Personnel risk grade evaluation method, terminal device and storage medium

Abstract

The invention relates to a personnel risk grade evaluation method, terminal equipment and a storage medium. The method comprises the following steps: collecting related data of personnel and events in a research area; constructing a personnel information basic library and an event information basic library; constructing a personnel element reference library and an event element reference library; related personnel and related events in the social security event information are extracted; calculating a personnel base number of related personnel, an event base number of related events, a relation coefficient, a personnel gain coefficient and an event gain coefficient; calculating the risk value of the related personnel to each related event related to the related personnel, and accumulating the risk values of all related events related to each related personnel to obtain the personnel risk index of each related personnel; and according to the size relationship between the personnel risk index and the risk index threshold, judging the risk level of each related personnel. Various potential risk personnel can be found in time, and the social safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a personnel risk level evaluation method, terminal equipment and storage medium. Background Art

[0002] Nowadays, with the development of society and economic growth, various events in daily work and life, such as family marriage, neighborhood, campus, economy, and social security, have also come along and are becoming more and more frequent, posing a certain degree of threat to social stability and prosperity. If timely intervention and effective prevention are not carried out, serious social events may occur at any time, causing huge losses to people's lives and property. Because in the face of social governance, post-event control is not as good as in-event control, and in-event control is not as good as pre-event control, therefore, how to timely discover risk personnel, prevent in advance, and resolve to avoid the occurrence or escalation of time events has become increasingly important.

[0003] In the existing technology, it is more about the dimensions of the parties involved in existing cases or disputes and early warning of event risk prediction, but lacks comprehensive and integrated analysis and evaluation of the specific situation of the large number of migrant workers in the city. With the development of artificial intelligence and big data technology, especially the application of big model technology and the establishment of intelligent computing centers in various places in recent years, larger-scale full-volume data calculation and analysis has become possible and more convenient, enabling a larger-scale and more comprehensive personnel risk analysis. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a personnel risk level evaluation method, a terminal device and a storage medium.

[0005] The specific plan is as follows:

[0006] A method for evaluating personnel risk level comprises the following steps:

[0007] S1: Collect data on people and events in the study area;

[0008] S2: Build a basic database of personnel information and event information based on the collected data;

[0009] S3: Select fields related to social security events from various fields contained in the personnel information basic database as personnel factors, set weights for various personnel factors, and build a personnel factor benchmark database to record various personnel factor information and weights of various personnel factors of various personnel contained in the personnel information basic database;

[0010] Select fields related to social security events from various fields included in the event information base as event elements, set weights for various event elements, and build an event element benchmark library to record event element information and weights of various event elements for various events included in the event information base;

[0011] S4: For the social security event information to be analyzed in the study area, extract the personnel as relevant personnel, extract the events as relevant events, and extract all personnel elements corresponding to the relevant personnel and all event elements corresponding to the relevant events;

[0012] S5: according to all personnel factors corresponding to the relevant personnel, the weight of each personnel factor is searched from the personnel factor benchmark library, and all personnel factors corresponding to each relevant personnel are weighted and summed to obtain the personnel base number of the relevant personnel;

[0013] According to all event elements corresponding to the relevant events, the weight of each event element is searched from the event element benchmark library, and all event elements corresponding to each relevant event are weighted summed to obtain the event cardinality of the relevant event;

[0014] S6: Calculate the relationship coefficient between the relevant persons and the relevant events according to whether the relevant persons and the relevant events are related;

[0015] S7: extracting all associated persons corresponding to the associated person from the personnel relationship field of the personnel information basic database, and generating a personnel gain coefficient of the associated person based on the positive and negative characteristics of the associated person related to the social security incident;

[0016] S8: searching for all events corresponding to the relevant personnel from the event information base, and generating an event gain coefficient of the relevant event based on the positive and negative characteristics of the found events;

[0017] S9: Calculate the risk value of each relevant person in the event information to be analyzed for each relevant event related to him according to the person base, event base, relationship coefficient, person gain coefficient and event gain coefficient, and accumulate the risk values ​​of all relevant events related to each relevant person within a period of time to obtain the person risk index of each relevant person;

[0018] S10: Determine the risk level of each relevant person according to the relationship between the calculated personnel risk index and the risk index thresholds corresponding to the different risk levels.

