adjusted simply and clearly according to the reason code.

Furthermore, after the target parking space number managed by a single person within the preset time length is determined, the required number of the persons can be calculated according to the total number of the parking spaces and the target parking space number; therefore, the parking management system can be rapidly informed of the manual work arrangement, and the stable operation of the parking management system can be ensured.

Further, according to the manual examination passing, the manual license plate modification passing and the manual examination of the abandoned in/out-of-position events, the number of the events of the manual actual examination of the in/out-of-position events in the preset time length is determined; and determining whether the manual auditing efficiency is abnormal or not according to the number of the events of the entry/exit events which are actually audited manually within the preset time length and the number of the events of the entry/exit events which need to be audited manually within the preset time length. Therefore, whether the manual ability reaches the standard can be judged.

Fig. 5 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present disclosure, which is applicable to a situation where an abnormal problem existing in a parking system is discovered by using an entry/exit event and an audit result thereof stored on a data center platform. Referring to fig. 5, the apparatus includes:

an obtaining module 501, configured to obtain an entry/exit event uploaded by a front-end device and an audit result of the entry/exit event fed back by an audit device;

an abnormal problem determination module 502, configured to determine an abnormal problem existing in the front-end device or the auditing device according to the in/out event of the at least one auditing result.

On the basis of the above embodiment, optionally, the audit result of the in/out-of-place event is at least one of automatic audit pass, automatic audit discard, manual audit pass, manual license plate modification pass, and manual audit discard.

On the basis of the foregoing embodiment, optionally, the abnormal problem determining module is further configured to:

aiming at an entry/exit event of manually modifying the passing of a license plate, license plate identification is carried out on an original image captured by front-end equipment and included in the entry/exit event through license plate iteration service to obtain a target license plate number;

comparing the similarity of the target license plate number with the manually modified license plate number included in the in/out-of-position event;

and if the similarity is greater than a preset threshold value, determining that the license plate recognition model in the front-end equipment has the problem of abnormal recognition effect.

On the basis of the foregoing embodiment, optionally, the method further includes:

the sample construction module is used for constructing a training sample of the license plate recognition model according to the original image and the license plate number after manual modification, and adding the training sample into a sample library;

and the iterative training module is used for performing iterative training on the license plate recognition model when the number of the training samples in the sample library is greater than a preset number threshold, and redeploying the trained license plate recognition model in the front-end equipment.

On the basis of the foregoing embodiment, optionally, the abnormal problem determination module is further configured to:

according to the entrance/exit events of different auditing results associated with the front-end equipment, determining the turnover rate or the abandonment rate of the parking space within a preset time length;

judging whether the turnover rate or the abandonment rate of the parking space is abnormal or not;

if yes, acquiring a current scene graph acquired by the front-end equipment, and detecting a parking space line in the current scene graph;

comparing the parking space line in the current scene graph with the parking space line in the standard scene graph corresponding to the front-end equipment; the standard scene graph is a scene graph collected when the front-end equipment is installed;

and judging whether the front-end equipment has abnormal lens shift according to the comparison result.

the first detection module is used for carrying out obstacle segmentation detection on the current scene graph to obtain a first obstacle mask if the front-end equipment does not have lens offset abnormality;

the second detection module is used for carrying out obstacle segmentation detection on the standard scene graph to obtain a second obstacle mask;

and the abnormity determining module is used for determining whether the front-end equipment has obstacle shielding abnormity according to the first obstacle mask and the second obstacle mask.

and the third detection module is used for carrying out fuzzy detection on the current scene graph and judging whether the front-end equipment has image fuzzy abnormity according to the detection result.

determining the number of the events of the in/out-of-position events needing manual examination in the preset time length according to the number of the events of the in/out-of-position events generated in the preset time length and the number of the events of the in/out-of-position events which are automatically examined in the preset time length;

determining the number of target parking spaces managed by a single person within a preset time according to the number of events, the number of active parking spaces and a preset manual capacity value parameter;

and determining whether the automatic auditing capability of the auditing equipment is abnormal or not according to a preset parking stall number demand threshold and a target parking stall number which are manually managed individually.

On the basis of the above embodiment, optionally, the method further includes:

the reason code acquisition module is used for acquiring reason codes fed back by the auditing equipment due to the fact that the entry/exit events cannot be automatically audited;

and the reporting module is used for reporting the reason codes and the information of the abnormal automatic audit capability when the automatic audit capability of the audit platform is abnormal.

On the basis of the above embodiment, optionally, the method further includes:

the number calculating module is used for calculating the required number of workers according to the total number of the parking spaces and the number of the target parking spaces;

the calculation module is used for determining the number of the events of the entry/departure events which are manually and actually checked within preset time according to the manual checking pass, the manual license plate modification pass and the manual checking of the abandoned entry/departure events;

and the manual efficiency abnormity detection module is used for determining whether the manual checking efficiency abnormity exists according to the number of the events of the entry/exit events which are manually and actually checked in the preset time length and the number of the events of the entry/exit events which need to be manually checked in the preset time length.

