Traffic violation processing method, electronic device, and program product

Abstract

The disclosure provides a traffic violation processing method, an electronic device and a program product, and relates to the technical field of computers. The method comprises the following steps: determining a penalty matter and identity information of a person to be punished according to a received fine generation request; obtaining a traffic behavior record corresponding to the identity information, wherein the traffic behavior record comprises a violation record and a snapshot record of a traffic behavior; generating a violation prediction result corresponding to the person to be punished according to the violation record and the snapshot record, wherein the violation prediction result is used to represent the possibility of the person to be punished violating again; generating a safety propaganda report for the person to be punished according to the violation prediction result, the violation record and the snapshot record; and superimposing access address information of the safety propaganda report on a traffic violation fine generated based on the penalty matter to generate a target traffic violation fine for the person to be punished. The technical scheme of the embodiment of the disclosure can improve the law enforcement efficiency and ensure the safety propaganda and education effect.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computers, in particular to a traffic violation processing method, an electronic device and a program product. BACKGROUND

[0002] With the acceleration of urbanization, the management of non-motor vehicle violations is facing the challenge of insufficient efficiency and intelligence. In the current technical solution, the processing of traffic violations of non-motor vehicles mainly relies on manual operation of law enforcement personnel, such as recording fine information, querying historical violation data, etc., resulting in a long time for on-site law enforcement. Due to the generalization of the content of traffic violation propaganda and education, the propaganda and education lack pertinence and weaken the educational effect. SUMMARY

[0003] The present disclosure provides a traffic violation processing method, an electronic device and a program product.

[0004] According to one aspect of the present disclosure, a traffic violation processing method is provided, comprising: determining a penalty matter and identity information of a to-be-penalized person according to a received fine generation request; obtaining a traffic behavior record corresponding to the identity information, the traffic behavior record comprising a violation record and a snapshot record of a traffic behavior; generating a violation prediction result corresponding to the to-be-penalized person according to the violation record and the snapshot record, the violation prediction result being used to represent a possibility of the to-be-penalized person violating again; generating a safety propaganda report for the to-be-penalized person according to the violation prediction result, the violation record and the snapshot record; and superimposing access address information of the safety propaganda report on a traffic violation fine generated based on the penalty matter, to generate a target traffic violation fine for the to-be-penalized person.

[0005] According to the technical solution of one aspect, by determining a penalty matter and identity information of a to-be-penalized person according to a received fine generation request, obtaining a traffic behavior record corresponding to the identity information, the traffic behavior record comprising a violation record and a snapshot record of a traffic behavior. Then, generating a violation prediction result corresponding to the to-be-penalized person according to the violation record and the snapshot record, the violation prediction result being used to represent a possibility of the to-be-penalized person violating again. Then, generating a safety propaganda report for the to-be-penalized person according to the violation prediction result, the violation record and the snapshot record, and superimposing access address information of the safety propaganda report on a traffic violation fine generated based on the penalty matter, to generate a target traffic violation fine for the to-be-penalized person.

[0006] Thus, by automatically generating the target traffic violation fine corresponding to the to-be-penalized personnel, manual recording of the fine content by law enforcement personnel can be avoided, and law enforcement efficiency is improved. Moreover, according to the violation record and the snapshot record of the to-be-penalized personnel, the possibility of repeated violation of the to-be-penalized personnel is predicted, and then a corresponding safety propaganda report is generated, which can improve the pertinence of the safety propaganda report and ensure the propaganda and education effect.

[0007] In some embodiments of the present disclosure, according to the violation record and the snapshot record, the violation prediction result corresponding to the to-be-penalized personnel is generated, including: according to the violation record and the snapshot record, determining the number of violations and the number of compliance of the to-be-penalized personnel in an evaluation period, the number of violations being the number of times that the to-be-penalized personnel is caught violating the rules in the evaluation period, and the number of compliance being the number of times that the to-be-penalized personnel is caught but complies with the rules in the evaluation period; according to the number of violations and the number of compliance in the evaluation period, determining a violation score of the to-be-penalized personnel in the evaluation period, the violation score being used to represent the severity of the violation of the to-be-penalized personnel in the evaluation period; and according to the violation score of the evaluation period, generating the violation prediction result corresponding to the to-be-penalized personnel.

[0008] In some embodiments of the present disclosure, the violation score of the to-be-penalized personnel in the evaluation period is determined according to the following formula:

[0009] wherein WVS is the violation score of the to-be-penalized personnel in the evaluation period, PVM is the number of violations of the to-be-penalized personnel in the evaluation period, NM is the number of compliance of the to-be-penalized personnel in the evaluation period, VM is the number of violations of the to-be-penalized personnel in the evaluation period, and WC is a violation weight coefficient.

[0010] In some embodiments of the present disclosure, according to the violation score of the evaluation period, the violation prediction result corresponding to the to-be-penalized personnel is generated, including: performing outlier screening on the violation scores of a plurality of evaluation periods; according to the violation scores after screening, determining a violation growth trend of the to-be-penalized personnel; and according to the violation growth trend, generating the violation prediction result corresponding to the to-be-penalized personnel.

[0011] In some embodiments of the present disclosure, the outlier screening on the violation scores of a plurality of evaluation periods includes: filtering out data with a violation score less than 0 in a plurality of evaluation periods; and based on normal distribution screening, removing abnormal data with a probability outside 3σ from the violation scores after filtering, σ being a standard deviation calculated based on the violation scores after filtering.

[0012] In some embodiments of the present disclosure, the violation growth trend of the person to be punished is determined based on the violation score after screening, including: determining the logarithmic growth rate corresponding to the violation score of the evaluation period based on the violation score after screening, and the logarithmic growth rate is calculated relative to the violation score of the adjacent previous evaluation period; predicting the logarithmic growth rate corresponding to the target evaluation period based on the logarithmic growth rate corresponding to the violation score of the evaluation period; determining the violation growth trend corresponding to the target evaluation period based on the logarithmic growth rate corresponding to the target evaluation period.

[0013] In some embodiments of the present disclosure, the logarithmic growth rate corresponding to the target evaluation period is predicted based on the logarithmic growth rate corresponding to the violation score of the evaluation period, including: establishing a linear regression model based on the logarithmic growth rate corresponding to the violation score of the evaluation period, and obtaining the logarithmic growth rate corresponding to the target evaluation period output by the linear regression model.

[0014] In some embodiments of the present disclosure, a safety publicity report is generated for the person to be punished based on the violation prediction results, the violation records and the snapshot records, including: generating a safety publicity report for the person to be punished based on the violation prediction results, the violation records, the snapshot records and the violation type warning publicity knowledge base, the safety publicity report including violation type statistical information, key violation types and safety cases of the person to be punished.

[0015] In some embodiments of the present disclosure, the access address information of the safety publicity report is reflected in the target traffic violation ticket in the form of a QR code.