[0019] Furthermore, step S1 also includes parsing the collected raw data, extracting feature data related to people and events, and labeling the extracted feature data with corresponding people or events.

[0020] Furthermore, when calculating the relationship coefficient between the relevant persons and the relevant events, step S6 not only considers the need for the relevant persons and the relevant events to be associated, but also considers the degree of association between the relevant persons and the relevant events.

[0021] Furthermore, the degree of association between the relevant personnel and the relevant events is calculated by whether the relevant personnel have positive characteristics that have an inhibitory effect on social security events and negative characteristics that have a promoting effect on social security events; if the relevant personnel have positive characteristics, the degree of association between the relevant personnel and the relevant events is reduced; if the relevant personnel have negative characteristics, the degree of association between the relevant personnel and the relevant events is increased.

[0022] Furthermore, the risk value P of the relevant person t to the relevant event i related to him ti The calculation formula is:

[0023] P ti =PR t ×ER i ×PER ti ×PGC t ×EGC t

[0024] Among them, PR t Indicates the number of personnel related to person t, ER i Represents the event cardinality of related event i, PER ti represents the relationship coefficient between relevant person t and relevant event i, PGC t Represents the personnel gain coefficient of the relevant personnel t, EGC t Represents the event gain coefficient of relevant person t.

[0025] Furthermore, the risk values ​​of all relevant events related to each relevant person within a period of time are accumulated, and it is determined whether the risk value corresponding to each relevant event is less than the risk value threshold. If so, the risk value of the relevant event is not accumulated during the accumulation.

[0026] A terminal device for evaluating personnel risk level includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described above in the embodiment of the present invention are implemented.

[0027] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above in an embodiment of the present invention are implemented.

[0028] The present invention adopts the above technical solution, and in social governance, various potential risk personnel can be discovered in a timely manner. Through targeted early prevention, it helps to reduce the occurrence of various social incidents in the process of urban management, enhance social security, and promote social harmony and stable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 Shown is a flow chart of a method according to a first embodiment of the present invention. DETAILED DESCRIPTION

[0030] To further illustrate various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementations and advantages of the present invention.

[0031] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0032] Embodiment 1:

[0033] The embodiment of the present invention provides a method for evaluating the risk level of personnel. Figure 1 As shown, the method comprises the following steps:

[0034] S1: Collect data on people and events in the study area.

[0035] Preferably, when collecting relevant data on personnel, the personnel information of all permanent residents and floating populations in the study area and the relationship information between personnel should be collected; when collecting relevant data on events, information related to all events that occurred in the study area within a period of time should be collected.

[0036] The events include events with negative characteristics and events with positive characteristics. In this embodiment, events with negative characteristics are referred to as social security events (i.e., events that undermine social security), such as fighting, theft, etc. Events with positive characteristics are events that maintain social security, such as rescuing and helping others.

[0037] In this embodiment, data is obtained from multiple channels by accessing a third-party system, such as accessing original data such as conflicts and disputes within the city; accessing original data such as public opinion information within the city; accessing original data such as police information, case information within the city; accessing original data such as one-standard-N-real and family tree within the city; accessing original data such as ticket travel information, hotel and travel registration information within the city; accessing original data such as cameras within the city.

[0038] The collected data can be used to extract the features of people and events needed in subsequent steps. In order to facilitate subsequent processing, this embodiment also includes data parsing of the collected raw data, extracting feature data related to people and events, and labeling the extracted feature data with corresponding people or events. Through data parsing, the raw data can be split and classified into feature data of different people and different events.

[0039] S2: Build a personnel information base and an event information base based on the collected data.

[0040] In this embodiment, both the personnel information basic database and the event information basic database are in tabular form. In the personnel information basic database, rows represent personnel, and columns represent fields corresponding to personnel characteristics, such as gender, age, occupation, personal emotions, personality, family members, etc.; in the event information basic database, rows represent events, and columns represent fields corresponding to event characteristics, such as location and time of occurrence.

