Police officer deployment method and device based on alliance chain, equipment and storage medium

Abstract

The application is applied to the technical field of police deployment, and discloses a police personnel deployment method, device and equipment based on a consortium chain and a storage medium. The method comprises the following steps: obtaining and fusing structured business account data and unstructured original business data to obtain global structure data representing the case handling situation of police personnel; obtaining quantitative evaluation points corresponding to the global structure data by using a quantitative evaluation contract deployed on a preset consortium chain; obtaining on-chain time series data of each police personnel in a professional period based on the original business data, the business account data and the quantitative evaluation points; and deploying tasks for each police personnel based on the on-chain time series data. In this way, the deployed tasks can be accurately matched with the police personnel, thereby improving the rationality and matching degree of the police personnel deployment.

Description

Technical Field

[0001] This invention relates to the field of police deployment technology, specifically to a method, apparatus and equipment, and storage medium for deploying police personnel based on a consortium blockchain. Background Technology

[0002] With the rapid development of public security informatization, public security organs across the country have generally built business systems such as law enforcement and case handling, police tracking, and emergency response to achieve informatization of police affairs. However, when deploying police officers, the existing business systems can only dispatch and deploy police officers based on geographical location and duty roster, without considering whether the deployed police officers are suitable. This results in unreasonable allocation of police force, low task matching, and low dispatch efficiency, making it difficult to meet the needs of modern police affairs for precise, intelligent, and standardized management.

[0003] Therefore, in order to overcome the above-mentioned technical problems, the present invention provides a method, apparatus and equipment, and storage medium for deploying police officers based on consortium blockchain. Summary of the Invention

[0004] The technical problem to be solved by this invention is how to improve the rationality and matching degree of police personnel deployment. The purpose is to provide a police personnel deployment method, device and equipment, and storage medium based on consortium blockchain to improve the rationality and matching degree of police personnel deployment.

[0005] This invention is achieved through the following technical solution:

[0006] Firstly, a method for deploying police officers based on a consortium blockchain includes: acquiring and integrating structured business ledger data and unstructured raw business data to obtain global structural data characterizing the case-handling situation of police officers; using a quantitative evaluation contract deployed on a pre-defined consortium blockchain to obtain quantitative evaluation scores corresponding to the global structural data; obtaining on-chain time-series data for each police officer's career cycle based on the raw business data, the business ledger data, and the quantitative evaluation scores; and deploying tasks to each police officer based on the on-chain time-series data.

[0007] In some embodiments, the acquisition and fusion of structured business ledger data and unstructured raw business data to obtain global structured data characterizing the case-handling situation of police officers includes: collecting the business ledger data and raw business data corresponding to police officers from several preset public security business systems using a preset middleware server; extracting entities from the raw business data using a preset large language model to obtain entity information; organizing the entity information to obtain first structured feature data; performing field mapping and enumeration value cleaning on the business ledger data to obtain second structured feature data; extracting the police officer's badge number and corresponding case number from the first structured feature data and the second structured feature data respectively; and fusing the first structured feature data and the second structured feature data based on the badge number and case number to obtain the global structured data.

[0008] In some embodiments, obtaining the quantitative evaluation score corresponding to the global structural data using a quantitative evaluation contract deployed on a consortium blockchain includes: using the quantitative evaluation contract to determine the police execution type of the global structural data; using the quantitative evaluation contract to extract feature parameters corresponding to the police execution type from the global structural data; using the quantitative evaluation contract to obtain the baseline value corresponding to the police execution type, the weight corresponding to each feature parameter, and the reward / penalty value corresponding to each feature parameter; and using the quantitative evaluation contract to obtain the quantitative evaluation score based on the weight, the baseline value, and the reward / penalty value.

[0009] In some embodiments, obtaining on-chain time-series data corresponding to each police officer based on the original business data, the business ledger data, and the quantitative evaluation score includes: obtaining a digital digest corresponding to the original business data; packaging the digital digest, the business ledger data, and the quantitative evaluation score, and adding corresponding timestamp tags and police execution type tags to the packaged data to obtain packaged result data; uploading the packaged result data to the consortium blockchain to utilize the consortium blockchain for multi-node verification of the packaged result data; storing the verified packaged result data in the accompanying blockchain distributed ledger of the consortium blockchain; and reading all verified packaged result data corresponding to each police officer in real time from the accompanying blockchain distributed ledger to obtain the on-chain time-series data.

[0010] In some embodiments, the original business data includes subjective business texts of police officers handling cases; uploading the packaged result data to the consortium blockchain includes: obtaining law enforcement record data of police officers handling cases; using the law enforcement record data to perform cross-validation on the subjective business texts; and uploading the packaged result data to the consortium blockchain if the cross-validation passes.

[0011] In some embodiments, the task deployment for each police officer based on the on-chain time series data includes: generating an occupational feature vector corresponding to each police officer based on the on-chain time series data; obtaining a risk assessment vector corresponding to each police officer; and deploying tasks for each police officer based on the occupational feature vector and the risk assessment vector.

[0012] Secondly, a police officer deployment device based on a consortium blockchain includes: a first acquisition module configured to acquire and fuse structured business ledger data and unstructured raw business data to obtain global structured data characterizing the case-handling situation of police officers; a scoring module configured to acquire quantitative evaluation scores corresponding to the global structured data using a quantitative evaluation contract deployed on the consortium blockchain; a second acquisition module configured to acquire on-chain time-series data corresponding to each police officer based on the raw business data, the business ledger data, and the quantitative evaluation scores; the on-chain time-series data describing a set of professional time characteristics within the career cycle of police officers; and a deployment module configured to deploy tasks to each police officer based on the on-chain time-series data.

[0013] Thirdly, a police officer deployment device based on a consortium blockchain includes a processor and a memory storing program instructions, wherein the processor is configured to execute the aforementioned police officer deployment method based on a consortium blockchain when running the program instructions.

[0014] Fourthly, an electronic device, the electronic device body; and the aforementioned police personnel deployment device based on consortium blockchain.

[0015] Fifthly, a storage medium stores program instructions that, when executed, perform the aforementioned consortium blockchain-based police personnel deployment method.

[0016] Compared with existing technologies, this invention obtains global structural data characterizing the case-handling performance of police officers by acquiring and fusing structured business ledger data and unstructured raw business data. It then uses a quantitative evaluation contract deployed on a pre-defined consortium blockchain to obtain quantitative evaluation scores corresponding to the global structural data. Based on the raw business data, business ledger data, and quantitative evaluation scores, it obtains on-chain time-series data for each police officer's career cycle, and then deploys tasks to each officer based on this on-chain time-series data. In this way, by acquiring and fusing structured business ledger data and unstructured raw business data, multi-source data fusion is achieved, enabling the fused global structural data to comprehensively characterize the case-handling performance of police officers. Finally, by using a quantitative evaluation contract deployed on a pre-defined consortium blockchain to obtain quantitative evaluation scores corresponding to the global structural data, the quantification of the global structural data is realized, allowing the quantitative evaluation scores to characterize the case-handling capabilities of police officers. Then, based on the original business data, business ledger data, and quantitative evaluation scores, on-chain time series data within the career cycle of each police officer is obtained, so that the on-chain time series data can comprehensively and accurately represent the case handling situation of each police officer within the career cycle. Then, based on the on-chain time series data, tasks are deployed to each police officer, so that the deployed tasks can be accurately matched with the police officers, thereby improving the rationality and matching degree of the deployment of police officers. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0018] Figure 1 This is a flowchart illustrating a method for deploying police officers based on a consortium blockchain, provided in an embodiment of this disclosure.