[0016] According to another aspect of the present disclosure, a traffic violation processing device is provided, including: a first determination module, used to determine the penalty matters and identity information of the person to be punished based on a received ticket generation request; an acquisition module, used to obtain traffic behavior records corresponding to the identity information, the traffic behavior records including violation records and snapshot records of the traffic behavior; a second determination module, used to generate a violation prediction result corresponding to the person to be punished based on the violation records and the snapshot records, the violation prediction result being used to characterize the possibility of the person to be punished violating the law again; a generation module, used to generate a safety publicity report for the person to be punished based on the violation prediction result, the violation records and the snapshot records; and a processing module, used to superimpose the access address information of the safety publicity report onto the traffic violation ticket generated based on the penalty matters, to generate a target traffic violation ticket for the person to be punished.

[0017] According to another aspect of the present disclosure, an electronic device is provided, comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, so that the processor executes the traffic violation handling method of any embodiment of the present disclosure.

[0018] According to another aspect of the present disclosure, a readable storage medium is provided, wherein the readable storage medium stores execution instructions, and when the execution instructions are executed by a processor, the method for handling traffic violations according to any embodiment of the present disclosure is used.

[0019] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the traffic violation processing method according to any embodiment of the present disclosure is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings illustrate exemplary embodiments of the present disclosure and together with the description serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0021] Figure 1 A schematic diagram showing an exemplary system architecture to which the technical solutions of the embodiments of the present disclosure can be applied is shown.

[0022] Figure 2 A flow chart of a method for handling traffic violations according to one embodiment of the present disclosure is shown.

[0023] Figure 3 A flow chart of step S230 in a method for handling traffic violations according to an embodiment of the present disclosure is shown.

[0024] Figure 4 A flow chart of step S233 in a method for handling traffic violations according to an embodiment of the present disclosure is shown.

[0025] Figure 5 A schematic diagram of an application scenario in which the technical solution of the embodiments of the present disclosure can be applied is shown.

[0026] Figure 6 A schematic structural block diagram of a traffic violation processing device according to one embodiment of the present disclosure is shown.

[0027] Figure 7 A schematic structural block diagram of an electronic device equipped with a traffic violation processing device according to one embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0028] The present disclosure is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are intended only to illustrate the relevant content and are not intended to limit the present disclosure. It should also be noted that, for ease of description, only the portions relevant to the present disclosure are shown in the accompanying drawings.

[0029] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure can be combined with each other. The technical solution of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] In current technology, the handling of non-motor vehicle violations primarily relies on on-site manual operations and database queries by law enforcement officers. Furthermore, the traffic management department's database serves only as a data repository, lacking efficient intelligent connectivity with on-site law enforcement. In principle, when law enforcement officers handle traffic violations, they are unable to quickly retrieve the violator's comprehensive historical violation information directly from the database and automatically incorporate it into the ticket.

[0031] For example, when handling a non-motor vehicle violation involving running a red light, law enforcement officers can only record information such as the time and location of the violation. To determine whether the individual has committed similar violations before and where they occurred, they must use a dedicated query system on a PC, input the offender's identity information, search the database, and manually organize the relevant information. Furthermore, if an analysis and summary of the violation is required, this can only be done manually. This process is not only inefficient but also prone to information omissions or errors. It makes it impossible to immediately establish a comprehensive deterrent and education for violators, and it also hinders traffic management departments from promptly grasping the overall violation characteristics and trends of violators, making it difficult to formulate targeted management strategies and publicity and education programs.

[0032] To this end, the present disclosure proposes the following technical solution, wherein, based on a received ticket generation request, the penalty item and identity information of the person to be punished are determined, and a traffic behavior record corresponding to the identity information is obtained. The traffic behavior record includes the violation record and snapshot record of the traffic behavior. Next, based on the violation record and snapshot record, a violation prediction result corresponding to the person to be punished is determined. The violation prediction result is used to describe the likelihood that the person to be punished will violate the traffic rules again. Then, based on the violation prediction result, violation record, and snapshot record, a safety publicity report is generated for the person to be punished, and the access address information of the safety publicity report is superimposed on the traffic violation ticket generated based on the penalty item, thereby generating a target traffic violation ticket for the person to be punished.

[0033] In this way, by automatically generating the target traffic violation ticket corresponding to the person to be punished, law enforcement personnel can avoid manually recording the content of the ticket, thereby improving law enforcement efficiency.

[0034] In addition, based on the violation records and photo-capture records of the person to be punished, the possibility of the person to be punished violating the law again can be predicted, and then a corresponding safety publicity report can be generated, which can improve the pertinence of the safety publicity report and enhance the publicity and education effect.

[0035] Figure 1 A schematic diagram showing an exemplary system architecture to which the technical solutions of the embodiments of the present disclosure can be applied is shown.

[0036] like Figure 1 As shown, the system architecture may include a terminal device 101, a network 102 and a server 103. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103, which may include various connection types, such as a wired communication link, a wireless communication link, etc.

[0037] It should be noted that the terminal device 101 may include but is not limited to one or more of a smart phone, a tablet computer, a portable computer, and a desktop computer. Of course, the terminal device 101 may also be a law enforcement terminal carried by the law enforcement personnel themselves.

[0038] Law enforcement officers can use terminal device 101 to interact with server 103 via network 102 to receive or send information, etc. Server 103 can be a server that provides various services. For example, a law enforcement officer uses terminal device 101 to send a ticket generation request to server 103. Based on the received ticket generation request, server 103 can determine the penalty and identity information of the person to be punished, and obtain the traffic behavior record corresponding to the identity information. The traffic behavior record includes the violation record and snapshot record of the traffic behavior. Next, based on the violation record and snapshot record, a violation prediction result corresponding to the person to be punished is determined. The violation prediction result is used to describe the likelihood that the person to be punished will violate the law again. Then, based on the violation prediction result, violation record, and snapshot record, a safety publicity report is generated for the person to be punished. The access address information of the safety publicity report is superimposed on the traffic violation ticket generated based on the penalty, thereby generating a target traffic violation ticket for the person to be punished.

[0039] It should be noted that the traffic violation handling method provided in the embodiments of the present disclosure is generally executed by a server, and accordingly, the traffic violation handling device is generally installed in the server. However, in other embodiments of the present disclosure, a terminal device may also have similar functions to the server to implement the traffic violation handling method provided in the embodiments of the present disclosure.

[0040] The implementation details of the technical solution of the embodiment of the present disclosure are described in detail below.

[0041] Figure 2FIG. 1 shows a flow chart of a method for handling traffic violations according to an embodiment of the present disclosure. Figure 2 As shown, the traffic violation handling method includes at least steps S210 to S250, which are described in detail as follows.

[0042] In step S210, the penalty items and identity information of the person to be punished are determined based on the received ticket generation request.

[0043] The ticket generation request may be information initiated by law enforcement personnel through a law enforcement terminal (such as a mobile police device) to request the generation of a traffic violation ticket.

[0044] In this embodiment, when handling traffic violations, law enforcement officers can use their own law enforcement terminals to enter the violation information of the person to be punished. This violation information may include, but is not limited to, the time, location, and type of violation, as well as the identity information of the person to be punished. This identity information may be unique identification information corresponding to the person to be punished, such as an ID number. In one example, this identity information may be input by the law enforcement officer through the terminal interface or generated by automatically reading an ID document (e.g., reading an ID card's NFC chip).