[0041] S3: Select fields related to social security events from the fields included in the personnel information base as personnel elements, set the weights of the personnel elements, and build a personnel element benchmark library to record the personnel element information and weights of the personnel elements of each person included in the personnel information base. Select fields related to social security events from the fields included in the event information base as event elements, set the weights of the event elements, and build an event element benchmark library to record the event element information and weights of the event elements of each event included in the event information base.

[0042] Fields related to social security events need to be selected by technical personnel from all fields in the personnel information base and the event information base according to actual business needs. When selecting, priority should be given to fields that have a greater impact on social security events, such as occupation, emotion, location, time of occurrence, etc.

[0043] S4: For the social security event information to be analyzed in the study area, extract the personnel as relevant personnel, extract the events as relevant events, and at the same time extract all personnel elements corresponding to the relevant personnel and all event elements corresponding to the relevant events.

[0044] S5: According to all personnel elements corresponding to the relevant personnel, the weight of each personnel element is searched from the personnel element benchmark library, and all personnel elements corresponding to each relevant personnel are weighted summed up to obtain the personnel cardinality of the relevant personnel; according to all event elements corresponding to the relevant events, the weight of each event element is searched from the event element benchmark library, and all event elements corresponding to each relevant event are weighted summed up to obtain the event cardinality of the relevant events.

[0045] In calculating the number of people, the value of each person factor used for weighted summation can be based on a pre-set value benchmark for each person factor. For example, if the person factor is emotion, the value when the emotion is angry is greater than the value when the emotion is calm. Similarly, in calculating the number of events, the value of each event factor used for weighted summation can be based on a pre-set value benchmark for each event factor. For example, if the event factor is occurrence time, the value when the occurrence time is at night is greater than the value when the occurrence time is during the day.

[0046] S6: Calculate the relationship coefficient between the relevant persons and the relevant events based on whether the relevant persons and the relevant events are related.

[0047] Further, for the accuracy of the subsequent evaluation results, in addition to considering the need for the relevant personnel and the relevant events to be associated, this embodiment also considers the degree of association between the relevant personnel and the relevant events when calculating the relationship coefficient between the relevant personnel and the relevant events. In this embodiment, the degree of association between the relevant personnel and the relevant events is calculated by whether the relevant personnel have positive characteristics that have an inhibitory effect on social security events and negative characteristics that have a promoting effect on social security events; if the relevant personnel have positive characteristics, the degree of association between the relevant personnel and the relevant events is reduced; if the relevant personnel have negative characteristics, the degree of association between the relevant personnel and the relevant events is increased. For example, when the relevant personnel and the relevant events are not associated, the relationship coefficient is set; when there is an association, the initial relationship coefficient is set to 1, and then it is increased or decreased based on 1 according to the degree of association. For example, when the personnel elements corresponding to the extracted relevant personnel include emotions, if the emotions are negative emotions such as irritability and anger, the relevant personnel have negative characteristics, and the degree of association between the relevant personnel and the relevant events is increased; if the personality of the relevant personnel is found to be a negative personality such as irritability from the personnel information base, the relevant personnel have negative characteristics, and the degree of association between the relevant personnel and the relevant events is increased. On the contrary, if the corresponding emotions or personality traits are all positive, then the relevant person has positive traits, which reduces the degree of association between the relevant person and the relevant event.

[0048] S7: extracting all associated persons corresponding to the relevant person from the personnel relationship field of the personnel information basic database, and generating a personnel gain coefficient of the relevant person based on the positive and negative characteristics of the associated person related to the social security incident.

[0049] For example, if the initial personnel gain coefficient is set to 1, when the related personnel have positive characteristics that have an inhibitory effect on social security incidents, the personnel gain coefficient of the related personnel will be reduced; when the related personnel have negative characteristics that have a promoting effect on social security incidents, the personnel gain coefficient of the related personnel will be increased.

[0050] Related personnel can be extracted from the fields of related personnel recorded in the personnel information basic database, such as the family member field. If a related person's family members include a wife, and the character of his wife is irritable, it means that the related person has negative characteristics, and the personnel gain coefficient of the related person is increased; when the character of his wife is approachable, it means that the related person has positive characteristics, and the personnel gain coefficient of the related person is reduced.

