WO2023039977A1

WO2023039977A1 - Law enforcement officer scheduling method and system, and computer apparatus and storage medium

Info

Publication number: WO2023039977A1
Application number: PCT/CN2021/124283
Authority: WO
Inventors: 梁立新; 沈永安; 林霖; 赵建
Original assignee: 深圳技术大学
Priority date: 2021-09-17
Filing date: 2021-10-18
Publication date: 2023-03-23
Also published as: CN113919655A

Abstract

A law enforcement officer scheduling method and system based on big data analysis of people's livelihood appeals, and a computer apparatus and a storage medium. The scheduling method comprises: acquiring people's livelihood appeal data, wherein the people's livelihood appeal data comprises the event type and occurrence time of people's livelihood appeals (S1); predicting a development tendency of the people's livelihood appeals according to the people's livelihood appeal data (S2); determining reference values of corresponding law enforcement officers according to the development tendency of the people's livelihood appeals (S3); and scheduling and assigning the law enforcement officers according to the reference values of the law enforcement officers (S4). By means of analyzing the acquired people's livelihood appeal data to obtain the development tendency of the people's livelihood appeals, the number of law enforcement officers required for handling the people's livelihood appeals is calculated according to the development tendency, so as to optimize personnel scheduling, thereby better solving and serving the people's livelihood appeals. The present invention is widely applied to the field of big data analysis.

Description

Law enforcement personnel dispatching method, system, computer device and storage medium

technical field

The invention relates to the field of big data analysis, in particular to a method, system, computer device and storage medium for dispatching law enforcement personnel based on big data analysis of people's livelihood demands.

Background technique

With the development of big data technology, the country advocates and vigorously develops the digitization and intelligence of government services, rationally uses big data analysis technology, and digs out the data of people's livelihood demands from multiple dimensions and deep levels, which can effectively provide the necessary data support for service-oriented government governance. . At present, the allocation and scheduling of law enforcement personnel to deal with people's livelihood appeals is relatively rigid, and it is impossible to flexibly and reasonably allocate the number of law enforcement personnel to people's livelihood appeals, resulting in a waste of law enforcement resources.

Contents of the invention

In view of at least one of the above technical problems, the purpose of the present invention is to provide a method for dispatching law enforcement personnel based on big data analysis of people's livelihood demands.

On the one hand, the embodiment of the present invention includes a method for dispatching law enforcement personnel based on big data analysis of people's livelihood demands, including:

Obtain data on people's livelihood appeals, where the data on people's livelihood appeals includes the event type and time of occurrence of people's livelihood appeals;

Predict the development trend of people's livelihood demands according to the data of people's livelihood demands;

According to the development trend of the people's livelihood demands, determine the reference value of the corresponding law enforcement officers;

According to the reference value of the law enforcement personnel, the law enforcement personnel are dispatched and assigned.

Further, it also includes:

Classify the people's livelihood demand data according to the type of event;

Transform the classified livelihood demands data into time series.

Further, the step of predicting the development trend of people's livelihood demands includes:

After processing the time series, a long-term trend is obtained;

The time series prediction algorithm is used to predict the long-term trend to obtain the development trend of people's livelihood demands.

Further, the step of obtaining the long-term change trend after processing the time series includes:

defining a normal range for said time series;

Extract outliers that deviate from the normal range, and the time series composed of the outliers is the accidental event sequence;

The long-term change trend is obtained by filtering the time series from which the occasional event sequence is removed.

Further, the step of defining the normal range of the time series includes:

According to the time series, Q _U is defined as the upper bound, Q _L is the lower bound, and the interval [Q _L -1.5*(Q _U -Q _L ), Q _U +1.5*(Q _U -Q _L )] is the normal range .

Further, according to the development trend of the people's livelihood demands, the step of determining the reference value of the corresponding law enforcement personnel includes:

According to the handling of different types of events by law enforcement officers, set corresponding weights for the types of people's livelihood appeal events;

The data of the development trend of all the above-mentioned people's livelihood demands are weighted and calculated to obtain the reference value of the corresponding law enforcement officers.