[0045] After the law enforcement terminal obtains the above-mentioned violation information, the law enforcement officer can generate a corresponding ticket generation request by clicking a specific area on the terminal interface (such as the "Generate Ticket" button). The law enforcement terminal can then send the ticket generation request to the server.

[0046] After receiving the ticket generation request, the server may parse the ticket generation request to determine the penalty item (ie, the violation type and its corresponding penalty content) and identity information of the person to be punished.

[0047] In one example, those skilled in the art can pre-configure a penalty rule database to automatically associate legal provisions (e.g., Article XX of the Road Traffic Safety Law) with penalty measures (e.g., fine amount, warning level). The server can then match the violation type in the ticket generation request against the penalty rule database to determine the corresponding penalty. For example, based on the violation type, the server can retrieve the penalty information, such as "a fine of XX yuan" and "require safety education," by invoking the penalty rule database.

[0048] In step S220, a traffic behavior record corresponding to the identity information is obtained, where the traffic behavior record includes a violation record and a snapshot record of the traffic behavior.

[0049] The violation record may be confirmed violation information extracted from the traffic management department database, including fields such as violation type, time, location, and penalty result.

[0050] The snapshot record can be traffic behavior data collected by front-end sensing equipment (such as traffic cameras, face capture devices, etc.), which may include the capture time, device number, scene map, non-motor vehicle map, face map, and the initially identified violation type.

[0051] In this embodiment, after determining the identity information of the person to be punished, the server can search in the database of the traffic management department based on the identity information, thereby determining and obtaining the traffic behavior record corresponding to the identity information, which may include violation records and snapshot records of traffic behavior.

[0052] In one example, ETL (Extract-Transform-Load), a process that extracts, transforms, and loads data from a source to a destination, can be used to pull non-motor vehicle violation records from a traffic violation system. This information includes details such as the offender's name, ID number, violation type (e.g., not wearing a helmet, occupying a motor vehicle lane, driving against traffic, speeding, overloading), time of violation, and location of the violation, thereby building a non-motor vehicle violation database. When the server needs to obtain the violation record corresponding to the person to be punished, it can query the non-motor vehicle violation database based on the person's identity information (e.g., ID number) to obtain the corresponding violation record.

[0053] In one example, non-motor vehicle perception data (including but not limited to perception ID, device number, device name, collection time, face image, non-motor vehicle image, scene image, non-motor vehicle violation type, etc.) can be collected through front-end fully structured equipment (including the aforementioned traffic cameras or facial capture devices, etc.). Next, the face image in the non-motor vehicle perception data is compared with the face identity database to identify the person's identity to supplement the non-motor vehicle perception data. The supplemented non-motor vehicle perception data includes the perception ID, device number, device name, collection time, face image, non-motor vehicle image, scene image, non-motor vehicle violation type, ID number, name, and similarity, thereby constructing a non-motor vehicle perception capture recognition database. In this way, when it is necessary to obtain the corresponding capture record of the person to be punished, the server can query the non-motor vehicle perception capture database based on the identity information of the person to be punished to obtain the corresponding capture record.

[0054] Please continue to refer to Figure 2 In step S230, a violation prediction result corresponding to the person to be punished is generated based on the violation record and the snapshot record. The violation prediction result is used to represent the possibility of the person to be punished violating the traffic rules again.

[0055] In this embodiment, the server can perform data analysis based on the violation records and snapshot records corresponding to the individual to be punished, thereby determining the individual's historical violation history (e.g., number of violations, violation types, most common violation types, violation trends, etc.). In this way, the server can determine the likelihood of the individual to be punished violating the law again based on this historical violation history, thereby generating a violation prediction result. For example, if the number of violations by the individual to be punished continues to increase or remain the same over multiple consecutive cycles, then the likelihood of the individual to be punished violating the law again is high; if the number of violations by the individual to be punished continues to decrease or reach zero over multiple consecutive cycles, then the likelihood of the individual to be punished violating the law again is low.

[0056] In this way, the possibility of the person to be punished violating the law again can be determined based on his or her violation records and snap-shot records, which can ensure the accuracy of the violation prediction results and thus ensure the pertinence and effectiveness of subsequent safety publicity reports.

[0057] In step S240, a safety publicity report for the person to be punished is generated based on the violation prediction result, the violation record and the snapshot record.

[0058] Among them, the safety publicity report can be used as content for traffic safety publicity and education for punished personnel.

[0059] In this embodiment, data analysis can be performed based on the violation records and photo-captured records corresponding to the person to be punished, thereby obtaining corresponding violation statistics (such as the violator's name, ID number, violation type, and corresponding violation frequency). The server can then combine these violation statistics with the previously determined violation prediction results to generate a corresponding safety publicity report. In one example, this safety publicity report can include the possible violation types of the person to be punished and corresponding violation cases (including text or images), thereby improving the publicity and education effect.

[0060] In some embodiments, the server can generate corresponding prompts based on the violation statistics and violation prediction results, and input them into a large language model (such as the qwen2.5:32b-instruct large language model in the Ollama platform). After parsing the input data, the large language model can generate a safety publicity report according to the following logic:

[0061] Statistical summary: List the number and percentage of each violation type (e.g., “Not wearing a helmet accounts for 75%”);

[0062] Risk warning: Mark the risk level based on the violation prediction results (e.g. "High-risk personnel require intensive education");

[0063] Case warning: Select the case that matches the violation type (including text description and image link);

[0064] Legal terms: cite relevant laws and regulations (such as fine amounts, penalty points rules);

[0065] Slogans: Generate personalized slogans (e.g., "Helmets keep you safe, a lucky break can lead to disaster!").

[0066] In one embodiment, the safety publicity report can be saved in PDF format, the file name is named according to the "ID number.pdf" rule, and a unique access link is generated.

[0067] Please continue to refer to Figure 2 In step S250, the access address information of the safety publicity report is superimposed on the traffic violation penalty ticket generated based on the penalty matter to generate a target traffic violation penalty ticket for the person to be punished.

[0068] In this embodiment, after generating a safety publicity report corresponding to the person to be punished, the server can generate a corresponding target traffic violation ticket based on the corresponding punishment items of the person to be punished (i.e., the violation type and its corresponding punishment content), wherein the generated target traffic violation ticket contains the access address information of the safety publicity report for the person to be punished to view.

[0069] So, based on Figure 2 The illustrated embodiment automatically generates targeted traffic violation tickets for individuals to be penalized, eliminating the need for law enforcement officers to manually record ticket details and improving law enforcement efficiency. Furthermore, based on the individual's previous violation history and captured footage, the system predicts the likelihood of the individual committing another violation, generating a corresponding safety awareness report. This improves the relevance of the report and ensures effective education.

[0070] Figure 3 FIG. 1 shows a flow chart of step S230 in a method for handling traffic violations according to an embodiment of the present disclosure. Figure 3 As shown, step S230 at least includes steps S231 to S233, which are described in detail as follows.

[0071] In step S231, the number of violations committed by the person to be punished during the evaluation period and the number of compliance times in which the person was captured but behaved in compliance with regulations are determined based on the violation records and the snapshot records.

[0072] The evaluation period may be a pre-set statistical time period (eg, weekly or monthly) for summarizing the traffic behavior data of the persons to be punished.