[0051] S8: Searching for all events corresponding to the relevant personnel from the event information base, and generating an event gain coefficient of the relevant event based on the positive and negative characteristics of the found events.

[0052] If the initial event gain coefficient is set to 1, when the found event has positive characteristics, the event gain coefficient of the related event is reduced; when the found event has negative characteristics, the event gain coefficient of the related event is increased.

[0053] S9: Calculate the risk value of each relevant person in the event information to be analyzed for each relevant event based on the personnel base, event base, relationship coefficient, personnel gain coefficient and event gain coefficient, and add up the risk values ​​of all relevant events related to each relevant person within a period of time to obtain the personnel risk index of each relevant person. The specific calculation formula is as follows:

[0054]

[0055] Among them, RV t represents the personnel risk index of relevant personnel t, i represents the sequence number of the relevant event, n represents the total number of relevant events, PR t Indicates the number of personnel related to person t, ER i Represents the event cardinality of related event i, PER ti represents the relationship coefficient between relevant person t and relevant event i, PGC t Represents the personnel gain coefficient of the relevant personnel t, EGC t P represents the event gain coefficient of relevant person t. ti =PR t ×ER i ×PER ti ×PGC t ×EGC t Represents the risk value of relevant person t to relevant event i.

[0056] The above period of time may be a recent period of time, such as within the past month.

[0057] Furthermore, in this embodiment, a risk value threshold (such as 0.001) corresponding to an invalid result is set, that is, if P tiIf it is less than the risk value threshold, it means that the personnel risk index calculation of event i for person t is an invalid value. In order to avoid its rigidity, the invalid risk value P is deleted during the cumulative calculation. ti , only the accumulation of the remaining n-1 risk values ​​is calculated.

[0058] S10: Determine the risk level of each relevant person according to the relationship between the calculated personnel risk index and the risk index thresholds corresponding to the different risk levels.

[0059] In this embodiment, the personnel risk level is set to four levels, namely high risk, medium risk, low risk and normal, and the corresponding risk index thresholds include three, namely LV1, LV2, and LV3, where:

[0060] a) Personnel with a risk index greater than or equal to LV1 are high-risk potential personnel;

[0061] b) Personnel whose risk index is greater than or equal to LV2 and less than LV1 are potential personnel with medium risk;

[0062] c) Personnel whose risk index is greater than or equal to LV3 and less than LV2 are low-risk potential personnel;

[0063] d) Personnel whose risk index is less than LV3 are normal personnel.

[0064] Those skilled in the art can continuously optimize and adjust the above risk levels and corresponding risk index thresholds according to actual applications, and no limitation is made here.

[0065] This embodiment can obtain the risk level of the relevant personnel of the recent social security incident design through the above method, so that different levels of attention can be paid to them based on different risk levels. For example, high risk is always paid attention to and followed up; medium risk is paid attention to and followed up continuously; low risk is paid attention to and followed up regularly; normal personnel are not paid attention to.

[0066] In social governance, the embodiments of the present invention can timely discover various potential risk persons, and through targeted early prevention, it helps to reduce the occurrence of various social incidents in the process of urban management, enhance social security, and promote social harmony and stable development.

[0067] Embodiment 2:

[0068] The present invention also provides a terminal device for evaluating personnel risk levels, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned method embodiment of embodiment 1 of the present invention when executing the computer program.

[0069] Further, as an executable solution, the personnel risk level assessment terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The personnel risk level assessment terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art may understand that the composition structure of the above-mentioned personnel risk level assessment terminal device is only an example of the personnel risk level assessment terminal device, and does not constitute a limitation on the personnel risk level assessment terminal device. It may include more or less components than the above-mentioned components, or a combination of certain components, or different components. For example, the personnel risk level assessment terminal device may also include input and output devices, network access devices, buses, etc., and the embodiments of the present invention do not limit this.

[0070] Further, as an executable solution, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the personnel risk level assessment terminal device, and uses various interfaces and lines to connect various parts of the entire personnel risk level assessment terminal device.