[0019] Figure 2 This is a schematic diagram of a police officer deployment device based on a consortium blockchain, provided in an embodiment of this disclosure;

[0020] Figure 3 This is a schematic diagram of another police officer deployment device based on a consortium blockchain provided in this disclosure embodiment;

[0021] Figure 4 This is a schematic diagram of a police officer deployment environment based on a consortium blockchain, provided in an embodiment of this disclosure. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0024] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0025] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0026] In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0027] Please see Figure 1 , Figure 1 This is a schematic flowchart illustrating a method for deploying police officers based on a consortium blockchain, as shown in an exemplary embodiment of this application. Figure 1 As shown in the figure, this disclosure provides a method for deploying police officers based on a consortium blockchain, the method including:

[0028] Step S101: Obtain and merge structured business ledger data and unstructured raw business data to obtain global structured data representing the case handling situation of police officers.

[0029] Step S102: Use the quantitative evaluation contract deployed on the preset consortium blockchain to obtain the quantitative evaluation score corresponding to the global structure data.

[0030] Step S103: Obtain on-chain time series data for each police officer's career cycle based on original business data, business ledger data, and quantitative evaluation scores.

[0031] Step S104: Deploy tasks to each police officer based on on-chain time series data.

[0032] In this embodiment, by acquiring and fusing structured business ledger data and unstructured raw business data, global structural data representing the case-handling performance of police officers is obtained. A quantitative evaluation contract deployed on a pre-defined consortium blockchain is used to obtain quantitative evaluation scores corresponding to the global structural data. Based on the raw business data, business ledger data, and quantitative evaluation scores, on-chain time-series data within each police officer's career cycle is obtained. Then, tasks are deployed to each police officer based on the on-chain time-series data. Thus, by acquiring and fusing structured business ledger data and unstructured raw business data, multi-source data fusion is achieved, enabling the fused global structural data to comprehensively represent the case-handling performance of police officers. Furthermore, the quantitative evaluation contract deployed on a pre-defined consortium blockchain obtains the quantitative evaluation scores corresponding to the global structural data, achieving the quantification of the global structural data and allowing the quantitative evaluation scores to represent the case-handling capabilities of police officers. Then, based on the original business data, business ledger data, and quantitative evaluation scores, on-chain time series data within the career cycle of each police officer is obtained, so that the on-chain time series data can comprehensively and accurately represent the case handling situation of each police officer within the career cycle. Then, based on the on-chain time series data, tasks are deployed to each police officer, so that the deployed tasks can be accurately matched with the police officers, thereby improving the rationality and matching degree of the deployment of police officers.

[0033] It should be noted that the pre-defined consortium blockchain is a permissioned blockchain jointly established, managed and maintained by multiple departments such as political work, legal affairs, supervision, and discipline inspection. It is between a public blockchain and a private blockchain and belongs to a semi-decentralized architecture.

[0034] Furthermore, structured business ledger data and unstructured raw business data are acquired and integrated to obtain global structured data representing the case-handling situation of police officers. This includes: collecting business ledger data and raw business data corresponding to police officers from several pre-set public security business systems using a pre-set middleware server; extracting entity information from the raw business data using a pre-set large language model; organizing the entity information to obtain first structured feature data; performing field mapping and enumeration value cleaning on the business ledger data to obtain second structured feature data; extracting the police officer's badge number and corresponding case number from the first and second structured feature data respectively; and integrating the first and second structured feature data based on the badge number and case number to obtain global structured data.

[0035] In this way, by relying on middleware servers to connect with multiple public security business systems, the system uniformly collects business ledger data and raw business data corresponding to police officers, realizing the automated collection of business ledger data and raw business data. Then, using a preset large language model, entity extraction is performed on the raw business data to obtain entity information. The entity information is organized to obtain the first structured feature data. Then, field mapping and enumeration value cleaning are performed on the business ledger data to obtain the second structured feature data. This realizes the automatic organization of business ledger data and raw business data. Then, the police officer's badge number and the corresponding case number are extracted from the first structured feature data and the second structured feature data, respectively. Based on the badge number and case number, the first structured feature data and the second structured feature data are merged to obtain global structure data. The information in the business ledger data and raw business data is integrated to form global structure data representing the case handling situation of police officers. This realizes the closed-loop connection of case handling information of single case and single police officer from all dimensions, so that the global structure data can accurately and completely represent the case handling performance of police officers.

[0036] It should be noted that a middleware server is a middleware system with security isolation, protocol conversion, and data routing capabilities. It includes an ETL (Extract-Transform-Load) engine and API (Application Programming Interface) routing aggregation functionality.

[0037] The middleware server can connect to various public security business systems through API interfaces to collect business ledger data and raw business data corresponding to police officers from these systems using an ETL engine.

[0038] It should be noted that the business ledger data is electronic tabular data that records relevant information of police officers’ daily law enforcement, case handling and management activities according to unified standard fields.

[0039] In some embodiments, business ledger data may include one or more of the following: police call and response ledger data, case handling ledger data, traffic management ledger data, and law enforcement supervision and internal affairs ledger data.

[0040] It should be noted that the business ledger data may include different types of data such as case number, involved personnel, handling police officers, location involved, case type, case time, and case processing time. Different business ledger data may also include their corresponding independent data. For example, case handling ledger data may also include case results data and evidence lists; traffic management ledger data may also include driver's license information, vehicle license plate numbers involved, and accident liability determination information; and law enforcement supervision and internal affairs ledger data may also include law enforcement recorder usage registration and equipment requisition information.

[0041] It should be noted that the original business data is raw text content that has no fixed tables or fields, no uniform format, and is freely written.

[0042] In some embodiments, raw business data may include transcripts, work records, and documents written by police officers during case handling.

[0043] It should be noted that the pre-configured large language model is deployed on the public security intranet or a local server, and is not exposed to the public network or allowed to leave the domain. This improves data security.

[0044] It should be noted that entity information is obtained by using a pre-defined large language model to extract entities from the original business data. In other words, the pre-defined large language model is used to perform semantic parsing and entity extraction on the original business data to obtain entity information.

[0045] In some embodiments, entity information includes information corresponding to multiple entity types.

[0046] Specifically, entity types include time entities, location entities, personnel entities, case entities, item entities, behavior entities, and unit entities.

[0047] For example: the information corresponding to the time entity includes one or more of the following: time of the incident, time of the police report, time of arrival at the police station, time of the conversation, and time period of the incident; the information corresponding to the location entity includes one or more of the following: the address of the incident, jurisdiction, road section, place, and landmark; the information corresponding to the person entity includes one or more of the following: name, nickname, gender, age, ID number, identification information indicating the victim, suspect, witness, or police officer, and contact information; the information corresponding to the case entity includes one or more of the following: the cause of action, case type, illegal or criminal act, and severity of the circumstances; the information corresponding to the item entity includes one or more of the following: the involved property, tools, vehicles, documents, and contraband; the information corresponding to the behavior entity includes one or more of the following: descriptions of the behavior such as beating, theft, robbery, quarrel, escape, surrender, and summons; the information corresponding to the unit entity includes one or more of the following: the unit involved, business premises, jurisdictional police station, and case-handling department.