[0073] The number of violations may be the total number of violations confirmed by the person to be punished during the evaluation period. It should be noted that the total number of violations includes the number of violations handled on-site by the person to be punished, as well as the number of violations that were captured and violated.

[0074] The number of compliance times can be the number of behaviors that are reviewed and determined to be compliant (i.e., in compliance with traffic regulations) from the non-motor vehicle perception, capture and recognition database during the evaluation period.

[0075] In this embodiment, according to the pre-set evaluation cycle, the number of violations committed by the person to be punished in each evaluation cycle and the number of compliance times in which the person was caught behaving in compliance with regulations can be determined based on the violation records and capture records corresponding to the person to be punished. In this way, by quantifying the number of violations and compliance times, the traffic behavior habits of the person to be punished can be objectively reflected.

[0076] In step S232, based on the number of violations and the number of compliances within the evaluation period, the violation score of the person to be punished within the evaluation period is determined, and the violation score is used to represent the severity of the violation of the person to be punished within the evaluation period.

[0077] In this embodiment, for each assessment period, a violation score for the individual to be punished can be determined based on the number of violations and compliances the individual has committed during that assessment period, thereby reflecting the severity of the individual's violations during that assessment period. For example, a weighted sum calculation can be performed based on the number of violations and compliances during the assessment period to obtain a corresponding violation score, thereby quantifying the severity of the individual's violations during that assessment period.

[0078] In one embodiment, the violation score of the person to be punished during the evaluation period can be determined according to the following formula:

[0079] Among them, WVS is the violation score of the person to be punished during the evaluation period; PVM is the number of violations of the person to be punished who was captured and behaved in violation of regulations during the evaluation period (determined based on the non-motor vehicle perception capture and recognition database); NM is the number of compliance times of the person to be punished who was captured and behaved in compliance with regulations during the evaluation period (determined based on the non-motor vehicle perception capture and recognition database); VM is the number of violations handled on-site by the person to be punished during the evaluation period (determined based on the non-motor vehicle personnel violation database); WC is the violation weight coefficient (which can be pre-set based on prior experience).

[0080] When calculating the violation score of the person to be punished during the evaluation period, it is necessary not only to determine the number of violations and violations of the person to be punished during the evaluation period, but also to determine the number of violations in which the person to be punished was captured and violated the regulations during the evaluation period. Based on these two numbers of violations, the total number of violations of the person to be punished during the evaluation period can be accurately calculated.

[0081] This formula accurately calculates the violation score for individuals under investigation during each assessment cycle, transforming complex behavioral data into intuitive scores that facilitate quick assessment of the severity of their violations. Furthermore, the violation weight coefficients in the formula support flexible configuration, adapting to traffic management strategy adjustments across different regions or time periods.

[0082] Please continue to refer to Figure 3 In step S233, based on the violation score of the evaluation period, a violation prediction result corresponding to the person to be punished is generated.

[0083] In one embodiment, the violation scores for each evaluation period can be arranged in order of the evaluation period, and then data analysis can be performed on the arranged violation scores to determine their changing trends. Then, based on these changing trends, a violation prediction result for the person to be punished is determined. In one example, the violation prediction result can include low probability, medium probability, or high probability.

[0084] In this way, by calculating the violation score of each evaluation period, the severity of the violation of the person to be punished during the evaluation period is quantified, thereby improving the accuracy of the determined violation prediction results.

[0085] Figure 4 FIG. 1 shows a flow chart of step S233 in a method for handling traffic violations according to an embodiment of the present disclosure. Figure 4 As shown, step S233 at least includes steps S2331 to S2333, which are described in detail as follows.

[0086] In step S2331, outlier values ​​are screened out from the violation scores of several evaluation periods.

[0087] Among them, outlier screening can be to screen out abnormal data that obviously deviates from other violation scores from the violation scores of each evaluation period.

[0088] In this embodiment, those skilled in the art can pre-set outlier screening rules based on prior experience. In this way, the server can identify and screen out abnormal data from the violation scores of each evaluation period based on the outlier screening rules to ensure the effectiveness of subsequent processing.

[0089] In some embodiments, when filtering out outliers in the violation scores of an evaluation period, the server may first filter out data with a violation score less than 0, obtaining evaluation periods with violations and data with a violation score greater than or equal to 0. The server may then sort the filtered data in the order of the evaluation periods and, using a normal distribution, remove outliers from the filtered violation scores with a probability outside of 3σ, where σ is the standard deviation calculated based on the filtered violation scores.

[0090] Specifically, the server may first calculate the average value PV_WVS and the standard deviation σ of the filtered violation scores, and remove a certain violation score WVS if it is less than PV_WVS-3*σ or greater than PV_WVS+3*σ.

[0091] In step S2332, the violation growth trend of the person to be punished is determined based on the violation scores after screening.

[0092] In this embodiment, the server arranges the violation scores after outlier screening in the order of the evaluation cycle, and then performs data analysis on the arranged data to determine the direction of data change, thereby obtaining the corresponding violation growth trend to provide a basis for subsequent violation prediction results.

[0093] In step S2333, based on the violation growth trend, a violation prediction result corresponding to the person to be punished is generated.

[0094] In this embodiment, the violation growth trend can be reflected in the form of a numerical value (for example, the violation growth trend can be a numerical change slope, which indicates an increase when it is a positive value, and a decrease when it is a negative value). The server can compare the violation growth trend with a pre-set threshold to determine the violation prediction result corresponding to the person to be punished.

[0095] In some embodiments of the present disclosure, when determining the violation prediction results corresponding to the person to be punished based on the violation growth trend, the server can use the violation scores after outliers are screened out to determine the logarithmic growth rate corresponding to the violation scores of each evaluation period, and the logarithmic growth rate is calculated relative to the violation scores of the previous adjacent evaluation period.

[0096] In one example, the logarithmic growth rate for each evaluation period can be determined according to the following formula:

[0097]

[0098] Among them, GR t is the violation growth rate in the tth evaluation period, WVS t is the violation score of the tth evaluation cycle, WVS t-1is the violation score for the (t-1)th evaluation cycle, and log() is the logarithmic function. It should be understood that t and t-1 are the order of the violation scores after filtering out outliers and sorting according to the chronological order of the evaluation cycles, and are not the original order of the violation scores.

[0099] In addition, it should be noted that log(1+GR t ) is added with 1 to handle the situation where the growth rate may be 0 or negative, to ensure the validity of the calculation results.

[0100] Next, the server predicts the logarithmic growth rate corresponding to the target evaluation period based on the violation scores of each evaluation period.

[0101] In one embodiment, a linear regression model may be established based on the logarithmic growth rate corresponding to the violation score in the evaluation period to obtain the logarithmic growth rate corresponding to the target evaluation period output by the linear regression model.

[0102] Specifically, we can use historical data (i.e., the logarithmic growth rates of multiple evaluation periods and the corresponding time variables or other related variables) to build a linear regression model, as shown below:

[0103]

[0104] in, is the predicted violation growth rate of the next evaluation period, β0 and β1 are regression coefficients, t represents the time week, is the error term.