The data processing device provided by the embodiment of the disclosure can execute the data processing method provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method. Reference may be made to the description of any method embodiment of the disclosure for a matter not explicitly described in this embodiment.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, and the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 executes the respective methods and processes described above, such as the data processing method. For example, in some embodiments, the data processing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM602 and/or the communication unit 609. When the computer program is loaded into the RAM603 and executed by the computing unit 601, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the data processing method by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method of data processing, comprising:

acquiring an in/out-of-position event uploaded by front-end equipment and an auditing result of the in/out-of-position event fed back by auditing equipment;

2. The method of claim 1, wherein the audit result of the in/out event is at least one of an automatic audit pass, an automatic audit reject, a manual audit pass, a manual license plate modification pass, and a manual audit reject.

3. The method of claim 2, wherein the determining the abnormal problem of the front-end equipment according to the in/out-of-position event of at least one audit result comprises:

aiming at an entry/departure event that a license plate is manually modified to pass through, license plate identification is carried out on an original image captured by the front-end equipment and included in the entry/departure event through license plate iteration service, and a target license plate number is obtained;

comparing the similarity of the target license plate number and the manually modified license plate number included in the in/out-of-position event;

4. The method of claim 3, further comprising:

constructing a training sample of the license plate recognition model according to the original image and the manually modified license plate number, and adding the training sample into a sample library;

and when the number of the training samples in the sample library is larger than a preset number threshold, performing iterative training on the license plate recognition model, and redeploying the trained license plate recognition model in the front-end equipment.

5. The method of claim 2, wherein the determining the abnormal problem of the front-end equipment according to the in/out-of-position event of at least one audit result comprises:

and judging whether the front-end equipment has abnormal lens shift or not according to the comparison result.

6. The method of claim 5, further comprising:

if the front-end equipment has no lens offset abnormality, performing obstacle segmentation detection on the current scene graph to obtain a first obstacle mask;

performing obstacle segmentation detection on the standard scene graph to obtain a second obstacle mask;

and determining whether the front-end equipment has obstacle shielding abnormity according to the first obstacle mask and the second obstacle mask.

7. The method of claim 6, further comprising:

and carrying out fuzzy detection on the current scene graph, and judging whether the front-end equipment has image fuzzy abnormity according to a detection result.

8. The method of claim 2, wherein determining an abnormal problem with the auditing device based on an in/out-of-place event of at least one audit result comprises:

determining the number of the events of the entry/exit events needing manual examination in the preset time length according to the number of the events of the entry/exit events generated in the preset time length and the number of the events of the entry/exit events automatically examined in the preset time length;

and determining whether the automatic auditing capability of the auditing equipment is abnormal or not according to a preset parking space number demand threshold value of single manual management and the target parking space number.

9. The method of claim 8, further comprising:

acquiring reason codes fed back by the auditing equipment due to the fact that the auditing equipment cannot automatically audit the in/out-of-position events;

and when the automatic auditing capability of the auditing platform is abnormal, reporting the reason code and the information of the abnormal automatic auditing capability.

10. The method of claim 8, further comprising:

calculating the required manual number according to the total number of the parking places and the target parking number;

determining the number of events of the manual actual checking entry/exit events within preset time according to the manual checking pass, the manual license plate modification pass and the manual checking of the abandoned entry/exit events;

and determining whether the manual auditing efficiency is abnormal or not according to the number of the events of the entry/exit events which are actually audited manually within the preset time length and the number of the events of the entry/exit events which need to be audited manually within the preset time length.

11. A data processing apparatus comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring an entry/departure event uploaded by front-end equipment and an audit result of the entry/departure event fed back by audit equipment;

and the abnormal problem determining module is used for determining the abnormal problem existing in the front-end equipment or the auditing equipment according to the in/out-of-position event of at least one auditing result.

12. The apparatus of claim 11, wherein the audit result of the in/out event is at least one of an automatic audit pass, an automatic audit discard, a manual audit pass, a manual modified license plate pass, and a manual audit discard.

13. The apparatus of claim 12, wherein the abnormal problem determination module is further configured to:

14. The apparatus of claim 13, further comprising:

the sample construction module is used for constructing a training sample of the license plate recognition model according to the original image and the manually modified license plate number, and adding the training sample into a sample library;

and the iterative training module is used for performing iterative training on the license plate recognition model when the number of training samples in the sample library is greater than a preset number threshold, and redeploying the trained license plate recognition model in the front-end equipment.

15. The apparatus of claim 12, wherein the abnormal issue determination module is further configured to:

16. The apparatus of claim 15, further comprising:

the first detection module is used for carrying out obstacle segmentation detection on the current scene graph to obtain a first obstacle mask if the front-end equipment has no abnormal lens shift;

17. The apparatus of claim 16, further comprising:

and the third detection module is used for carrying out fuzzy detection on the current scene graph and judging whether the front-end equipment has image fuzzy abnormality or not according to a detection result.

18. The apparatus of claim 12, wherein the abnormal problem determination module is further configured to:

19. The apparatus of claim 18, further comprising:

the reason code acquisition module is used for acquiring the reason code fed back by the auditing equipment due to the fact that the entry/exit event cannot be automatically audited;

20. The apparatus of claim 18, further comprising:

the number calculating module is used for calculating the required number of workers according to the total number of the parking places and the target parking number;

21. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the data processing method of any one of claims 1-10.

22. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the data processing method according to any one of claims 1 to 10.

23. A computer program product comprising a computer program which, when executed by a processor, implements a data processing method according to any one of claims 1-10.