Further, it also includes: setting the time range of the data for weighted calculation according to the work attributes of the law enforcement officers.

On the other hand, the embodiment of the present invention also includes a law enforcement personnel dispatching system based on big data analysis of people's livelihood demands, including:

The first module is used to obtain data on people's livelihood appeals, and the data on people's livelihood appeals includes the event type and time of occurrence of people's livelihood appeals;

The second module is used to predict the development trend of people's livelihood demands according to the data of people's livelihood demands;

The third module is used to determine the reference value of corresponding law enforcement officers according to the development trend of the people's livelihood demands;

The fourth module is used for scheduling and assigning law enforcement personnel according to the reference value of the law enforcement personnel.

On the other hand, the embodiment of the present invention also includes a law enforcement personnel scheduling device based on big data analysis of people's livelihood demands, including a memory and a processor, the memory is used to store at least one program, and the processor is used to load the at least one A program, the processor is used to load the at least one program to execute the law enforcement personnel scheduling method based on big data analysis of people's livelihood demands.

On the other hand, the embodiment of the present invention also includes a storage medium, which stores a processor-executable program, wherein the processor-executable program is used to execute the livelihood-based A Law Enforcement Officer Scheduling Approach Requiring Big Data Analysis.

The beneficial effects of the present invention are: based on the processing and analysis of the big data of people's livelihood demands, the development trend of people's livelihood demands can be obtained, and the development trend includes the events of people's livelihood demands predicted at future time points, and the predicted results and actual conditions can be used to deal with the people's livelihood demands Evaluate the number of law enforcement personnel involved in the event, so that law enforcement personnel can be allocated and dispatched based on the reference value obtained from the assessment, better realize the allocation and utilization of human resources, and also facilitate the government to designate a reasonable plan for handling future incidents, and improve the effectiveness of law enforcement Efficiency, more convenient to serve the needs of the masses.

Description of drawings

Fig. 1 is the flow chart of the method for dispatching law enforcement personnel based on big data analysis of people's livelihood demands in an embodiment;

Fig. 2 is the sequence decomposition diagram that is used for illustration in the embodiment;

Fig. 3 is a sequence prediction diagram of unlicensed traveling merchants in the embodiment.

Fig. 4 is a sequence prediction diagram of public transportation class in the embodiment.

Detailed ways

Example 1

In this embodiment, the law enforcement personnel scheduling method based on big data analysis of people's livelihood appeals is realized under the background of "Internet + government services". With the development of society, people can send appeals to the government in various ways. For example, through phone calls, government service websites, government service APPs, etc. to feed back information to the government, the government can rationally use big data technology to collect the information and appeals of the masses, and dig out the data of people's livelihood appeals from multiple dimensions and in-depth, effectively Provide necessary data support for service-oriented government governance.

This embodiment provides a law enforcement personnel scheduling method based on big data analysis of people's livelihood demands, which is to analyze and process the acquired big data of people's livelihood demands to mine necessary data, and evaluate a reasonable scheduling method for law enforcement personnel resources, as shown in Figure 1 The flow chart of the dispatching method for law enforcement personnel based on big data analysis of people's livelihood demands includes:

S1. Acquire data on people's livelihood appeals, where the data on people's livelihood appeals includes event types and time of occurrence of people's livelihood appeals.

The way to obtain data on people’s livelihood needs can be collected through the Internet and various communication platforms. At present, governments at all levels have increased investment in the management of government affairs data, established data management bureaus, and used big data to varying degrees. The analysis method has achieved remarkable results in processing government data, and established a more complete integrated big data center for provinces, cities and counties. It can cooperate with other Internet companies to share big data information, such as cooperating with mobile phone manufacturers to collect data on people's livelihood demands generated by users when using mobile phones; cooperating with platforms such as Douyin, Kuaishou, and Weibo to receive user feedback and extract Out of the user's demands.