[0105] In this way, using the established linear regression model, the logarithmic growth rate of a future evaluation cycle (i.e., the target evaluation cycle) can be predicted. (where k is the time span of the forecast).

[0106] The server can then determine the violation growth trend (i.e., violation growth rate) corresponding to the target evaluation period based on the logarithmic growth rate of the target evaluation period. Specifically, based on the predicted logarithmic growth rate of the target evaluation period, the violation growth rate of the target evaluation period can be calculated according to the following formula:

[0107]

[0108] Where exp( ) is an exponential function used to restore the logarithmic growth rate.

[0109] In some embodiments of the present disclosure, a threshold value may be pre-set to determine the likelihood of a person to be punished violating traffic rules again. Taking a threshold value of 10% as an example, the violation prediction result SVA of the person to be punished is:

[0110]

[0111] It should be understood that the above “10%” is an illustrative example, and those skilled in the art can determine the corresponding judgment threshold according to actual implementation needs, and the present disclosure does not make any special limitation on this.

[0112] In some embodiments of the present disclosure, a safety publicity report for the person to be punished is generated based on the violation prediction result, the violation record, and the captured record, including:

[0113] Based on the violation prediction results, the violation records, the captured records and the violation type warning and publicity knowledge base, a safety publicity report is generated for the person to be punished. The safety publicity report includes the violation type statistical information, key violation types and safety cases of the person to be punished.

[0114] In this embodiment, a violation type warning publicity knowledge base can be pre-constructed, which can include corresponding violation types, hazard descriptions, laws and regulations, case warnings (including pictures and case text descriptions), etc.

[0115] When a safety publicity report needs to be generated, statistics can be first collected based on violation records and snapshot records. The statistical results, violation prediction results, and the warning publicity knowledge base for the violation type are then combined according to the prompt template and input into the large language model for data analysis. This allows the large language model to generate a safety publicity report for the person to be punished and store it as a PDF file named after their ID number. In this way, the use of the large language model eliminates the need for human intervention to provide guidance and suggestions for traffic violations, improving the effectiveness and efficiency of safety publicity report generation.

[0116] In one example, the safety publicity report may include, but is not limited to, statistical information on the types of violations committed by the individuals to be punished, key violation types (e.g., violation types with a frequency exceeding a certain threshold), and safety cases, to ensure the effectiveness of the safety publicity report in terms of publicity and education.

[0117] In one embodiment, the access address information for the safety publicity report can be reflected in the target traffic violation ticket in the form of a QR code. Specifically, a corresponding QR code can be generated based on the access address of the safety publicity report and attached to the end of the traffic violation ticket generated based on the penalty, allowing the person being penalized to scan and view the information. This prevents the person being penalized from being unable to view the contents of the ticket due to the complexity of the ticket.

[0118] Based on the technical solutions of the above embodiments, a specific application scenario of the embodiments of the present application is introduced below.

[0119] Figure 5A schematic diagram of an application scenario in which the technical solution of the embodiments of the present disclosure can be applied is shown.

[0120] like Figure 5 As shown in this application scenario, the traffic violation system 510 records the handling of non-motorized vehicle violations, while the front-end fully structured device 520 records the sensory capture data of non-motorized vehicles. Both systems send the acquired data to the data analysis service 530, which processes and analyzes the data, such as identifying people and determining the type of violation based on the sensory capture data.

[0121] The analyzed data is transmitted to the violation prediction and violation statistics library 540, so that it can count the traffic behavior of the violator (including the number of violations and the number of compliance behaviors when being photographed but compliant) based on the violation records and capture records, and calculate the violation score, and then predict the possibility of the violator violating again (that is, the aforementioned violation prediction result).

[0122] Next, the large language model 550 generates a personalized safety awareness report for the violator based on the statistical results, violation prediction results, and the violation safety awareness knowledge base 560. This safety awareness report is stored and an access link (i.e., an access address) is provided. When law enforcement officers issue a traffic violation ticket 570, the law enforcement terminal can generate a traffic violation ticket that includes the access address for the safety awareness report. The access address for the safety awareness report is displayed in the form of a QR code on the traffic violation ticket. Violators can scan the QR code 580 to view the corresponding safety awareness report.

[0123] based on Figure 5 In the application scenario shown, the present disclosure provides another embodiment of a method for handling traffic violations, which mainly includes the following steps.

[0124] Step 1: Data Collection and Integration

[0125] 1. Build a database of violations by non-motor vehicle users

[0126] Through ETL, non-motor vehicle violation handling record information is pulled from the traffic violation system. Non-motor vehicle violation data includes the name of the violator, ID number, violation type (non-motor vehicle not wearing a helmet, non-motor vehicle occupying the motor vehicle lane, non-motor vehicle driving in the opposite direction, non-motor vehicle speeding, non-motor vehicle overloading), violation time, violation location and other detailed information.

[0127] 2. Build a non-motor vehicle perception, capture and recognition library

[0128] 2.1. Data aggregation: Non-motor vehicle perception data (perception ID, device number, device name, collection time, face image, non-motor vehicle image, scene image, non-motor vehicle violation type (normal, non-motor vehicle without helmet, non-motor vehicle occupying motor vehicle lane, non-motor vehicle driving in the wrong direction, non-motor vehicle speeding, non-motor vehicle overloaded with passengers)) are collected through front-end fully structured devices.

[0129] 2.2. Personnel identification: Compare the facial images in the non-motor vehicle perception data with the facial identity database to identify the person's identity and supplement the data (perception ID, device number, device name, collection time, facial image, non-motor vehicle image, scene image, non-motor vehicle violation type (normal, non-motor vehicle without a helmet, non-motor vehicle occupying the motor vehicle lane, non-motor vehicle driving in the opposite direction, non-motor vehicle speeding, non-motor vehicle overloaded with people), ID number, name, similarity).

[0130] 3. Build a knowledge base for warnings and publicity on non-motorized traffic violations

[0131] Establish a knowledge base maintenance function, the knowledge base content includes violation types, hazard descriptions, laws and regulations, and case warnings (including pictures and corresponding case text descriptions).

[0132] Step 2: Traffic violation prediction

[0133] 1. The non-motor vehicle violation database is based on the number of violations per person per week (one week is one evaluation cycle), and the data obtained is as follows:

[0134] [{name of offender, ID number of offender, week of offender, number of offenders}, ......

[0135] {name of offender, offender ID number, week of offense, number of offenses}].

[0136] 2. The non-motor vehicle sensing, capturing, and recognition database collects traffic violation statistics per person per week, and the data obtained is as follows:

[0137] [{Name of the person who senses the violation, ID number of the person who senses the violation, number of times the violation is sensed, number of times the violation is sensed}, ......

[0138] {Name of the person who sensed the violation, ID number of the person who sensed the violation, number of times the violation was sensed, number of times the violation was sensed}].

