Early warning sorting method, device, equipment, medium and product

Abstract

The invention discloses an early warning sorting method, device and equipment, a medium and a product, and relates to the technical field of intelligent driving. Receiving early warning information sent by the target vehicle; determining a target early warning identifier and a target weight value from an abnormal behavior library based on the environment data and an early warning rule; the abnormal behavior library comprises an early warning identifier and a weight value corresponding to the early warning identifier; associating the target early warning identifier and the target weight and storing the target early warning identifier and the target weight in the abnormal behavior library; and sorting the at least one early warning identifier in the abnormal behavior library based on the target weight value. According to the technical scheme, the early warning identifiers and the weight values corresponding to the early warning information are determined through the constructed abnormal behavior library and the early warning rules, the early warning identifiers are ranked, the early warning information is intelligently ranked in real time, and the problem that existing first-level early warning information cannot be displayed according to the danger degree is solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to a method, apparatus, device, medium, and product for early warning sequencing. Background Technology

[0002] With the development of intelligent driving technology, a great many technologies in terms of safety and comfort have emerged; users are becoming more aware of and demanding of intelligent technologies.

[0003] The existing Sentry Mode uses the vehicle's surround-view or side-view cameras and various sensors to help owners monitor the vehicle's surroundings after the vehicle is locked. When someone approaches, touches, or even vandalizes or damages the vehicle, Sentry Mode can intelligently record these suspicious individuals and notify the owner via a mobile app linked to the vehicle. The Level 1 alarm in Sentry Mode detects suspicious individuals passing by or loitering within a very close range of the vehicle, or suspicious individuals touching or attempting to open the vehicle's four doors and two hoods. However, not all alarm videos at Level 1 are dangerous, and the proportion of videos that actually pose a danger is relatively low.

[0004] Therefore, there is an urgent need for an early warning ranking method to solve the problem of intelligently ranking the severity of first-level alarms. Summary of the Invention

[0005] This invention provides a method, apparatus, device, medium, and product for sorting early warning information, which solves the problem that existing first-level early warning information cannot be displayed according to the degree of danger. By constructing an abnormal behavior database and early warning rules, the invention determines the early warning identifier and weight value corresponding to each early warning information, sorts each early warning identifier, and performs intelligent sorting of early warning information in real time.

[0006] According to one aspect of the present invention, an early warning sorting method is provided, comprising:

[0007] Receive warning information sent by the target vehicle; the warning information includes the warning level and environmental data;

[0008] Based on the environmental data and early warning rules, target early warning identifiers and target weight values ​​are determined from the abnormal behavior database; the abnormal behavior database includes early warning identifiers and the corresponding weight values ​​of the early warning identifiers.

[0009] The target warning identifier and the target weight are associated and stored in the abnormal behavior database;

[0010] At least one warning identifier in the abnormal behavior database is sorted based on the target weight value.

[0011] According to another aspect of the present invention, an early warning sorting device is provided, comprising:

[0012] A receiving module is used to receive warning information sent by the target vehicle; the warning information includes the warning level and environmental data.

[0013] The determination module is used to determine the target warning identifier and the target weight value from the abnormal behavior database based on the environmental data and the warning rules; the abnormal behavior database includes warning identifiers and the weight values ​​corresponding to the warning identifiers;

[0014] The storage module is used to associate and store the target warning identifier and the target weight in the abnormal behavior database;

[0015] The sorting module is used to sort at least one warning identifier in the abnormal behavior database based on a target weight value.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the early warning sorting method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the early warning sorting method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the early warning sorting method according to any embodiment of the present invention.