[0048] It should be noted that organizing entity information to obtain the first structured feature data means integrating the entity information of various police officers in different cases in chronological order of alarm time to obtain the first structured feature data.

[0049] It should be noted that field mapping includes field name mapping.

[0050] In some embodiments, in tables of different business ledger data, the same semantic information name may have multiple field names. Specifically, for the same case, in the police call ledger data, the field name describing the address where the incident occurred is the location of the incident, while in the case handling ledger data, the field name with the same semantic meaning is the address of the incident. In order to unify them, it is necessary to map the field names, for example, map them all to the address of the incident.

[0051] It's important to note that enumeration value cleaning is a standardized process for handling specific information. For example, for a unified case type, some business ledger data might contain case number codes, while others might contain text. Enumeration value cleaning transforms information in different formats into a unified representation.

[0052] It should be noted that the global structured data is obtained by fusing the first and second structured feature data based on the police badge number and case number. Specifically, for each case number, the case information and entity information of each police officer are extracted from the corresponding first and second structured feature data. The entity information of each police officer is then fused using the police badge number to obtain the officer information. Finally, the case number, case information, and the fused officer information are merged to obtain the global structured data. This global structured data represents the case information under each case number and the case-handling status of different police officers.

[0053] Furthermore, the quantitative evaluation contract deployed on the consortium blockchain is used to obtain the quantitative evaluation score corresponding to the global structure data, including: using the quantitative evaluation contract to determine the police execution type of the global structure data; using the quantitative evaluation contract to extract the feature parameters corresponding to the police execution type from the global structure data; using the quantitative evaluation contract to obtain the benchmark value corresponding to the police execution type, the weight corresponding to each feature parameter, and the reward / penalty value corresponding to each feature parameter; and using the quantitative evaluation contract to obtain the quantitative evaluation score based on the weight, benchmark value, and reward / penalty value.

[0054] In this way, by using quantitative evaluation contracts to determine the police execution type of the global structural data, and then using quantitative evaluation contracts to extract the feature parameters corresponding to the police execution type from the global structural data, the benchmark value, the weight of each feature parameter, and the reward / penalty value corresponding to each feature parameter are obtained using quantitative evaluation contracts. Based on the weights, benchmark values, and reward / penalty values, quantitative evaluation scores are obtained using quantitative evaluation contracts, realizing the automatic quantification of police officers' case-handling capabilities in police execution types. At the same time, the entire derivation and calculation process is automatically executed by the on-chain quantitative evaluation contracts. The evaluation rules, weight parameters, and reward / penalty standards are all stored on the blockchain and are tamper-proof, reducing subjective intervention and calculation errors caused by manual scoring and calculation. This effectively solves the problems of inconsistent police assessment standards, cumbersome calculations, and insufficient fairness in traditional police assessments, achieving standardized derivation, automated calculation, and traceable verification of police officers' case-handling performance quantitative assessment, and significantly improving the accuracy, fairness, and efficiency of police assessments.

[0055] It should be noted that the type of police duty execution refers to the business category of police officers' duties. In some embodiments, the type of police duty execution includes responding to and handling police calls, handling administrative cases, handling criminal cases, mediating public order disputes, patrolling and prevention, managing key personnel, inspecting business premises, handling traffic accidents, and handling fraud-related seizures and confiscations.

[0056] In some embodiments, the starting letters of case numbers differ for different police enforcement types. Utilizing a quantitative assessment contract to determine the police enforcement type within the global structure data allows for direct determination of the police enforcement type from the case numbers within the global structure data.

[0057] It should be noted that the quantitative evaluation contract defines the feature parameters to be extracted for different police execution types. Therefore, the quantitative evaluation contract is used to extract the feature parameters corresponding to the police execution types from the global structured data.

[0058] It should be noted that the quantitative assessment contract stores a database of police characteristic parameters. This database stores the correspondence between four elements: police execution type, the weight of each characteristic parameter corresponding to that type, the baseline value for that type, and the reward / penalty value for each characteristic parameter. Specifically, the reward / penalty value for a characteristic parameter refers to the reward / penalty value corresponding to the value of that characteristic parameter. That is, different characteristic parameter values ​​result in different reward / penalty values.

[0059] The quantitative evaluation contract is used to obtain the benchmark value, the weight of each feature parameter, and the reward / penalty value of each feature parameter corresponding to the police execution type. In other words, the quantitative evaluation contract is used to perform a lookup operation in the police feature parameter database according to the police execution type to obtain the weight of each feature parameter, the benchmark value, and the reward / penalty value of each feature parameter corresponding to the police execution type.

[0060] Optionally, a quantitative assessment contract can be used to obtain quantitative assessment scores based on weights, benchmark values, and reward / penalty values. That is, for each police execution type corresponding to the global structure data of the same police number and case number, the quantitative assessment contract is used to perform a weighted sum based on weights and reward / penalty values. The weighted sum is then added to the benchmark value to obtain the quantitative assessment score.

[0061] In some embodiments, for police officer A, their police duty execution type is B, and the corresponding baseline value is 80. The characteristic parameters corresponding to police duty execution type B include characteristic parameter C1, characteristic parameter C2, and characteristic parameter C3. The reward / punishment value corresponding to C1 is 1.2, with a weight of 0.3; the reward / punishment value corresponding to C2 is -0.5, with a weight of 0.3; and the reward / punishment value corresponding to C3 is 3, with a weight of 0.4. Therefore, the quantitative evaluation score = 1.2 × 0.3 - 0.5 × 0.3 + 3 × 0.4 + 80 = 81.41.

[0062] Optionally, a quantitative assessment contract is used to obtain quantitative assessment scores based on weights, benchmark values, and reward / penalty values. Specifically, for each police execution type corresponding to the same alarm number and case number in the global structure data, a weighted sum is calculated using the quantitative assessment contract based on weights and reward / penalty values. This weighted sum is then added to the benchmark value to obtain candidate quantitative assessment scores. If the candidate quantitative assessment score is less than or equal to a preset capping threshold, the candidate quantitative assessment score is determined as the quantitative assessment score. If the candidate quantitative assessment score is greater than the capping threshold, the capping threshold is determined as the quantitative assessment score.

[0063] Furthermore, based on the original business data, business ledger data, and quantitative assessment scores, on-chain time-series data corresponding to each police officer is obtained, including: obtaining digital digests corresponding to the original business data; packaging the digital digests, business ledger data, and quantitative assessment scores, and adding corresponding timestamp tags and police execution type tags to the packaged data to obtain packaged result data; uploading the packaged result data to the consortium blockchain for multi-node verification; storing the verified packaged result data in the consortium blockchain's accompanying blockchain distributed ledger; and reading all verified packaged result data corresponding to each police officer in real time from the accompanying blockchain distributed ledger to obtain on-chain time-series data.

[0064] In this way, by obtaining the digital digest corresponding to the original business data, the unstructured original business data is simplified, and the original business data can be uniquely identified based on the digital digest. This reduces the problems of excessive volume, duplicate storage, and susceptibility to tampering of the original business data, and ensures the verifiability of the original case-handling data. Then, the digital digest, business ledger data, and quantitative evaluation points are packaged together, and corresponding timestamp tags and police execution type tags are added to the packaged data to obtain the packaged result data. This allows the packaged result data to be associated with the timestamp tags and police execution type tags.