[0139] 3. Calculate weekly violation scores based on personnel:

[0140] Define the name of the person PN, the person's ID number PI, the number of weeks W, the weight coefficient of the violation WC (the current setting of the violation weight is 0.1, which means that the violation score is added by 10 points for being punished once on the road), the number of violations VM (the number of violations handled on site), the number of perceived violations PVM (i.e. the number of violations that are caught and the behavior is in violation), the number of perceived normal times NM (i.e. the number of times that are caught but the behavior is in compliance), and the weekly violation score WVS. Then:

[0141]

[0142] In this way, the following data can be obtained:

[0143] [ {PN1, PI1, W1, WVS1},

[0144] {PN1, PI1, W2, WVS2},

[0145] {PN1, PI1, WN, WVS N},

[0146] {PNM, PIM, W1, WVS1},

[0147] {PNM, PIM, W2, WVS2},

[0148] {PNm, PIm, Wm, WVS m}].

[0149] 4. Predict the possibility of re-violation:

[0150] Define the predicted person's re-violation score as PVR. The following is an example of calculating the re-violation score of PN1 (i.e. the aforementioned person to be punished).

[0151] 4.1. Filter out the data with WVS less than 0 from the data corresponding to PN1, and obtain the data with violation weeks WM and WVS greater than or equal to 0, and sort them in chronological order to obtain:

[0152] [ {PN1, PI1, W1, WVS1},

[0153] {PN1, PI1, W2, WVS2},

[0154] {PN1, PI1, W4, WVS4},

[0155] {PN1, PI1, W6, WVS6},

[0156] {PN1, PI1, Wn, WVS n},

[0157] {PN1, PI1, Wm, WVSm}]

[0158] 4.2. Use normal distribution to filter out abnormal data with WVS probability outside 3σ:

[0159] 4.2.1 Calculating the average violation score PV_WVS

[0160] PV_WVS=(WVS1+WVS2+WVS4+WVS6+...+WVS n +WVS m ) / WM

[0161] Among them, WVS i Score the violation score for week i.

[0162] 4.2.2 Calculate the standard deviation σ according to the following formula

[0163]

[0164] 4.2.3 Identifying Outliers in Weekly Violation Scores

[0165] Remove the data whose WVS is less than PV_WVS-3*σ or greater than PV_WVS+3*σ to obtain the valid week number VW and data set data:

[0166] [{PN1, PI1, W1, WVS1},

[0167] {PN1, PI1, W2, WVS2},

[0168] {PN1, PI1, W4, WVS4},

[0169] {PNm, PIm, Wm, WVS m}].

[0170] 4.3 Calculate the logarithmic growth rate of weekly violation scores:

[0171] For the weekly violation growth rate GR t (where t represents the time week), first calculate its logarithm:

[0172]

[0173] Note that 1 is added here to handle the case where the growth rate may be 0 or negative.

[0174] 4.4 Establishing a linear regression model:

[0175] Using historical data (i.e., multiple weeks of logarithmic growth rates and corresponding time variables or other related variables), build a linear regression model:

[0176]

[0177] in, is the predicted logarithmic growth rate for the next week, β0 and β1 are regression coefficients, t represents the time week, and ϵ is the error term.

[0178] 4.5 Predicting logarithmic growth rate:

[0179] Using the established linear regression model, we can predict the logarithmic growth rate in a certain week in the future. (where k is the forecast time span, That is, it refers to the logarithmic growth rate of the kth evaluation cycle after the tth evaluation cycle).

[0180] 4.6 Calculate the predicted violation growth rate:

[0181] The predicted violation growth rate can be calculated using the predicted value of the logarithmic growth rate:

[0182]

[0183] Note that the exponential function exp() is used here to restore the logarithmic growth rate.

[0184] 4.7 Assessment of the likelihood of a re-violation (SVA) (i.e., the aforementioned violation prediction result):

[0185] Based on the predicted violation growth rate, a threshold can be set to determine the likelihood of a relapse. For example, if the predicted violation growth rate is higher than a certain percentage (such as 10%), the likelihood of a relapse may be considered high.

[0186]

[0187] Get the SVA prediction value set of the possibility of the person violating the traffic rules again:

[0188] [{PN1, PI1, SVA1},

[0189] {PN2, PI2, SVA2},

[0190] {PNm, PIm, SVA m}].

[0191] Step 3: Traverse the ID cards of the personnel to perform violation statistics and combined storage of prediction information

[0192] [{

[0193] PN1 (name), PI1 (ID card), SVA1 (predicted likelihood of re-violation),

[0194] [{'Violation Type 1': 'Violation Number 3',

[0195] 'Violation Type 2': 'Violation Count 2', ......

[0196] 'Violation Type n': 'Violation Count n',}]

[0197] },{

[0198] PN2 (name), PI2 (ID card), SVA2 (predicted likelihood of re-violation),

[0199] [{'Violation Type 1': 'Violation Number 1',

[0200] 'Violation Type 2': 'Violation Count 2', ......

[0201] 'Violation Type n': 'Violation Count n',}]

[0202] },

[0203] {

[0204] PNn (name), PIn (ID card), SVA n (predicting the likelihood of another violation),

[0205] [{'Violation Type 1': 'Violation Number 1',

[0206] 'Violation Type 2': 'Violation Count 2', .......

[0207] 'Violation Type n': 'Violation Count n',}] .......

[0208] }]

[0209] Step 4: Call the large language model to output and store the safety publicity report

[0210] Run the Qwen2.5:32b-instruct large language model on the Ollama platform and send the query violation statistics, predicted reoffending probability, and non-motorized violation type warning and publicity knowledge base to the Qwen2.5 large language model for data analysis based on the prompt phrases. Based on the violator's name, ID card, predicted reoffending probability, violation type statistics, and non-motorized violation type warning and publicity knowledge base returned from the database query, the large language model generates a safety awareness report for the violator and saves it as a PDF file named after the ID card. The access link address is then added to the data in step 3.

[0211] Among them, the question setting: as a non-motor vehicle safety propagandist, according to the name of the illegal personnel, ID, prediction of the possibility of illegal again, illegal type statistical information, non-motor illegal type warning propaganda knowledge base, report summary and suggestion measures, summary output form: illegal type statistical information, key attention safety information and safety cases, propaganda safety slogans.

[0212] The following data is obtained:

[0213] [{

[0214] PN1 (name), PI1 (ID), SVA1 (prediction of the possibility of illegal again), SURL1 (safety propaganda report file access address)

[0215] [{ 'illegal type 1': 'illegal times 3',

[0216] 'illegal type 2': 'illegal times 2', ......

[0217] 'illegal type n': 'illegal times n',}]

[0218] },

[0219] PN2 (name), PI2 (ID), SVA2 (prediction of the possibility of illegal again), SURL2 (safety propaganda report file access address)

[0220] [{ 'illegal type 1': 'illegal times 1',

[0221] 'illegal type 2': 'illegal times 2', ......

[0222] 'illegal type n': 'illegal times n',}]

[0223] }, .......

[0224] {

[0225] PNn (name), PIn (ID), SVA n (prediction of the possibility of illegal again), SURLn (safety propaganda report file access address)

[0226] [{ 'illegal type 1': 'illegal times',

[0227] 'illegal type 2': 'illegal times 2', ......

[0228] 'illegal type n': 'illegal times n',}]

[0229] }]

[0230] Step 5: Generation of ticket during on-site enforcement process

[0231] Based on the original traffic violation ticket, the access address of the safety publicity report is queried according to the identity information of the violator, and a QR code is generated and added to the end of the ticket. The violator can view the corresponding safety publicity report by scanning the QR code.