[0022] This invention, through the construction of an abnormal behavior database and early warning rules, determines the early warning identifier and weight value corresponding to each early warning information, sorts each early warning identifier, and intelligently sorts the early warning information in real time, thus solving the problem that existing first-level early warning information cannot be displayed according to the degree of danger.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of an early warning sorting method provided according to an embodiment of the present invention;

[0026] Figure 2 This is a flowchart of an early warning sorting method provided according to an embodiment of the present invention;

[0027] Figure 3 This is a flowchart of a method for determining a target early warning identifier and a first weight value according to an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of an early warning sorting device according to an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the early warning sorting method of this invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Furthermore, it should be noted that the information collected in the technical solution of this invention is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data all comply with the relevant laws, regulations and standards of relevant countries and regions, necessary confidentiality measures have been taken, and public order and good morals are not violated. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0033] Figure 1 This is a flowchart of a warning sorting method provided by an embodiment of the present invention. This embodiment is applicable to situations where warnings are issued for the environment surrounding parked vehicles, and is particularly suitable for displaying vehicle warning information. The method can be executed by the warning sorting device provided by this embodiment, which can be implemented in hardware and / or software and can be configured in a server. Figure 1 As shown, the method includes:

[0034] S110: Receive warning information sent by the target vehicle; the warning information includes the warning level and environmental data.

[0035] The target vehicle is a parked vehicle with the sentry mode activated; the warning level is the level in sentry mode, which can be level one or level two. For example, it can sense the distance, movement status and duration of nearby moving obstacles such as people and animals. When a suspicious obstacle is close and stays for a period of time; or when the vehicle's four doors and two hoods sense suspicious behavior such as touching or attempting to unlock, a level one alarm will be triggered; if the vehicle senses violent vibrations or illegal opening of the four doors and two hoods, a level two alarm will be triggered; the environmental data can be various images of the surrounding environment captured by onboard sensors or 360-degree holographic imaging.

[0036] Specifically, it receives the warning information corresponding to the Level 1 warning of the target vehicle in Sentinel mode, including the warning level when the warning was triggered and the surrounding environmental data.

[0037] S120. Based on environmental data and early warning rules, determine the target early warning identifier and target weight value from the abnormal behavior database; the abnormal behavior database includes early warning identifiers and the corresponding weight values ​​of the early warning identifiers.

[0038] The warning rules are rules for the weight values ​​corresponding to the current warning information calculated based on environmental data; the abnormal behavior database is pre-built and stores the behavioral characteristics of each target object that triggers a level 1 or level 2 alarm, as well as the warning score value corresponding to that target object; the target warning identifier is used to distinguish the target object in each warning information; the target weight value can represent the warning score of the target object, which is used to clarify the degree of danger corresponding to each warning information; the warning identifier is used to distinguish different objects and may include the behavioral characteristics corresponding to the target object in the warning information.

[0039] Specifically, based on the calculation rules of environmental data and weight values, the target early warning identifier and target weight value corresponding to this environmental data are determined from the abnormal behavior database.

[0040] In an optional embodiment of the present invention, if the target object corresponding to the environmental data is not stored in the abnormal behavior database, the target warning identifier and target weight value corresponding to the environmental data are obtained only according to the calculation rules of the environmental data and weight value.

[0041] It is understandable that by setting up an abnormal behavior database to store the weight values ​​corresponding to the warning information, the danger level of the warning information can be intelligently sorted and determined.

[0042] S130. Associate the target warning identifier and the target weight value and store them in the abnormal behavior database.

[0043] Specifically, the warning identifier and weight value corresponding to the warning information obtained according to the warning rules will be associated and stored in the abnormal behavior database so that the abnormal behavior database can be updated in real time according to the triggered warning information.

[0044] S140. Sort at least one warning identifier in the abnormal behavior database based on the target weight value.

[0045] The sorting can be done by sorting according to the size of the weight value.

[0046] Specifically, each warning sign is sorted according to the weight value stored in the abnormal behavior database, with the larger weight value sorted first and the smaller weight value sorted last, so that the user of the target vehicle can quickly locate the target based on the sorting, and further realize the traceability of the warning.

[0047] Optionally, it also includes: if the warning level is level two, then the warning identifier is determined based on the environmental data of the warning information;

[0048] The warning identifiers are sorted based on the time of the warning information.

[0049] The time of each warning message is the timestamp when it was triggered.

[0050] Specifically, if the warning level is level two, since level two alarms all involve serious destructive behavior, there is no need to score the degree of danger. Instead, the target object and its behavioral characteristics are determined by analyzing the environmental data of the warning information. These behavioral characteristics are then used as warning identifiers, and the warning identifiers can be sorted according to the timestamps of each warning information.