[0065] The packaged data is then uploaded to the consortium blockchain for multi-node verification, ensuring its accuracy and legitimacy. The verified data is then stored in the consortium blockchain's accompanying distributed ledger. This ledger allows for real-time retrieval of all verified packaged data for each police officer, generating on-chain time-series data. This enables the on-chain time-series data to comprehensively and accurately represent the case-handling performance of police officers across different police roles throughout their entire career.

[0066] It should be noted that the digital summary, business ledger data and quantitative assessment points are packaged together. That is, for each police officer, the digital summary, business ledger data and quantitative assessment points for the same case are packaged together according to the case number, while the digital summary, business ledger data and quantitative assessment points for different cases are packaged separately.

[0067] It should be noted that the timestamp label can indicate the time when police officers processed the case corresponding to the case number.

[0068] In some embodiments, for each police officer, a packaged result data set corresponds to a digital summary, business ledger data, and quantitative assessment score for each case. That is, for police officer A1, the cases they handle include case B1 and case B2. Therefore, for police officer A1, case B1 corresponds to a packaged result data set C1; case B2 corresponds to a packaged result data set C2. For police officer A2, the cases they handle include case B2 and case B3. Therefore, for police officer A2, case B2 corresponds to a packaged result data set C3; case B3 corresponds to a packaged result data set C4.

[0069] Furthermore, obtaining the digital digest corresponding to the original business data includes: normalizing the original business data. The original business data is processed using a pre-defined SM3 cryptographic hash algorithm to obtain the corresponding digital digest. This way, even if only a single punctuation mark is changed in the original business data, the generated digital digest will undergo a drastic and unpredictable change, allowing the digital digest to directly point to the original business data. Simultaneously, it facilitates subsequent data packaging, eliminating the need to package the massive original business data along with it; only the digital digest needs to be packaged and stored, thus reducing storage space.

[0070] It should be noted that multi-node verification of the packaged result data is performed using a consortium blockchain, that is, the nodes of each department in the consortium blockchain are used to verify the packaged result data.

[0071] In some embodiments, the consortium blockchain is a permissioned blockchain jointly established, managed, and maintained by multiple departments such as political work, legal affairs, supervision, and discipline inspection. Each department has one or more verification nodes on the consortium blockchain, and each department can perform multi-node verification on the uploaded packaged result data through the consortium blockchain. The nodes that different packaged result data need to go through can be the same or different. If all the nodes that the packaged result data goes through pass, the verification is determined to be successful.

[0072] It should be noted that the verified packaging result data is stored in the accompanying blockchain distributed ledger of the consortium blockchain, that is, the verified packaging result data is solidified into the accompanying blockchain distributed ledger.

[0073] In some embodiments, in a companion blockchain distributed ledger, the packaged result data can be stored in a chain based on the sergeant numbers of different police officers, i.e., one sergeant number corresponds to one storage chain. In the storage chain, the packaged result data is arranged in chronological order according to its timestamp tags.

[0074] Furthermore, the original business data includes the subjective business texts of police officers handling cases; uploading the packaged result data to the consortium blockchain includes: obtaining law enforcement record data of police officers handling cases; using the law enforcement record data to cross-validate the subjective business texts; and uploading the packaged result data to the consortium blockchain if the cross-validation passes.

[0075] In this way, by using the law enforcement records of police officers during case handling to cross-validate the subjective business texts of police officers in the original business data, the packaged result data is uploaded to the consortium blockchain when the cross-validation passes. This reduces the occurrence of fictitious or erroneous data on the blockchain, ensuring that the final packaged result data uploaded to the blockchain truly reflects the actual case handling situation of police officers. This significantly improves the accuracy, authenticity, and authority of the data stored on the consortium blockchain, allowing subsequent task deployment to be based on objective and credible data, and improving the rationality and accuracy of task deployment.

[0076] It should be noted that the law enforcement record data of police officers during case handling can include the trajectory data and video data of the body camera worn by the police officers during the case handling, as well as equipment issuance records.

[0077] Preferably, the law enforcement recorder can be a 360-degree panoramic law enforcement recorder. Equipment requisition records can be retrieved through the equipment storage cabinet.

[0078] The trajectory and video data collected by law enforcement recorders during case handling can be used to extract one or more of the following: case location, number of suspects, arrival time at the scene, and case duration; the use of police equipment can be determined through equipment requisition records.

[0079] It should be noted that cross-validation of subjective business texts using law enforcement record data includes: extracting subjective information to be validated from the subjective business texts; obtaining standard validation information based on law enforcement record data; and performing cross-validation based on the standard validation information and the subjective information to be validated.

[0080] In some embodiments, for a sudden case of disorderly conduct occurring overnight, the corresponding subjective business text describes: "Arriving at the scene at 2:15 AM, facing 5 armed and intoxicated individuals, decisively drawing a gun as a warning and quickly bringing the situation under control, resolving the crisis in 30 minutes." The subjective information to be verified can be extracted as follows: Arrival time: 2:15 AM; Number of suspects: 5; Case handling time: 30 minutes; Use of police equipment: Used police equipment as a warning. By obtaining video and trajectory data from the law enforcement records of the police officers handling the case, target monitoring was performed on the video data, determining the number of suspects to be 2; the trajectory data determined the arrival time to be 2:35 AM. Simultaneously, the equipment requisition record confirmed that the police officers did not requisition police equipment. Therefore, the standard verification information includes: Number of suspects: 2; Arrival time: 2:35 AM; Use of police equipment: Not used. It is evident that the standard verification information is completely different from the subjective information to be verified, and cross-validation fails.

[0081] It should be noted that cases that fail cross-validation can be pushed to the to-do list of the consortium blockchain's disciplinary inspection and supervision node.

[0082] This reduces the long-standing problem of grassroots staff fabricating records and inflating achievements in order to obtain performance points, and improves the purity and objectivity of on-chain data.

[0083] In some embodiments, the handling of a burglary case involving a gang in a high-end residential community is taken as an example. The underlying business database contains unstructured electronic case files, including investigation and interrogation records, as well as structured ledgers, such as attendance records. Among them, the unstructured electronic case files are the original business data; the structured ledgers are the business ledger data.

[0084] After retrieving raw business data and business ledger data through the middleware server, entity extraction can be performed on the raw business data using a pre-defined large language model to obtain entity information; the entity information can then be organized to obtain the first structured feature data. Simultaneously, field mapping and enumeration value cleaning are performed on the business ledger data to obtain the second structured feature data; the police badge numbers and corresponding case numbers of the corresponding police officers are extracted from the first and second structured feature data respectively; based on the police badge numbers and case numbers, the first and second structured feature data are merged to obtain global structured data: {"Case Number":"kw001","Case Nature":"Burglary", "Amount Involved":125000, "Details of Participants": [{"Police Badge":"011","Role":"Organizer / Commander","Action":"Analysis and Arrest"}, {"Police Badge":"012","Role":"Scene Investigation","Action":"Fingerprint Extraction"}, {"Police Badge":"013","Role":"Interrogation and Case Handling","Action":"Overnight Interrogation"}, {"Police Badge":"014","Role":"Service Support","Action":"Cross-Provincial Escort"}]}. This global structured data summarizes the case-handling activities of police officers 011, 012, 013, and 014 in case number kw001. After this structured data is input into the consortium blockchain, a quantitative evaluation contract deployed on the pre-defined consortium blockchain is used to obtain the quantitative evaluation score corresponding to the global structured data and to obtain the digital digest corresponding to the original business data. The digital digest, business ledger data, and quantitative evaluation score are packaged, and corresponding timestamp tags and police execution type tags are added to the packaged data to obtain the packaged result data. The packaged result data is uploaded to the consortium blockchain for multi-node verification. The verified packaged result data is stored in the consortium blockchain's accompanying distributed ledger. This achieves multi-subject role identification and fine-grained quantitative on-chaining of unstructured case file data from the internal network, as well as silent evaluation of the entire chain and multiple subjects in this case. Furthermore, on-chain time-series data can be obtained based on the accompanying distributed ledger to enable subsequent personnel deployment.