Big data technology can be used to classify trivial livelihood issues. The types of livelihood issues can be divided into unlicensed business, public transportation, sewer covers, education, daily life and other livelihood issues. When the masses send appeals to the government, the content can be classified and the time when the appeals are sent can be recorded, and the appeal events can be handled flexibly. The event types and occurrence time mentioned here generally refer to the types of appeal events made by users and It is not ruled out that there will be a certain time delay in the time to resolve the appeal.

S2. Predict the development trend of people's livelihood demands according to the data of people's livelihood demands.

Sequence decomposition of people's livelihood appeal data: the classified livelihood appeal events can be converted into a time series {x(t)} according to the classification of appeal events in units of days or a limited period of time. This sequence reflects the government or research institutions from various The law of changes in the number of people's livelihood appeal events obtained through channels over time.

The time series decomposition method is used to decompose the occasional event sequence. Extraction of sporadic event change e(t) sequence: sporadic events are composed of a series of outliers that deviate from the normal range, which will cause great interference to the final prediction results in the framework of this algorithm. Deterministic factors, many situations may lead to great changes in the number of people's livelihood appeal events, such as national policy releases, natural disasters, and perceived factors, etc. These uncertain factors often have a great impact on predicting the development trend of people's livelihood appeals , here the method of box plot in statistics is used to separate outliers. Define Q _U as the upper bound and Q _L as the lower bound, and its physical meaning is expressed as: most of the data in all observations are located in the interval [Q _L , Q _U ]. An outlier is defined as a value less than Q _L -1.5*(Q _U -Q _L ) or greater than Q _U +1.5*(Q _U -Q _L ) in the time series, and the corresponding point is an outlier point. The timing sequence composed of group points is the change e(t) of bit accidental events. Here, the upper bound Q _U is set to 90%, and the lower bound Q _L is set to 0%, and the upper bound and the next value can be set according to the actual situation.

According to the periodic characteristics of the people's livelihood appeal data, the long-term change trend L(t) is extracted from the time series {x(t)-e(t)} after removing the occasional event sequence. The moving average filtering method is used to extract the monthly change trend L(t) sequence, and the length of the sliding window function is 30 data points, which reflects the change law in units of months, and can limit other time spans to carry out long-term change trend L(t) Extracted, it may be related to long-term conditions such as economic development, weather changes, etc. The long-term change trend refers to the time series that remains after removing the occasional event sequence is stable and subject to certain restrictions. For example, the obtained people’s livelihood appeal events are generally affected by seasonality, and the summer people’s livelihood demand for water and electricity There will be more people's livelihood in autumn. The demand for meat, eggs and milk will increase. Different people's livelihood demands will produce different results during a certain period of the day. As it increases, the electricity used to return home at night will increase, and people's demands for electricity will also increase. There is a certain regularity in the long-term change trend by removing occasional events. The larger the time span obtained and the greater the number of events obtained, the stronger the regularity of the long-term change trend finally obtained.

Extract several types of sub-events with the largest demands, perform time series prediction on the long-term trend L(t) obtained by sequence decomposition, and use a time series prediction algorithm to perform time series prediction (such as LSTM/ARIMA/RNN, etc., according to the characteristics of experimental data Different prediction algorithms can be used), according to the characteristics of the time series of people’s livelihood appeals, and considering the seasonal characteristics of the people’s livelihood appeal data, 70% (should be greater than or equal to one year) of data is used as the training set, and the remaining 30% of the data is used as the test set. Predict the development trend of people's livelihood demands. The specific data volume of the training set and test set is allocated according to the actual situation.