[0051] Understandably, sorting the warning information of Level 2 alerts by timestamps further ensures the traceability of Level 2 alarm information and improves the user experience.

[0052] This invention addresses the problem of existing level-one warning information not being displayed according to the degree of danger by receiving warning information sent by a target vehicle, including warning level and environmental data, determining target warning identifiers and target weight values ​​from an abnormal behavior database based on the environmental data and warning rules, and associating and storing the target warning identifiers and target weights in the database. The invention also sorts at least one warning identifier in the target abnormal behavior database based on the target weight value. This technical solution, through the constructed abnormal behavior database and warning rules, determines the warning identifiers and weight values ​​corresponding to each warning message and sorts the warning identifiers, providing real-time intelligent sorting of warning information and solving the problem that existing level-one warning information cannot be displayed according to the degree of danger.

[0053] Figure 2 This is a flowchart of an early warning ranking method according to an embodiment of the present invention. Based on the above embodiments, this embodiment supplements the specific determination method of the target early warning identifier and the target weight value. It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 2 As shown, the method includes:

[0054] S210, Receive warning information sent by the target vehicle; the warning information includes the warning level and environmental data.

[0055] S220. Determine the target early warning identifier and the first weight value based on environmental data and early warning rules.

[0056] The first weight value is the hazard score corresponding to the current environmental data.

[0057] Specifically, the target early warning identifier and the corresponding first weight value are determined based on environmental data and early warning rules.

[0058] Optional, such as Figure 3 The method for determining a target early warning identifier and a first weight value, as shown, includes:

[0059] S221. Find at least one candidate image frame with the target object from the environmental data.

[0060] The target object is an obstacle object appearing in the environmental data, which can be a person or at least one target object; the candidate image frame is an image containing the target object.

[0061] Specifically, at least one candidate image frame containing the obstacle object is found from the video image frames captured that triggered this warning.

[0062] S222. Preprocess the candidate image frames to determine the target image frame and the target distance.

[0063] The preprocessing involves grayscale processing and distance calculation of candidate image frames; the target image frame can be the image frame closest to the target object and the target vehicle; the target distance is the distance between the target object and the target vehicle.

[0064] Specifically, grayscale processing and distance calculation are performed on candidate image frames to determine the distance between the target object and the target vehicle in the candidate image frames; and the candidate image frame with the closest distance between the target object and the target vehicle is selected as the target image frame based on the distance.

[0065] Optionally, the candidate image frames are preprocessed to determine the target image frame and the target distance, including:

[0066] Feature extraction is performed on candidate image frames to obtain the image features of the target object;

[0067] Determine the candidate distance of the target object based on candidate image frames and image features;

[0068] Select the smallest candidate distance from the candidate distances as the target distance;

[0069] The candidate image frame corresponding to the target distance is then used as the target image frame.

[0070] The image features include those of the target object, such as histogram features, color features, template features, structural features, and Haar features. The candidate distance is the distance between the target object and the target vehicle, which can be determined by using an object of known size in the image as a reference or by end-to-end ranging through a monocular depth estimation network. It should be noted that the specific distance between the target object and the target vehicle can be calculated using existing computer vision algorithms, sensor data, and geometric principles. This embodiment of the invention does not impose specific limitations on this, and those skilled in the art can design and select the appropriate method based on actual needs.

[0071] Specifically, feature extraction is performed on candidate image frames to obtain image features of the target object, such as histogram features, color features, template features, structural features, and Haar features; based on the candidate image frames and image features, the candidate distance between the target object and the target vehicle corresponding to each candidate image frame is determined; the smallest candidate distance is taken as the target distance; and the candidate image frame corresponding to the target distance is taken as the target image frame.

[0072] Understandably, by using the candidate image frame closest to the target vehicle as the target image frame, the behavioral characteristics of the target object can be accurately and clearly obtained subsequently, so as to achieve accurate identification of suspicious persons in the warning information and precise determination of the degree of danger.

[0073] S223. Extract features from the target image frame to obtain the behavioral features of the target object.