[0085] Furthermore, tasks are deployed for each police officer based on on-chain time-series data, including: generating occupational feature vectors for each police officer based on on-chain time-series data; obtaining risk assessment vectors for each police officer; and deploying tasks for each police officer based on occupational feature vectors and risk assessment vectors.

[0086] In this way, by generating occupational feature vectors for each police officer based on on-chain time series data, and then deploying tasks for each police officer based on the occupational feature vectors and the risk assessment vectors for each police officer, the occupational features and risk assessments of the deployed police officers meet the requirements, thereby improving the rationality and accuracy of task deployment.

[0087] Furthermore, based on on-chain time series data, a professional feature vector corresponding to each police officer is generated, including: extracting several quantitative assessment scores for each police officer from the on-chain time series data; introducing a preset time decay function to obtain the time decay coefficient corresponding to each quantitative assessment score; obtaining the state time aggregate score for each police officer based on the time decay coefficient and the quantitative assessment score; for each police officer, dividing the state time aggregate score based on a preset capability dimension to obtain one or more state time aggregate scores corresponding to each capability dimension; then obtaining the business score corresponding to each capability dimension based on the state time aggregate score corresponding to each capability dimension; and obtaining the professional feature vector corresponding to each police officer based on each business score.

[0088] It should be noted that the time decay function can be an exponential decay function, a power decay function, a linear decay function, a logarithmic decay function, or other types of time decay functions.

[0089] In some embodiments, the exponential decay function is: ,in, To quantify the time decay coefficient corresponding to the evaluation integral; This is the preset first attenuation control coefficient. The larger its value, the faster the time attenuation coefficient decays. This is the cutoff time for the quantitative evaluation score; it should be noted that the cutoff time is the difference between the current time and the time represented by the timestamp label corresponding to the quantitative evaluation score.

[0090] The power function decay function is ,in, This is the preset second attenuation control coefficient. The larger the value, the faster the time attenuation coefficient decays.

[0091] The linear decay function is ,in, This is the preset third attenuation control coefficient. The larger the value, the faster the time attenuation coefficient decays.

[0092] The logarithmic decay function is ,in, This is the preset fourth decay control coefficient. The larger its value, the faster the time decay coefficient decays.

[0093] Furthermore, based on the time decay coefficient and the quantitative assessment score, the state time aggregate score of each police officer is obtained, including: for each police officer's police execution type, the weight corresponding to each quantitative assessment score is obtained based on the time decay coefficient; the weights are used to perform a weighted summation of each quantitative assessment score to obtain the state time aggregate score corresponding to each police execution type of each police officer.

[0094] It should be noted that the weights corresponding to each quantitative assessment score are obtained based on the time decay coefficient, meaning the time decay coefficient is directly determined as the weight. Alternatively, the time decay coefficients corresponding to each type of police duty performed by each police officer are normalized to obtain the weights corresponding to each quantitative assessment score.

[0095] It should be noted that different types of police duties correspond to different capability dimensions. For example: when the police duty type is handling emergency calls, the corresponding capability dimension may include communication skills; when the police duty type is handling administrative cases, the corresponding capability dimension may include administrative case handling skills; when the police duty type is handling criminal cases, the corresponding capability dimension may include criminal case handling skills; when the police duty type is mediating public order disputes, the corresponding capability dimension may include grassroots governance skills; when the police duty type is managing key personnel, the corresponding capability dimension may include grassroots governance skills; when the police duty type is inspecting business premises, the corresponding capability dimension may include grassroots governance skills; and when the police duty type is handling traffic accidents, the corresponding capability dimension may include standardized law enforcement skills.

[0096] It should be noted that for the same police officer, one police execution type corresponds to one state-time aggregate score; however, one capability dimension can correspond to one or more police execution types. Based on the preset capability dimension, each state-time aggregate score is divided to obtain multiple state-time aggregate scores corresponding to each capability dimension. Then, the multiple state-time aggregate scores corresponding to the capability dimension are the state-time aggregate scores of one or more police execution types corresponding to that capability dimension.

[0097] Furthermore, based on the state-time aggregated scores corresponding to each capability dimension, the business scores corresponding to each capability dimension are obtained. That is, the state-time aggregated scores are weighted using preset business weights to obtain the business scores corresponding to each capability dimension.

[0098] Furthermore, based on each business score, the professional feature vector corresponding to each police officer is obtained, including: normalizing the business scores of the same police officer; and then, for each police officer, the normalized business scores are arranged into an array according to a preset first order to obtain the professional feature vector corresponding to each police officer.

[0099] In some embodiments, after obtaining the occupational feature vectors corresponding to each police officer, a polygonal capability radar chart can be generated based on the occupational feature vectors. The occupational feature vectors are input into a pre-defined large model to generate political work comments describing the police officer corresponding to that occupational feature vector. The polygonal capability radar chart and the political work comments are then used to define the occupational profile of the police officer. This allows for a visual representation of the capability distribution of the police officer.

[0100] It should be noted that the default large model is a local large language model.

[0101] Furthermore, the risk assessment vectors for each police officer are obtained, including: obtaining the financial risk factor, physical fatigue factor, and mental state factor for each police officer; and concatenating the financial risk factor, physical fatigue factor, and mental state factor in a preset second order to obtain the risk assessment vector for each police officer.

[0102] It should be noted that obtaining the financial risk factors, physical fatigue factors, and mental state factors for each police officer includes: extracting financial risk data for each officer; obtaining financial risk factors based on the financial risk data; obtaining fatigue information for each officer; obtaining physical fatigue factors based on the fatigue information; and obtaining mental state information for each officer; obtaining mental state factors based on the mental state information.

[0103] It should be noted that the financial risk data refers to the frequency of credit delinquencies and the amount of litigation enforcement for police officers, or Boolean values ​​representing these values. Thus, by obtaining only the Boolean values ​​representing the frequency of credit delinquencies and the amount of litigation enforcement for police officers, without obtaining the specific values, zero-knowledge proof cryptography is employed. This achieves data usability without visibility while protecting the privacy of police officers.

[0104] Furthermore, based on the financial risk data, financial risk factors are obtained, that is, by using a preset step penalty function to normalize the financial risk data to obtain financial risk factors.

[0105] The tiered penalty function assigns different financial risk factors based on the frequency of credit delinquency and the amount of litigation enforcement. Specifically, the higher the frequency of credit delinquency and the larger the amount of litigation enforcement, the higher the financial risk for the police officer, and the higher the corresponding value of the financial risk factor.

[0106] Furthermore, fatigue information for each police officer is obtained, including: extracting the total dispatch time and night shift frequency of each police officer in a preset recent time period based on on-chain time series data; obtaining heart rate variability data and sleep monitoring data of each police officer; and identifying the total dispatch time, night shift frequency, heart rate variability data, and sleep monitoring data as fatigue information.