It should be noted that the time series forecasting algorithm is a regression forecasting method, which belongs to quantitative forecasting. Its basic principle is: on the one hand, it recognizes the continuity of the development of things, uses past time series data for statistical analysis, and infers the development trend of things. On the other hand, fully consider the randomness caused by accidental factors, in order to eliminate the impact of random fluctuations, use historical data for statistical analysis, and properly process the data to predict trends. Time forecasting algorithms are available for short-term, medium-term and long-term forecasts. The long-term forecast is used here for the prediction of people's livelihood demand data because the people's livelihood demand is a long-term law. The use of short-term forecasting can use big data to predict people's livelihood demands for a period of time, such as a day, but the practical value of such predictions in practical applications is not as high as that of long-term forecasting. It is not accurate, and its data is mainly a method of dispatching personnel, and the frequent transfer of law enforcement personnel during the day is also unreasonable. It can be predicted by exponential smoothing method, that is, based on the actual number and forecast value of the previous period of historical data, and forecasted by exponential weighting. This method is essentially a method evolved from the inner weighted moving average method. The advantage is that as long as there are the actual data of the previous period and the forecast value of the previous period, the forecast value of the next period can be calculated, which can save a lot of data and data processing time, and reduce The storage capacity of the data is simple and convenient. The seasonal trend forecasting method predicts the seasonal change trend of economic things based on the cyclical seasonal change index that recurs every year. Different methods can be used to calculate the seasonal index. The commonly used methods are quarterly (monthly) average method and moving average method: a. Quarterly (monthly) average method. It is to average the values of each year in quarters (or months) and divide them by the total average of each year (or month) to obtain the quarter (month) index. This method can be used to analyze seasonal changes in economic matters such as production, sales, raw material reserves, and estimated capital turnover needs; b. Moving average method. That is to use the moving average to calculate the proportion to find the typical seasonal index.

S3, according to the development trend of the demands of the people's livelihood, determine the reference value corresponding to the law enforcement personnel.

According to the predicted development trend of various appeal events, due to the different division of law enforcement personnel, for example, the law enforcement personnel for unlicensed business incidents are mainly urban management, and the main law enforcement personnel for public transportation incidents are traffic police, etc., corresponding to each type of law enforcement Personnel, set a reasonable weight for each type of incident. For example, the weight of public transportation incidents to urban management law enforcement personnel is almost 0, which means that urban management law enforcement personnel will hardly handle public transportation incidents, and unlicensed The weight of the tourist category can be set to 0.6, the weight of the out-of-store business category can be set to 0.4, etc. (the specific weight setting can be flexibly adjusted according to local policies). For the standardized (normalized) forecast data, each Calculate the data of one day or a period of time, so as to obtain the reference value of one day or a cumulative period of time as the evaluation standard of personnel scheduling. If the reference value is high, more corresponding law enforcement personnel will be arranged for targeted law enforcement. A small number of law enforcement officers can optimize personnel scheduling and optimize the use of human resources.

S4. Scheduling and assigning law enforcement personnel according to the reference value of the law enforcement personnel.

According to the reference value of the law enforcement personnel obtained in the above embodiment, the actual situation is analyzed, and the corresponding law enforcement personnel are dispatched, which can solve the problem that the number of certain types of people's livelihood appeal events exceeds the execution of the corresponding law enforcement personnel in a certain period of time The ability to deal with people’s livelihood issues: For example, the predicted data shows that the urban management is dealing with unlicensed businessmen. The high reference value indicates that more urban management is needed to deal with unlicensed businessmen. The reference value of out-of-store business incidents is low, indicating that there is no need for too many urban management to deal with out-of-store business incidents, and the urban management that usually handles out-of-store business incidents can be assigned to deal with unlicensed businessmen incidents to achieve reasonable human resources. distribution and improve work efficiency. What is mentioned here is only an example of manpower dispatching, and the actual situation can be analyzed according to this logic, and then specific law enforcement personnel dispatching can be carried out.

Figure 2 uses the data of people's livelihood needs for a total of about 14 months from February 1, 2018 to May 5, 2019 in Pingshan District, Shenzhen. Through the above method steps, data modeling and cleaning are carried out first, and the 6 types of appeal data types with the largest weight are filtered out, and separated into occasional events e(t) and long-term development trends L(t). From the figure, it can be clearly seen that each The long-term change trend obtained is the original basis for future data prediction.