[0074] The behavioral characteristics of the target object can include its visual features, pixel statistical features, image transform coefficient features, and image algebraic features.

[0075] Specifically, feature extraction is performed on the target image frame to obtain the behavioral features of the target object. It should be noted that the feature vector method or the surface texture template method can be used to identify the behavioral features of the target object, and the embodiments of the present invention do not specifically limit this.

[0076] S224. Perform a hash operation on the behavioral characteristics to obtain a hash value, and use the hash value as the target warning identifier for the target object.

[0077] Specifically, the behavioral characteristics are hashed to obtain hash values, which are then stored as target warning identifiers for the target objects.

[0078] Understandably, by performing hash operations on behavioral characteristics, retaining the hash value, and automatically erasing the original data, the privacy of the target object is guaranteed, and the leakage of the original data is avoided.

[0079] S225. Determine the first weight value based on the early warning rules and target distance.

[0080] Specifically, the first weight value corresponding to the warning information is obtained by calculating the warning rule's formula and the target distance. The formula for calculating the first weight value is as follows:

[0081]

[0082] Where x is the target object; The first weight value of the target object in the current period; The target distance.

[0083] In an optional embodiment of the present invention, the weight value of the target object at the level of Level 2 warning does not need to be calculated and can be directly set to a fixed weight value, such as 5. The warning identifier and fixed weight value corresponding to the Level 2 warning can also be stored in an abnormal behavior database to determine the final target weight value. It should be noted that the embodiments of the present invention do not limit the fixed weight value for Level 2 warnings; those skilled in the art can set it according to actual needs.

[0084] Understandably, the danger score of the warning information is calculated by measuring the distance between the target object and the target vehicle. This standardizes the danger level corresponding to a Level 1 alarm when the target object and the target vehicle are not in contact. The farther the target object and the target vehicle are, the lower the first weight value. When the target object and the target vehicle are in contact, i.e., the distance is zero, the first weight value is the highest. This further improves the fine-grained differentiation of the danger level under a Level 1 alarm, ensuring timely alarm processing for subsequent users of the target vehicle.

[0085] S230. Based on the target warning identifier, search for the corresponding second weight value from the abnormal behavior database.

[0086] The second weight value is the weight score corresponding to the warning identifier in the abnormal behavior database, which can be the weight score of the previous period of the current period.

[0087] Specifically, the system checks whether the target warning identifier exists in the abnormal behavior database. If the target warning identifier exists in the abnormal behavior database, its corresponding weight value is used as the second weight value.

[0088] Optionally, a second weight value can be retrieved from the abnormal behavior database based on the target warning identifier, including:

[0089] The target warning identifiers are analyzed to obtain the behavioral characteristics of the target object;

[0090] The similarity between the behavioral features and historical behavioral features in the abnormal behavior database is calculated to obtain at least one candidate similarity.

[0091] If a candidate similarity exceeds the similarity threshold, the candidate similarity is used as the target similarity.

[0092] Determine the corresponding historical behavioral characteristics of the target based on the target similarity;

[0093] The weight value corresponding to the target's historical behavioral characteristics is used as the second weight value.

[0094] Among them, historical behavior features are the behavior features corresponding to each warning icon in the abnormal behavior database; similarity calculation is to match the behavior features with historical behavior features.

[0095] Specifically, the target warning identifier is parsed to obtain the behavioral characteristics of the target object; the behavioral characteristics are matched with the historical behavioral characteristics in the abnormal behavior database to obtain at least one candidate similarity; if there is a candidate similarity exceeding the similarity threshold, the candidate similarity is used as the target similarity; and the corresponding historical behavioral characteristics of the target are determined based on the target similarity; the weight value corresponding to the historical behavioral characteristics of the target is used as the second weight value.

[0096] S240. Determine the target weight value based on the first weight value and the second weight value.

[0097] The target weight value is the danger score corresponding to the warning label of the target object.

[0098] Specifically, the target weight value is obtained by summing the first weight value and the second weight value. The formula for calculating the target weight value is as follows:

[0099]

[0100] in, The target weight value; This is the second weight value.

[0101] S250. Associate the target warning identifier and the target weight value and store them in the abnormal behavior database.