[0107] It should be noted that the preset recent time period is the period from now to the preset collection duration. In some embodiments, the preset collection duration is 7 days, 15 days, or 30 days, etc., and there is no limitation here.

[0108] The total response time is the sum of the case handling time of police officers in the recent period.

[0109] Night shift frequency refers to the frequency with which police officers work night shifts within a recent time period. Whether a police officer is working a night shift can be determined by the time corresponding to the timestamp tag. Based on this time, the frequency of a police officer's night shifts can be determined.

[0110] It should be noted that police officers can wear wearable devices that can monitor heart rate variability and sleep data in real time. The heart rate variability and sleep data can be uploaded and retrieved by the wearable devices.

[0111] Furthermore, obtaining physical fatigue factors based on fatigue information includes: inputting fatigue information into a preset fatigue accumulation assessment model to obtain physical fatigue factors. This fatigue accumulation assessment model can be a neural network model.

[0112] Furthermore, the psychological information of each police officer is obtained, including: retrieving the original operational data corresponding to each officer from the on-chain time-series data; inputting the original operational data into a large language model to conduct a psychological assessment of each officer based on the original operational data, obtaining an anxiety score for each officer; obtaining psychological test scores for each officer; and defining each anxiety score and each psychological test score as the psychological information of each officer.

[0113] Furthermore, mental state factors are obtained based on mental state information, including: performing a weighted average operation on anxiety scores and psychological assessment scores to obtain mental state factors.

[0114] It should be noted that the values ​​of the financial risk factor, physical fatigue factor, and mental state factor are all within the range of 0 to 1.

[0115] Furthermore, task deployment for each police officer is based on occupational feature vectors and risk assessment vectors, including: obtaining the task instructions for the task to be deployed; obtaining the duty sensitivity of the task to be deployed based on the task instructions; identifying and eliminating abnormal personnel among the police officers based on duty sensitivity and risk assessment vectors; determining the target personnel to perform the task to be deployed from the remaining police officers using a preset multi-objective optimization function based on occupational feature vectors; and deploying the task to the target personnel.

[0116] In this way, when the risk is too high, the active circuit breaker mechanism is triggered to identify and remove abnormal personnel, thereby reducing the risk of using police officers during duty.

[0117] It should be noted that obtaining the duty sensitivity of the task to be deployed based on the task instruction includes: extracting entities from the task instruction to obtain several business entities of the task to be deployed; performing a search operation in the preset duty score database to obtain the duty score of each business entity; obtaining the entity weight corresponding to each business entity; and using the entity weights to perform a weighted summation of each business entity to obtain the duty sensitivity.

[0118] In some embodiments, the business entity includes the level of involvement, number of firearms, level of confidentiality, and high-risk environment of the mission to be deployed.

[0119] The pre-defined duty score database stores the correspondence between each business entity and its duty score.

[0120] It should be noted that in the duty score database, the higher the level of the case, the more duty points it corresponds to; the higher the number of firearms, the more duty points it corresponds to; the higher the level of security, the more duty points it corresponds to; and the more dangerous the high-risk environment, the more duty points it corresponds to.

[0121] The entity weights corresponding to each business entity can be preset values.

[0122] Furthermore, based on duty sensitivity and risk assessment vectors, abnormal personnel are identified and removed from each police officer, including: when the duty sensitivity is greater than a preset sensitivity threshold, obtaining the police execution type corresponding to the task to be deployed; obtaining the dynamic risk factor corresponding to each police officer based on the police execution type and risk assessment vector; identifying the police officer corresponding to the dynamic risk factor that is greater than or equal to the preset risk threshold as an abnormal personnel; and removing the abnormal personnel.

[0123] It should be noted that the dynamic risk factors for each police officer are obtained based on the police execution type and the risk assessment vector, including: obtaining the risk factor weight vector corresponding to the police execution type for each police officer; and performing a dot product operation between the risk factor weight vector and the risk assessment vector to obtain the dynamic risk factor for that police officer.

[0124] It should be noted that the i-th element in the risk factor weight vector corresponds to the attention weight of the i-th element in the risk assessment vector. That is, the larger the value of the i-th element in the risk factor weight vector, the higher the attention given to the i-th element in the risk assessment vector, and the greater the risk associated with the type of police operation.

[0125] It should be noted that the objectives of a multi-objective optimization function include: maximizing capability, minimizing risk, and maximizing response.

[0126] Specifically, the capability maximization objective represents maximizing the sum of scores corresponding to the occupational feature vectors of the target personnel. The scores corresponding to the occupational feature vectors are obtained as follows: the preset feature weights corresponding to each element in the occupational feature vector are obtained; the preset feature weights are then used to perform a weighted summation of the elements in the occupational feature vector to obtain the score corresponding to the occupational feature vector.

[0127] The risk minimization objective represents minimizing the sum of dynamic risk factors for the identified target personnel;

[0128] The goal of maximizing response is to minimize the sum of the distances between the geographical locations of the identified target personnel and the locations corresponding to the tasks to be deployed.

[0129] Specifically, the geographical location of the target personnel can be obtained from their personal devices, such as user devices or body cameras worn by law enforcement officers. The location of the task to be deployed can be extracted from the task instructions of the task to be deployed.

[0130] It should be noted that the constraints of the multi-objective optimization function include the number of people and the qualifications of the personnel.

[0131] Specifically, the task instructions for a task to be deployed may include the required number of personnel and required qualifications.

[0132] The headcount constraint means that the number of target personnel must equal the number of required personnel.

[0133] The qualification requirement indicates that the qualifications of the target personnel meet the qualification requirements.

[0134] Based on the aforementioned objectives and constraints, a multi-objective optimization function can be constructed to determine the target personnel. Then, a pre-defined non-dominated sorting genetic algorithm or particle swarm optimization algorithm is used to solve this multi-objective optimization function, obtaining several target personnel and their respective job assignment schemes. The job assignment scheme can be determined by the required qualifications.

[0135] It should be noted that task deployment for target personnel involves sending the job assignment plan for each target person to the command center, which then triggers the command center to issue personnel instructions for the tasks to be deployed to the target personnel, so that the target personnel can execute the tasks to be deployed.

[0136] In some embodiments, the security work for an upcoming "high-level international conference" requires the deployment of over a hundred police officers and the need to ensure absolute safety.

[0137] The system then issues task instructions specifying security levels, core area security checks, perimeter bomb disposal, and the required qualifications and personnel for mobile emergency response. It then acquires on-chain time-series data and generates occupational characteristic vectors for each police officer; it also acquires risk assessment vectors for each officer.

[0138] The task sensitivity of the task to be deployed is obtained based on the task instruction. If the sensitivity exceeds a preset threshold, the police execution type corresponding to the task is obtained. Based on this execution type and risk assessment vector, the dynamic risk factor for each police officer is obtained. Police officers with dynamic risk factors greater than or equal to the preset risk threshold are identified as aberrant personnel. For example, although Officer E has experience in large-scale security operations, on-chain data shows that he has participated in three consecutive high-intensity overnight shifts this month, resulting in an excessive physical fatigue factor in his risk assessment vector, causing his dynamic risk factor to exceed the risk threshold. Officer F's recent psychological assessment in the smart political work database shows a high-pressure state, and he has a record of large-scale abnormal debt disputes and litigation, triggering a dual high-sensitivity risk warning for both mental and financial matters, causing his dynamic risk factor to exceed the risk threshold. Both Officer E and Officer F are identified as aberrant personnel. Officers E and F are then removed from the list. Then, using a preset multi-objective optimization function, the target personnel to be deployed are determined from the remaining police officers based on their occupational feature vectors; and the task is deployed to the target personnel.