[0232] In one example, the generated safety publicity report can desensitize personal privacy information, for example, retain the first 6 digits and the last 2 digits of the ID card, and replace the remaining digits with *, and replace the second character of the name with *.

[0233] The above technical solution improves law enforcement efficiency. Law enforcement officers can quickly obtain complete violation information on the scene, eliminating the need for tedious manual query and collation. This significantly shortens enforcement time and improves the overall efficiency of traffic management departments. It also provides traffic management departments with a more comprehensive and accurate basis for violation statistics and analysis, enabling them to formulate scientific and reasonable traffic control plans.

[0234] In addition, the safety publicity report file disclosed herein can be directly scanned and viewed on a mobile device in the form of a QR code, making it convenient to provide targeted education to violators and improving the flexibility and efficiency of traffic management.

[0235] Furthermore, the technical solution disclosed in this disclosure introduces large language model technology into the field of non-motor vehicle violation management, promotes the development of traffic management towards intelligence, and provides a technical foundation for future intelligent transportation applications.

[0236] The following describes an embodiment of the device disclosed herein, which can be used to execute the traffic violation processing method in the above-mentioned embodiment of the present disclosure. For details not disclosed in the embodiment of the device disclosed herein, please refer to the embodiment of the traffic violation processing method in the above-mentioned embodiment of the present disclosure.

[0237] Figure 6 A block diagram of a traffic violation processing device according to an embodiment of the present disclosure is shown. For ease of explanation, certain steps of the above method are described as corresponding to modules. It should be understood that the corresponding modules that perform one or more steps of the above method can be one or more hardware modules specifically configured to perform the corresponding steps, or can be implemented by a processor configured to perform the corresponding steps, or can be stored in a computer-readable medium for implementation by a processor, or can be implemented by some combination thereof.

[0238] Reference Figure 6As shown, the traffic violation processing device 600 according to one embodiment of the present disclosure includes a first determination module 610 , an acquisition module 620 , a second determination module 630 , a generation module 640 and a processing module 650 .

[0239] Among them, the first determination module 610 is used to determine the penalty matters and identity information of the person to be punished based on the received ticket generation request; the acquisition module 620 is used to obtain the traffic behavior record corresponding to the identity information, and the traffic behavior record includes the violation record and the snapshot record of the traffic behavior; the second determination module 630 is used to generate the violation prediction result corresponding to the person to be punished based on the violation record and the snapshot record, and the violation prediction result is used to describe the possibility of the person to be punished violating the law again; the generation module 640 is used to generate a safety publicity report for the person to be punished based on the violation prediction result, the violation record and the snapshot record; and the processing module 650 is used to superimpose the access address information of the safety publicity report on the traffic violation ticket generated based on the penalty matters to generate a target traffic violation ticket for the person to be punished.

[0240] In some embodiments of the present disclosure, a violation prediction result corresponding to the person to be punished is generated based on the violation record and the snapshot record, including: determining the number of violations committed by the person to be punished during the evaluation period and the number of compliance times in which the person was captured but behaved in compliance based on the violation record and the snapshot record; determining the violation score of the person to be punished during the evaluation period based on the number of violations and the number of compliance times within the evaluation period, the violation score being used to characterize the severity of the violation of the person to be punished during the evaluation period; generating a violation prediction result corresponding to the person to be punished based on the violation score of the evaluation period.

[0241] In some embodiments of the present disclosure, the violation score of the person to be punished during the evaluation period is determined according to the following formula:

[0242]

[0243] Among them, WVS is the violation score of the person to be punished during the evaluation period; PVM is the number of violations in which the person to be punished was captured during the evaluation period; NM is the number of compliance violations in which the person to be punished was captured during the evaluation period; VM is the number of violations handled on-site by the person to be punished during the evaluation period; WC is the violation weight coefficient.

[0244] In some embodiments of the present disclosure, the violation prediction result corresponding to the personnel to be punished is generated according to the violation scores of the evaluation periods, including: performing outlier screening on the violation scores of the evaluation periods; determining the violation growth trend of the personnel to be punished according to the screened violation scores.

[0245] In some embodiments of the present disclosure, the outlier screening on the violation scores of the evaluation periods includes: filtering out data with a violation score less than 0 in the evaluation periods; removing abnormal data with a probability outside 3σ from the filtered violation scores based on normal distribution screening, where σ is a standard deviation calculated based on the filtered violation scores.

[0246] In some embodiments of the present disclosure, the violation growth trend of the personnel to be punished is determined according to the screened violation scores, including: determining a logarithmic growth rate corresponding to the violation score of the evaluation period based on the screened violation scores, the logarithmic growth rate being calculated relative to the violation score of an adjacent previous evaluation period; predicting a logarithmic growth rate corresponding to a target evaluation period according to the logarithmic growth rate corresponding to the violation score of the evaluation period; and determining a violation growth trend corresponding to the target evaluation period according to the logarithmic growth rate corresponding to the target evaluation period.

[0247] In some embodiments of the present disclosure, the logarithmic growth rate corresponding to the target evaluation period is predicted according to the logarithmic growth rate corresponding to the violation score of the evaluation period, including: establishing a linear regression model based on the logarithmic growth rate corresponding to the violation score of the evaluation period to obtain a logarithmic growth rate corresponding to the target evaluation period output by the linear regression model.

[0248] In some embodiments of the present disclosure, the safety propaganda report for the personnel to be punished is generated according to the violation prediction result, the violation record, and the snapshot record, including: generating the safety propaganda report for the personnel to be punished according to the violation prediction result, the violation record, the snapshot record, and a violation type warning propaganda knowledge base, the safety propaganda report including violation type statistical information, a key violation type, and a safety case of the personnel to be punished.

[0249] In some embodiments of the present disclosure, the access address information of the safety propaganda report is embodied in the form of a two-dimensional code in the target traffic violation ticket.

[0250] The present disclosure also provides an electronic device. Figure 7 A schematic diagram of a hardware implementation of a processing system is shown.

[0251] As Figure 7As shown, the hardware structure of electronic device 1000 can be implemented using a bus architecture. The bus architecture can include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the hardware. Bus 1100 connects various circuits including one or more processors 1200, memory 1300, and / or hardware modules. Bus 1100 can also connect various other circuits 1400 such as peripheral devices, voltage regulators, power management circuits, external antennas, etc. Bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of illustration, the figure shows only one connecting line, but this does not mean that there is only one bus or only one type of bus.

[0252] The present disclosure also provides a readable storage medium, in which a computer program is stored, and the computer program is used to implement the above-mentioned method when executed by a processor. "Readable storage medium" can be any device that can contain storage, communication, dissemination or transmission programs for use in an instruction execution system, device or equipment or in combination with these instruction execution systems, devices or equipment. More specific examples of readable storage media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM), etc.

[0253] The present disclosure also provides a computer program product. The method of the present disclosure can be implemented in whole or in part using software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed, the process or function of the present disclosure is performed in whole or in part.