[0102] Specifically, the target warning identifier is associated with the corresponding target weight value on a one-to-one basis and stored in the abnormal behavior database.

[0103] S260. Sort at least one warning identifier in the abnormal behavior database based on the target weight value.

[0104] This invention processes environmental data corresponding to early warning information using early warning rules to obtain early warning identifiers for target objects. It then calculates the weight value of the target object by combining the weight value of the early warning identifier with an abnormal behavior database. This links the danger level in the first-level alarm with the weight value and combines historical weight values ​​from the historical abnormal behavior database to accurately identify and calculate the danger value of the target object. This achieves accurate identification of target objects under the first-level early warning, ensuring that vehicle users can promptly view the target object and the degree of danger and take appropriate alarm actions.

[0105] Figure 4This is a schematic diagram of a warning sorting device according to an embodiment of the present invention. This embodiment is applicable to situations where warnings are issued for the environment surrounding parked vehicles, and is particularly suitable for displaying vehicle warning information. The warning sorting device can be implemented in hardware and / or software and can be configured in a server. The warning sorting device 300 includes a receiving module 310, a determining module 320, a storage module 330, and a sorting module 340.

[0106] The receiving module 310 is used to receive warning information sent by the target vehicle; the warning information includes the warning level and environmental data.

[0107] The determination module 320 is used to determine the target warning identifier and target weight value from the abnormal behavior database based on environmental data and warning rules; the abnormal behavior database includes warning identifiers and the corresponding weight values ​​of the warning identifiers;

[0108] Storage module 330 is used to associate and store target warning identifiers and target weights in the abnormal behavior database;

[0109] The sorting module 340 is used to sort at least one warning identifier in the abnormal behavior database based on the target weight value.

[0110] This invention addresses the problem of receiving warning information from a target vehicle. The warning information includes a warning level and environmental data. Based on the environmental data and warning rules, a target warning identifier and target weight value are determined from an abnormal behavior database. The abnormal behavior database includes warning identifiers, corresponding behavioral characteristics, and corresponding weight values. The target warning identifiers and target weights are associated and stored in the abnormal behavior database. At least one warning identifier in the target abnormal behavior database is then sorted based on its target weight value. This technical solution, by constructing an abnormal behavior database and warning rules to determine the warning identifier and weight value corresponding to each warning message and sorting the warning identifiers, intelligently sorts the warning information in real time, solving the problem that existing level-one warning information cannot be displayed according to its degree of danger.

[0111] Optionally, the determining module 320 includes a determining unit, a second weight value determining unit, and a target weight value determining unit;

[0112] The determination unit is used to determine the target early warning identifier and the first weight value based on environmental data and early warning rules;

[0113] The second weight value determination unit is used to find the corresponding second weight value from the abnormal behavior database based on the target early warning identifier;

[0114] The target weight value determination unit is used to determine the target weight value based on the first weight value and the second weight value.

[0115] Optionally, the determining unit is also used to search for at least one candidate image frame with the target object from the environmental data based on the early warning rules;

[0116] Candidate image frames are preprocessed to determine the target image frame and the distance to the target;

[0117] Feature extraction is performed on the target image frame to obtain the behavioral features of the target object;

[0118] The behavioral characteristics are hashed to obtain hash values, which are then used as target warning identifiers for the target objects.

[0119] The target weight is determined by the early warning rules and the target distance.

[0120] Optionally, the determining unit is also used to extract features from candidate image frames to obtain image features of the target object;

[0121] Determine the candidate distance of the target object based on candidate image frames and image features;

[0122] Select the smallest candidate distance from the candidate distances as the target distance;

[0123] The candidate image frame corresponding to the target distance is then used as the target image frame.

[0124] Optionally, the second weight value determination unit is also used to parse the target warning label to obtain the behavioral characteristics of the target object;

[0125] The similarity between the behavioral features and historical behavioral features in the abnormal behavior database is calculated to obtain at least one candidate similarity.

[0126] If a candidate similarity exceeds the threshold, the candidate similarity will be used as the target similarity.