[0071] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the personnel risk level assessment terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0072] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in the embodiment of the present invention are implemented.

[0073] If the module / unit integrated in the terminal device for assessing the risk level of personnel is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory) and software distribution medium, etc.

[0074] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

Claims

1. A personnel risk level evaluation method, characterized in that: The following steps are involved: S1: Collect data on people and events in the study area; S2: Build a basic database of personnel information and event information based on the collected data; S3: Select fields related to social security events from various fields contained in the personnel information basic database as personnel factors, set weights for various personnel factors, and build a personnel factor benchmark database to record various personnel factor information and weights of various personnel factors of various personnel contained in the personnel information basic database; Select fields related to social security events from various fields included in the event information base as event elements, set weights for various event elements, and build an event element benchmark library to record event element information and weights of various event elements for various events included in the event information base; S4: For the social security event information to be analyzed in the study area, extract the personnel as relevant personnel, extract the events as relevant events, and extract all personnel elements corresponding to the relevant personnel and all event elements corresponding to the relevant events; S5: according to all personnel factors corresponding to the relevant personnel, the weight of each personnel factor is searched from the personnel factor benchmark library, and all personnel factors corresponding to each relevant personnel are weighted and summed to obtain the personnel base number of the relevant personnel; According to all event elements corresponding to the relevant events, the weight of each event element is searched from the event element benchmark library, and all event elements corresponding to each relevant event are weighted summed to obtain the event cardinality of the relevant event; S6: Calculate the relationship coefficient between the relevant persons and the relevant events according to whether the relevant persons and the relevant events are related; S7: extracting all associated persons corresponding to the associated person from the personnel relationship field of the personnel information basic database, and generating a personnel gain coefficient of the associated person based on the positive and negative characteristics of the associated person related to the social security incident; S8: searching for all events corresponding to the relevant personnel from the event information base, and generating an event gain coefficient of the relevant event based on the positive and negative characteristics of the found events; S9: Calculate the risk value of each relevant person in the event information to be analyzed for each relevant event related to him according to the person base, event base, relationship coefficient, person gain coefficient and event gain coefficient, and accumulate the risk values ​​of all relevant events related to each relevant person within a period of time to obtain the person risk index of each relevant person; S10: Determine the risk level of each relevant person according to the relationship between the calculated personnel risk index and the risk index thresholds corresponding to the different risk levels.

2. The personnel risk level assessment method according to claim 1, characterized in that: Step S1 also includes parsing the collected raw data, extracting feature data related to people and events, and labeling the extracted feature data with corresponding people or events.

3. The personnel risk level evaluation method according to claim 1, characterized in that: When calculating the relationship coefficient between the relevant persons and the relevant events in step S6, in addition to considering the need for the relevant persons and the relevant events to be associated, the degree of association between the relevant persons and the relevant events is also considered.

4. The personnel risk level assessment method according to claim 3 is characterized in that: The degree of association between relevant persons and relevant events is calculated by whether the relevant persons have positive characteristics that have an inhibitory effect on social security events and negative characteristics that have a promoting effect on social security events; if the relevant persons have positive characteristics, the degree of association between the relevant persons and relevant events is reduced; if the relevant persons have negative characteristics, the degree of association between the relevant persons and relevant events is increased.

5. The personnel risk level assessment method according to claim 1, characterized in that: The risk value P of the relevant person t to the relevant event i related to him ti The calculation formula is: P ti =PR t ×ER i ×PER ti ×PGC t ×EGC t Among them, PR t Indicates the number of personnel related to person t, ER i Represents the event cardinality of related event i, PER ti represents the relationship coefficient between relevant person t and relevant event i, PGC t Represents the personnel gain coefficient of the relevant personnel t, EGC t Represents the event gain coefficient of relevant person t.

6. The personnel risk level assessment method according to claim 1, characterized in that: The risk values ​​of all relevant events related to each relevant person within a period of time are accumulated, and it is determined whether the risk value corresponding to each relevant event is less than the risk value threshold. If so, the risk value of the relevant event is not accumulated during the accumulation.

7. A terminal device for evaluating personnel risk level, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images