Figure 3 and Figure 4 are forecasted according to the long-term development trend L(t) obtained in Figure 2, using the LSTM algorithm (after comparing multiple algorithms, the LSTM algorithm has the best prediction accuracy and fit, and can also be used according to different experimental data Using different forecasting algorithms), according to the characteristics of the time series of people's livelihood appeals, taking into account the seasonal characteristics of the people's livelihood appeal data, take 85% (about one year) of data as the training set, and the remaining 15% (2 months) of data as the test set , to predict the development trend of people's livelihood demands. The prediction results of sub-events such as unlicensed businessmen and public transportation are shown in Figure 3 and Figure 4 respectively. It can be seen that the training part basically fits, and the test data part fits well. The degree of fit is also good, and the root mean square errors after data de-standardization are 0.61 and 0.12, respectively. Therefore, according to the obtained development trend, the people's livelihood demands that will occur in the future can be predicted more accurately.

Example 2

In this embodiment, by compiling the law enforcement personnel scheduling method based on the big data analysis of people's livelihood demands in Example 1 into a computer program, and writing the computer program into the computer hardware, a law enforcement personnel scheduling system based on the big data analysis of people's livelihood demands can be obtained , computer devices and storage media.

The law enforcement personnel dispatching system based on big data analysis of people's livelihood demands includes:

The first module, the second module, the third module and the fourth module may be hardware modules, software modules or a combination of hardware and software modules with corresponding functions on computer equipment such as servers.

The device for dispatching law enforcement personnel based on big data analysis of people's livelihood demands includes a memory and a processor, the memory is used to store at least one program, and the processor is used to load the at least one program to execute the cell dispatching method.

Write the above steps S1-S4 into a driver program, and write it into the existing display device and storage medium. When the computer program in the storage medium is read and executed, the control method can be executed, and the An existing display device becomes the display device in the first embodiment. Thereby reach the beneficial effect described in embodiment 1.

It should be noted that, unless otherwise specified, when a feature is called "fixed" or "connected" to another feature, it can be directly fixed and connected to another feature, or indirectly fixed and connected to another feature. on a feature. In addition, descriptions such as up, down, left, and right used in the present disclosure are only relative to the mutual positional relationship of the components of the present disclosure in the drawings. As used in this disclosure, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. In addition, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by those skilled in the art. The terms used in the description of this embodiment are only for describing specific embodiments, not for limiting the present invention. The term "and/or" used in this embodiment includes any combination of one or more related listed items.

It should be understood that although the terms first, second, third etc. may be used in the present disclosure to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish elements of the same type from one another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the present disclosure. The use of any and all examples, or exemplary language ("such as", "such as", etc.) provided in the examples is intended merely to better illuminate the examples of the invention and will not cast a shadow on the scope of the invention unless otherwise claimed impose restrictions.

It should be appreciated that embodiments of the invention may be realized or implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods can be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, where the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the specific Methods and Figures described in the Examples. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, the programs can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on an application specific integrated circuit programmed for this purpose.

Furthermore, operations of processes described in this embodiment may be performed in any suitable order unless otherwise indicated by this embodiment or otherwise clearly contradicted by context. The processes described in this embodiment (or variants and/or combinations thereof) can be executed under the control of one or more computer systems configured with executable instructions, and can be executed as code jointly executed on one or more processors (eg, executable instructions, one or more computer programs, or one or more applications), hardware or a combination thereof. The computer program comprises a plurality of instructions executable by one or more processors.

Further, the method can be implemented in any type of computing platform operably connected to a suitable one, including but not limited to personal computer, minicomputer, main frame, workstation, network or distributed computing environment, stand-alone or integrated computer platform, or communicate with charged particle tools or other imaging devices, etc. Aspects of the invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or written storage medium, RAM, ROM, etc., such that they are readable by a programmable computer, when the storage medium or device is read by the computer, can be used to configure and operate the computer to perform the processes described herein. Additionally, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described in this embodiment includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein.