[0127] Determine the corresponding historical behavioral characteristics of the target based on the target similarity;

[0128] The weight value corresponding to the target's historical behavioral characteristics is used as the second weight value.

[0129] Optionally, the early warning sorting device 300 also includes a secondary sorting module, which is used to determine the early warning identifier based on the environmental data of the early warning information if the early warning level is level two.

[0130] The warning identifiers are sorted based on the time of the warning information.

[0131] The early warning sorting device provided in the embodiments of the present invention can execute the early warning sorting method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0132] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0133] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0134] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0135] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0136] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the alert sorting method.

[0137] In some embodiments, the warning sorting method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the warning sorting method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the warning sorting method by any other suitable means (e.g., by means of firmware).

[0138] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0139] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0140] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0141] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the 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 can be received in any form (including sound input, voice input, or tactile input).

[0142] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0143] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system. This addresses the shortcomings of traditional physical hosts and dedicated virtual services, such as high management difficulty and weak business scalability.

[0144] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0145] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for early warning sorting, characterized in that, include: Receive warning information sent by the target vehicle; The early warning information includes the early warning level and environmental data; Based on the environmental data and early warning rules, target early warning identifiers and target weight values ​​are determined from the abnormal behavior database; the abnormal behavior database includes early warning identifiers and the corresponding weight values ​​of the early warning identifiers. The target warning identifier and the target weight are associated and stored in the abnormal behavior database; At least one warning identifier in the abnormal behavior database is sorted based on the target weight value.

2. The method according to claim 1, characterized in that, The step of determining the target warning identifier and target weight value from the abnormal behavior database based on the environmental data and warning rules includes: Based on the environmental data and early warning rules, a target early warning identifier and a first weight value are determined; The corresponding second weight value is searched from the abnormal behavior database based on the target early warning identifier; The target weight value is determined based on the first weight value and the second weight value.

3. The method according to claim 2, characterized in that, The process of determining the target early warning identifier and the first weight value based on the environmental data and early warning rules includes: Find at least one candidate image frame containing the target object from the environmental data; The candidate image frames are preprocessed to determine the target image frame and the target distance; Feature extraction is performed on the target image frame to obtain the behavioral features of the target object; The behavioral characteristics are hashed to obtain a hash value, and the hash value is used as the target warning identifier for the target object. The first weight value is determined by the warning rule and the target distance.

4. The method according to claim 3, characterized in that, The preprocessing of the candidate image frames to determine the target image frame and the target distance includes: Feature extraction is performed on the candidate image frames to obtain the image features of the target object; Based on the candidate image frames and the image features, determine the candidate distance of the target object; The smallest candidate distance is selected from the candidate distances as the target distance; The candidate image frame to which the target distance belongs is then taken as the target image frame.

5. The method according to claim 2, characterized in that, The step of searching for the corresponding second weight value from the abnormal behavior database based on the target early warning identifier includes: The target warning identifier is parsed to obtain the behavioral characteristics of the target object; The similarity between the behavioral features and historical behavioral features in the abnormal behavior database is calculated to obtain at least one candidate similarity. If a candidate similarity exceeds the threshold, then the candidate similarity is taken as the target similarity. The corresponding historical behavioral features of the target are determined based on the target similarity. The weight value corresponding to the target's historical behavior features is used as the second weight value.

6. The method according to claim 1, characterized in that, Also includes: If the warning level is level two, then the warning identifier is determined based on the environmental data of the warning information; The warning identifiers are sorted based on the time of the warning information.

7. A pre-warning sorting device, characterized in that, include: The receiving module is used to receive warning information sent by the target vehicle; The early warning information includes the early warning level and environmental data; The determination module is used to determine a target warning identifier and a target weight value from the abnormal behavior database based on the environmental data and warning rules; the abnormal behavior database includes warning identifiers, behavioral features corresponding to the warning identifiers, and weight values ​​corresponding to the warning identifiers; The storage module is used to associate and store the target warning identifier and the target weight in the abnormal behavior database; The sorting module is used to sort at least one warning identifier in the abnormal behavior database based on the target weight value.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the early warning sorting method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the early warning sorting method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the early warning sorting method according to any one of claims 1-6.

Images