[0139] It should be noted that the consortium blockchain can also deploy adaptive smart contracts based on reinforcement learning algorithms. These adaptive smart contracts receive real-time heatmap data of police incidents within a preset area. When a preset type of police incident is detected to deviate from the historical baseline, such as a surge in telecommunications fraud incidents, the weights of the feature parameters corresponding to that type of police action in the quantitative evaluation contract can be adjusted. At the same time, when the case status changes to the preset transfer for review and prosecution status, hash locking technology can be used to relay the digital digest and evidence compliance points of the case on the public security intranet blockchain to the political and legal committee's collaborative judicial blockchain.

[0140] This solution achieves the following results:

[0141] (1) The local introduction of a large language model to process police logs, namely structured business ledger data and unstructured raw business data, greatly improves the extraction and recall rate of key elements in case handling. Since it is processed locally, it improves the security bottom line of business ledger data and raw business data not leaving the network.

[0142] (2) By utilizing the quantitative evaluation contract and multi-node verification mechanism of the consortium blockchain, the performance indicators of police officers, namely packaged result data, are realized. The immutability of the data is ensured, and a highly credible accompanying evidence storage system is constructed. The on-chain time series data composed of packaged result data provides a legally valid digital archive for the full career management of police officers.

[0143] (3) By using risk assessment vectors to quantify implicit physical and mental risks into feature vectors to participate in the scheduling and deployment calculation of police officers, an active circuit breaker mechanism can be triggered to identify and remove abnormal personnel when the risk is too high, thereby reducing the risk of using police officers in duty.

[0144] (4) By deeply binding the objective physical state of police personnel deployment based on consortium blockchain with front-end hardware devices, namely law enforcement recorders and equipment storage cabinets, and cross-verifying with subjective information to be verified, cross-modal mutual verification of subjective data recorded by personnel and objective perception of the Internet of Things is realized, forming an unbreakable data ownership closed loop and improving data reliability.

[0145] (5) By introducing zero-knowledge proof technology, the privacy of police officers is protected while data is made available but not visible, thus completing the task of mine clearance and circuit breaking; at the same time, it has the ability to obtain quantitative evaluation points through quantitative evaluation contracts, getting rid of the lag of static assessment, and becoming a "smart brain" that can automatically carry out macro-control of police resources according to the security situation in the jurisdiction, realizing the optimal solution of compliant scheduling and dynamic game:

[0146] Combination Figure 2As shown in the figure, this disclosure provides a police officer deployment device 200 based on a consortium blockchain. The device includes: a first acquisition module 201, a scoring module 202, a second acquisition module 203, and a deployment module 204.

[0147] The first acquisition module 201 is configured to acquire and merge structured business ledger data and unstructured raw business data to obtain global structured data characterizing the case handling situation of police officers.

[0148] Scoring module 202 is configured to obtain quantitative evaluation scores corresponding to global structure data by using a quantitative evaluation contract deployed on the consortium blockchain;

[0149] The second acquisition module 203 is configured to acquire on-chain time series data corresponding to each police officer based on raw business data, business ledger data and quantitative evaluation scores; the on-chain time series data describes the set of professional time characteristics of police officers within their professional career cycle;

[0150] Deployment module 204 is configured to deploy tasks to police officers based on on-chain time series data.

[0151] The police officer deployment device based on a consortium blockchain provided in this disclosure acquires and merges structured business ledger data and unstructured raw business data to obtain global structural data characterizing the case-handling performance of police officers. A quantitative evaluation contract deployed on a pre-defined consortium blockchain is used to obtain quantitative evaluation scores corresponding to the global structural data. Based on the raw business data, business ledger data, and quantitative evaluation scores, on-chain time-series data within each police officer's career cycle is obtained. Then, tasks are deployed to each police officer based on the on-chain time-series data. In this way, by acquiring and merging structured business ledger data and unstructured raw business data, multi-source data fusion is achieved, enabling the merged global structural data to comprehensively characterize the case-handling performance of police officers. Then, by using a quantitative evaluation contract deployed on a pre-defined consortium blockchain to obtain quantitative evaluation scores corresponding to the global structural data, the global structural data is quantified, allowing the quantitative evaluation scores to characterize the case-handling capabilities of police officers. Then, based on the original business data, business ledger data, and quantitative evaluation scores, on-chain time series data within the career cycle of each police officer is obtained, so that the on-chain time series data can comprehensively and accurately represent the case handling situation of each police officer within the career cycle. Then, based on the on-chain time series data, tasks are deployed to each police officer, so that the deployed tasks can be accurately matched with the police officers, thereby improving the rationality and matching degree of the deployment of police officers.

[0152] Furthermore, the first acquisition module is configured to acquire and merge structured business ledger data and unstructured raw business data in the following manner to obtain global structured data representing the case-handling situation of police officers: using a pre-set middleware server to collect business ledger data and raw business data corresponding to police officers from several pre-set public security business systems; using a pre-set large language model to extract entities from the raw business data to obtain entity information; organizing the entity information to obtain first structured feature data; performing field mapping and enumeration value cleaning on the business ledger data to obtain second structured feature data; extracting the police officer's badge number and corresponding case number from the first and second structured feature data respectively; and fusing the first and second structured feature data based on the badge number and case number to obtain global structured data.

[0153] Furthermore, the evaluation module is configured to obtain the quantitative evaluation score corresponding to the global structure data using a quantitative evaluation contract deployed on the consortium blockchain in the following ways: using the quantitative evaluation contract to determine the police execution type of the global structure data; using the quantitative evaluation contract to extract the feature parameters corresponding to the police execution type from the global structure data; using the quantitative evaluation contract to obtain the benchmark value corresponding to the police execution type, the weight corresponding to each feature parameter, and the reward / penalty value corresponding to each feature parameter; and using the quantitative evaluation contract to obtain the quantitative evaluation score based on the weight, benchmark value, and reward / penalty value.

[0154] Furthermore, the second acquisition module is configured to acquire on-chain time-series data corresponding to each police officer based on the original business data, business ledger data, and quantitative assessment scores in the following manner: acquiring the digital digest corresponding to the original business data; packaging the digital digest, business ledger data, and quantitative assessment scores, and adding their corresponding timestamp tags and police execution type tags to the packaged data to obtain the packaged result data; uploading the packaged result data to the consortium blockchain to utilize the consortium blockchain for multi-node verification of the packaged result data; storing the verified packaged result data in the consortium blockchain's accompanying blockchain distributed ledger; and reading all verified packaged result data corresponding to each police officer in real time from the accompanying blockchain distributed ledger to obtain on-chain time-series data.

[0155] Furthermore, the second acquisition module is configured to acquire the original business data, including the subjective business text of police officers handling cases, and upload the packaged result data to the consortium blockchain in the following manner: acquire the law enforcement record data of police officers handling cases; perform cross-validation on the subjective business text using the law enforcement record data; and upload the packaged result data to the consortium blockchain if the cross-validation passes.