Computer programs can be applied to input data to perform the functions described in this embodiment, thereby transforming the input data to generate output data stored to non-volatile memory. Output information may also be applied to one or more output devices such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on a display.

The above is only a preferred embodiment of the present invention, and the present invention is not limited to the above-mentioned implementation, as long as it achieves the technical effect of the present invention by the same means, within the spirit and principles of the present invention, any Any modification, equivalent replacement, improvement, etc., shall be included within the protection scope of the present invention. Various modifications and changes may be made to the technical solutions and/or implementations within the protection scope of the present invention.

Claims

The dispatching method of law enforcement personnel based on big data analysis of people's livelihood demands is characterized in that it includes:

Obtain data on people's livelihood appeals, where the data on people's livelihood appeals includes the event type and time of occurrence of people's livelihood appeals;

Predict the development trend of people's livelihood demands according to the data of people's livelihood demands;

According to the development trend of the people's livelihood demands, determine the reference value of the corresponding law enforcement officers;

According to the reference value of the law enforcement personnel, the law enforcement personnel are dispatched and assigned.
According to claim 1, the method for dispatching law enforcement personnel based on big data analysis of people's livelihood demands, is characterized in that it also includes:

Classify the people's livelihood demand data according to the type of event;

Transform the classified livelihood demands data into time series.
According to claim 2, the method for dispatching law enforcement personnel based on big data analysis of people's livelihood demands, wherein the step of predicting the development trend of people's livelihood demands comprises:

After processing the time series, a long-term trend is obtained;

The time series prediction algorithm is used to predict the long-term trend to obtain the development trend of people's livelihood demands.
The law enforcement personnel dispatching method based on big data analysis of people's livelihood demands according to claim 3, wherein the step of obtaining a long-term change trend after processing the time series comprises:

defining a normal range for said time series;

Extract outliers that deviate from the normal range, and the time series composed of the outliers is the accidental event sequence;

The long-term change trend is obtained by filtering the time series from which the occasional event sequence is removed.
The law enforcement personnel scheduling method based on big data analysis of people's livelihood demands according to claim 4, wherein the step of defining the normal range of the time series comprises:

According to the time series, Q U is defined as the upper bound, Q L is the lower bound, and the interval [Q L -1.5*(Q U -Q L ), Q U +1.5*(Q U -Q L )] is the normal range .
According to claim 1, the method for dispatching law enforcement officers based on big data analysis of people's livelihood demands, characterized in that, according to the development trend of the people's livelihood demands, the step of determining the reference value of the corresponding law enforcement officers comprises:

According to the handling of different types of events by law enforcement personnel, corresponding weights are set for the types of the people's livelihood appeal events; weighted calculations are made for all the data of the development trend of the people's livelihood appeals, and reference values for corresponding law enforcement personnel are obtained.
The method for dispatching law enforcement personnel based on big data analysis of people's livelihood demands according to claim 6, further comprising: setting a time range for weighted calculation data according to the work attributes of law enforcement personnel.
A law enforcement personnel dispatching system based on big data analysis of people's livelihood demands, characterized in that it includes:

The first module is used to obtain the data of people's livelihood appeals, and the data of people's livelihood appeals includes the event type and time of occurrence of people's livelihood appeals;

The second module is used to predict the development trend of people's livelihood demands according to the data of people's livelihood demands;

The third module is used to determine the reference value of corresponding law enforcement officers according to the development trend of the people's livelihood demands;

The fourth module is used for scheduling and assigning law enforcement personnel according to the reference value of the law enforcement personnel.
A computer device, characterized by comprising a memory and a processor, the memory is used to store at least one program, and the processor is used to load the at least one program to execute the method according to any one of claims 1-7.
A storage medium storing a processor-executable program therein, wherein the processor-executable program is used to execute the method according to any one of claims 1-7 when executed by a processor.