[0254] The computer program or instructions can be stored in or transferred from one computer-readable medium to another, e.g., from one website or computer to another website or computer, by way of wired or wireless communication. The computer-readable medium can be any available medium or a combination of one or more of the available media that can be accessed by a server, data center, or the like, and includes both volatile and nonvolatile media, removable and non-removable media. The computer-readable medium can be a magnetic medium, e.g., a floppy disk, a hard disk drive, a magnetic tape; optical media, e.g., a compact disc, a DVD, etc.; or a semiconductor medium, e.g., a solid-state drive. The computer-readable medium can be a volatile or non-volatile medium, or can include both volatile and non-volatile media.

[0255] Those skilled in the art will appreciate that embodiments of the present disclosure can be readily used as a method, apparatus, or computer program product. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure can take the form of a computer program product on one or more computer-readable medium(s) (including, but not limited to, diskettes, CD-ROMs, optical storage devices, etc.) embodying computer readable program code thereon.

[0256] The present disclosure is described herein with reference to flow diagrams and / or block diagrams of methods, apparatuses, electronic devices, and computer program products according to this disclosure. It will be understood that each flow and / or block, and combinations of flows and / or blocks, in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, an embedded processor or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams illustrate the architecture, functionality, and operation of possible implementations of apparatuses and computer program products according to this disclosure. In this regard, each flow and / or block in the flow diagrams and / or block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that, in some alternative implementations, the flow diagram and / or block diagram can represent a Figure 1 The apparatus can be implemented by one or more of the flow or flows and / or blocks therein and / or combinations of the flow or flows and / or blocks in the flow diagrams and / or block diagrams.

[0257] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 The flow diagram and / or block diagram in the flow diagrams and / or block diagrams illustrate the architecture, functionality, and operation of possible implementations of apparatuses and computer program products according to this disclosure. In this regard, each flow and / or block in the flow diagrams and / or block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that, in some alternative implementations, the flow diagram and / or block diagram can represent a Figure 1 The apparatus can be implemented by one or more of the flow or flows and / or blocks therein and / or combinations of the flow or flows and / or blocks in the flow diagrams and / or block diagrams.

[0258] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable data processing devices, to generate a computer implemented process, so that the instructions executed on the computer or other programmable data processing devices provide the function of realizing the processes specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in the block Figure 1 Figure 1 one flow or multiple flows and / or the functions specified in the block

[0259] In the description of the present specification, the description of the terms "one embodiment / way", "some embodiments / ways", "example", "specific example", or "some examples" and the like means that the specific features, structures, or characteristics described in connection with the embodiment / way or example are included in at least one embodiment / way or example of the present disclosure. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment / way or example. Also, the specific features, structures, or characteristics described can be combined in any appropriate manner in any one or more embodiments / ways or examples. In addition, the person skilled in the art can combine and combine the different embodiments / ways or examples described in the present specification and the features of the different embodiments / ways or examples without contradiction.

[0260] The person skilled in the art should understand that the above embodiments are only for clearly illustrating the present disclosure, and are not intended to limit the scope of the present disclosure. Based on the above disclosure, other changes or modifications can also be made by those skilled in the art, and these changes or modifications are still within the scope of the present disclosure.

Claims

1. A method for handling traffic violations, characterized in that: include: Determine the penalty items and identity information of the person to be penalized based on the received penalty ticket generation request; Obtaining a traffic behavior record corresponding to the identity information, the traffic behavior record including a violation record and a captured record of the traffic behavior; Generating a traffic violation prediction result corresponding to the person to be punished based on the traffic violation record and the captured record, wherein the traffic violation prediction result is used to indicate the possibility of the person to be punished violating the traffic rules again; Generate a safety publicity report for the person to be punished based on the violation prediction result, the violation record and the captured record; as well as Superimposing the access address information of the safety publicity report onto the traffic violation penalty ticket generated based on the penalty matter to generate a target traffic violation penalty ticket for the person to be punished; The generating of a violation prediction result corresponding to the person to be punished based on the violation record and the captured record includes: Determine, based on the violation records and the captured records, the number of violations handled on-site by the person to be punished during the evaluation period, the number of violations in which the person was captured during the evaluation period and engaged in illegal behavior, and the number of violations in which the person was captured but engaged in compliant behavior; Determine, based on the number of violations handled on-site, the number of violations captured and violated by video, and the number of compliance times, a violation score for the person to be punished during the evaluation period, the violation score being used to represent the severity of the violation by the person to be punished during the evaluation period; Generating a violation prediction result corresponding to the person to be punished based on the violation scores of the evaluation period includes: screening out abnormal values ​​from the violation scores of several evaluation periods; determining a violation growth rate of the person to be punished based on the filtered violation scores; and generating a violation prediction result corresponding to the person to be punished based on the violation growth rate; The method of determining the violation growth rate of the person to be punished based on the violation scores after screening includes: arranging the violation scores after screening in the order of the evaluation cycles, and determining the logarithmic growth rate corresponding to the violation scores of each evaluation cycle, wherein the logarithmic growth rate is calculated relative to the violation scores of the previous evaluation cycle; predicting the logarithmic growth rate corresponding to a future evaluation cycle, i.e., a target evaluation cycle, based on the logarithmic growth rate corresponding to the violation scores of each evaluation cycle; and determining the violation growth rate corresponding to the target evaluation cycle based on the logarithmic growth rate corresponding to the target evaluation cycle. The step of predicting the logarithmic growth rate corresponding to a future evaluation period, i.e., a target evaluation period, based on the logarithmic growth rates corresponding to the violation scores in each evaluation period includes: A linear regression model is established based on the logarithmic growth rates corresponding to the violation scores in each evaluation period, and the logarithmic growth rate corresponding to the target evaluation period output by the linear regression model is obtained.

2. The method according to claim 1, characterized in that The violation score of the person to be punished during the evaluation period is determined according to the following formula: Among them, WVS is the violation score of the person to be punished during the evaluation period; PVM is the number of violations in which the person to be punished was captured during the evaluation period; NM is the number of compliance violations in which the person to be punished was captured during the evaluation period; VM is the number of violations handled on-site by the person to be punished during the evaluation period; WC is the violation weight coefficient.

3. The method according to claim 1, characterized in that Outlier screening was performed on the violation scores for several of the assessment cycles, including: Filter out data with a violation score less than 0 in a number of the evaluation periods; Based on normal distribution screening, abnormal data with a probability outside 3σ are removed from the filtered violation scores, where σ is the standard deviation calculated based on the violation scores obtained after filtering.

4. The method according to claim 1, wherein Generate a safety publicity report for the person to be punished based on the violation prediction result, the violation record, and the captured record, including: Based on the violation prediction results, the violation records, the captured records and the violation type warning and publicity knowledge base, a safety publicity report is generated for the person to be punished. The safety publicity report includes the violation type statistical information, key violation types and safety cases of the person to be punished.

5. The method according to any one of claims 1 to 4, characterized in that The access address information of the safety publicity report is reflected in the target traffic violation ticket in the form of a QR code.

6. An electronic device, characterized in that: include: a memory storing execution instructions; as well as A processor, wherein the processor executes the execution instructions stored in the memory, so that the processor executes the method according to any one of claims 1 to 5.

7. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images