[0156] Furthermore, the deployment module is configured to deploy tasks to each police officer based on on-chain time series data in the following manner: generating occupational feature vectors for each police officer based on on-chain time series data; obtaining risk assessment vectors for each police officer; and deploying tasks to each police officer based on the occupational feature vectors and risk assessment vectors.

[0157] Combination Figure 3 As shown, this disclosure provides another police officer deployment device 300 based on a consortium blockchain, including a processor 301 and a memory 302. Optionally, the device may further include a communication interface 303 and a bus 304. The processor 301, communication interface 303, and memory 302 can communicate with each other via the bus 304. The communication interface 303 can be used for information transmission. The processor 301 can call logical instructions in the memory 302 to execute the police officer deployment method based on a consortium blockchain described in the above embodiment.

[0158] Furthermore, the logic instructions in the aforementioned memory 302 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0159] The memory 302, as a storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 301 executes functional applications and data processing by running the program instructions / modules stored in the memory 302, thereby realizing the police personnel deployment method based on consortium blockchain in the above embodiments.

[0160] The memory 302 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 302 may include high-speed random access memory and may also include non-volatile memory.

[0161] This disclosure provides an electronic device, including: an electronic device body; and Figure 2 or Figure 3 The device shown is a police officer deployment device based on a consortium blockchain.

[0162] Please see Figure 4 , Figure 4 This diagram illustrates the deployment environment for police officers based on a consortium blockchain, as described in this solution.

[0163] like Figure 4As shown, Command Center 401 issues task instructions for the tasks to be deployed. Then, it receives feedback from electronic devices regarding the target personnel and their assigned roles for each task. Based on these target personnel, it then issues task instructions for the tasks to be deployed and their assigned roles to the target personnel.

[0164] Electronic device 402 is configured to acquire and integrate structured business ledger data and unstructured raw business data to obtain global structured data characterizing the case-handling situation of police officers; utilize a quantitative assessment contract deployed on a pre-defined consortium blockchain to obtain quantitative assessment scores corresponding to the global structured data; acquire on-chain time-series data for each police officer's career cycle based on raw business data, business ledger data, and quantitative assessment scores; generate career feature vectors for each police officer based on the on-chain time-series data; acquire risk assessment vectors for each police officer; and acquire task instructions for tasks to be deployed issued by command center 401. Based on these task instructions, the duty sensitivity of the tasks to be deployed is obtained. Based on duty sensitivity and risk assessment vectors, abnormal personnel are identified and eliminated from each police officer. Using a preset multi-objective optimization function, several target personnel to be deployed and their job assignment schemes are determined from the remaining police officers according to their occupational characteristic vectors. Then, each target person and their job assignment scheme are pushed to the command center to trigger the command center to issue the task instructions and job assignment schemes for the target personnel to be deployed, so as to deploy the target personnel to execute the task to be deployed.

[0165] This disclosure provides a storage medium storing computer-executable instructions configured to execute the aforementioned consortium blockchain-based police personnel deployment method.

[0166] The aforementioned storage media can be either transient computer-readable storage media or non-transitory computer-readable storage media. Non-transitory storage media include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and can also be transient storage media.

[0167] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0168] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0169] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for deploying police officers based on a consortium blockchain, characterized in that, include: Acquire and integrate structured business ledger data and unstructured raw business data to obtain global structured data characterizing the case-handling situation of police officers; The quantitative evaluation score corresponding to the global structure data is obtained by using a quantitative evaluation contract deployed on a pre-defined consortium blockchain. Based on the original business data, the business ledger data, and the quantitative evaluation scores, on-chain time series data of each police officer's career cycle is obtained. Tasks are deployed to each police officer based on the on-chain time series data.

2. The method according to claim 1, characterized in that, The process of acquiring and integrating structured business ledger data and unstructured raw business data to obtain global structured data characterizing the case-handling situation of police officers includes: The business ledger data and the original business data corresponding to police officers are collected from several pre-set public security business systems using a pre-set middleware server. Entity information is obtained by extracting entities from the original business data using a pre-defined large language model. Organize the entity information to obtain the first structured feature data; Field mapping and enumeration value cleaning are performed on the business ledger data to obtain the second structured feature data; Extract the police officer's badge number and the corresponding case number from the first structured feature data and the second structured feature data, respectively; The global structure data is obtained by fusing the first structured feature data and the second structured feature data based on the police number and case number.

3. The method according to claim 1, characterized in that, The step of obtaining the quantitative evaluation score corresponding to the global structure data using the quantitative evaluation contract deployed on the consortium blockchain includes: The quantitative evaluation contract is used to determine the police execution type of the global structure data; the quantitative evaluation contract is used to extract the feature parameters corresponding to the police execution type from the global structure data; The quantitative evaluation contract is used to obtain the baseline value corresponding to the police execution type, the weight corresponding to each of the feature parameters, and the reward / punishment value corresponding to each of the feature parameters; The quantitative evaluation score is obtained using the quantitative evaluation contract based on the weight, the benchmark value, and the reward / penalty value.

4. The method according to claim 1, characterized in that, The process of obtaining on-chain time-series data for each police officer based on the original business data, the business ledger data, and the quantitative evaluation scores includes: Obtain the digital digest corresponding to the original business data; The digital digest, the business ledger data, and the quantitative evaluation score are packaged together, and their corresponding timestamp tags and police execution type tags are added to the packaged data to obtain the packaged result data; The packaged result data is uploaded to the consortium blockchain so that the consortium blockchain can be used to perform multi-node verification of the packaged result data; The verified packaged result data is stored in the accompanying blockchain distributed ledger of the consortium blockchain; The on-chain time series data is obtained by reading all the verified packaged result data corresponding to each police officer in real time from the accompanying blockchain distributed ledger.

5. The method according to claim 4, characterized in that, The original business data includes the subjective business texts of police officers during case handling; uploading the packaged result data to the consortium blockchain includes: Obtain law enforcement records from police officers during case handling; The subjective business text is cross-validated using the law enforcement record data. If the cross-validation passes, the packaged result data is uploaded to the consortium blockchain.

6. The method according to claim 1, characterized in that, The task deployment for each police officer based on the on-chain time series data includes: Based on the on-chain time series data, generate occupational feature vectors for each police officer; Obtain the risk assessment vector corresponding to each police officer; Tasks are deployed to each police officer based on the occupational feature vector and the risk assessment vector.

7. A police personnel deployment device based on a consortium blockchain, characterized in that, include: The first acquisition module is configured to acquire and merge structured business ledger data and unstructured raw business data to obtain global structured data characterizing the case handling situation of police officers; The scoring module is configured to obtain the quantitative evaluation score corresponding to the global structure data by using a quantitative evaluation contract deployed on the consortium blockchain; The second acquisition module is configured to acquire on-chain time series data corresponding to each police officer based on the original business data, the business ledger data, and the quantitative evaluation score; the on-chain time series data describes the set of professional time characteristics of the police officer within his / her career cycle; The deployment module is configured to deploy tasks to each police officer based on the on-chain time-series data.

8. A police officer deployment device based on a consortium blockchain, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to execute the police officer deployment method based on any one of claims 1 to 6 when running the program instructions.

9. An electronic device, characterized in that, include: The electronic device itself; And the police officer deployment device based on consortium blockchain as described in claim 7 or claim 8.

10. A storage medium storing program instructions, characterized in that, When the program instructions are executed, they perform the police officer deployment method based on the consortium blockchain as described in any one of claims 1 to 6.

Images