Hidden risk personnel mining method and system based on behavior trajectory data

Abstract

A hidden risk personnel mining method based on behavior trajectory data comprises the following steps: acquiring data which is captured by front-end sensing equipment and subjected to personnel identity recognition, and storing the data to generate a personnel trajectory library; screening the personnel track library based on user requirements to generate a key target object library; marking business attributes of personnel in the key target object library, and constructing a static label library; performing behavior attribute frequency marking on the personnel in the key target object library, and constructing a dynamic label library; respectively calculating the weight value of each label in the static label library and the dynamic label library; and calculating respective tag scores according to the tag weight values and the hit conditions of the key target object library in the static tag library and the dynamic tag library, and mining hidden risk personnel. According to the method disclosed by the invention, data of various related departments can be fully fused, and the working efficiency and achievements of actual combat departments in the field can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of social governance and big data analysis, and in particular to a method and system for mining hidden risk personnel based on behavior trajectory data. Background Art

[0002] With the development of social economy, social contradictions are gradually increasing, and the number of hidden risk personnel in society is gradually increasing. Faced with a large number of hidden risk personnel in society, it takes a lot of manpower and material resources to analyze and manage them. At present, the mining of hidden risk personnel only considers the historical behavior information of the risk personnel themselves, which leads to the fact that most of the current mining of hidden risk personnel cannot be predicted in advance. Therefore, there is an urgent need for a hidden risk personnel mining method and system based on behavior trajectory data. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

[0005] In a first aspect, an embodiment of the present invention discloses a method for mining hidden risk personnel based on behavior trajectory data, comprising:

[0006] S100. Obtaining data captured by the front-end sensing device after personnel identification, and storing the data to generate a personnel trajectory library;

[0007] S200. Screening the personnel trajectory library based on user needs to generate a key target object library;

[0008] S300. Mark the business attributes of the personnel in the key target object library to build a static tag library;

[0009] S400. Mark the behavior attribute frequency of the personnel in the key target object library and build a dynamic tag library;

[0010] S500. Calculate the weight values ​​of each tag in the static tag library and the dynamic tag library using the priority graph algorithm and the TF-IDF algorithm respectively;

[0011] S600. Calculate the respective label scores according to the label weight values ​​and the hit status of the key target object library in the static label library and the dynamic label library, and mine the hidden risk personnel through the label scores.

[0012] Furthermore, in S100, after the front-end sensing device captures the data after personnel identification, it combines the data after personnel identification with the basic attributes of the personnel, constructs a target object library and stores the relevant results in the database; the basic attributes of the personnel include at least age range and gender.

[0013] Furthermore, in S200, the personnel trajectory library is screened based on user needs to obtain a key target object library, and the specific method includes: performing secondary filtering on the personnel trajectory library according to user needs, and the user needs at least include age group and gender of personnel.

[0029] Furthermore, in S500, a priority graph algorithm is used to calculate the weight value of each tag in the static tag library. The specific method includes: comparing the static tags in pairs, and assigning a corresponding score to each tag according to the comparison result; if tag Xi is more important than tag Xj, Xi gets 1 point; if both are equally important, Xi gets 0.5 points; if tag Xj is more important than tag Xi, Xi gets 0 points. Through a series of comparisons and scoring, the weight value of each tag is obtained, thereby determining the importance ranking of the tags.

[0030] Furthermore, in S500, the TF-IDF algorithm is used to calculate the weight value of each tag in the dynamic tag library, and the specific method includes:

[0031] The first step is to introduce the concept of TF eigenvalue frequency algorithm. TF eigenvalue frequency represents the frequency of occurrence of a certain type of feature in the total feature system. The specific formula is as follows:

[0032]

[0033] w(p,t)=∑x i p∈target person,x i ∈ the i-th eigenvalue

[0034] t i ∈All tags of this person

[0035] Among them, w(p,t) represents the total number of occurrences of a certain characteristic value of p personnel, ∑w(p,t i ) represents the total number of occurrences of all eigenvalues ​​of p persons;

[0036] The second step is to introduce the IDF inverse eigenvalue frequency scarcity algorithm in all eigenvalues. The specific formula is as follows:

[0037] p j ∈All staff

[0038] Among them, ∑∑w(p j ,t i ) represents the total number of eigenvalues ​​of all key target objects, ∑w(p j ,t) represents the sum of a certain characteristic value of all personnel;

[0039] The third step is to calculate the weight ratio of a single feature. The specific formula is as follows:

[0040]

[0041] Among them, w(p,t) represents the total number of occurrences of a certain characteristic value of p personnel, ∑w(p,t i ) represents the total number of occurrences of all eigenvalues ​​of p persons, ∑∑w(p j ,t i ) represents the total number of eigenvalues ​​of all key target objects, ∑w(p j ,t) represents the sum of a certain characteristic value of all personnel.

[0042] Furthermore, in S500, the TF-IDF algorithm is used to calculate the weight values ​​of each tag in the dynamic tag library. The specific method also includes: after obtaining the weight proportion of each feature value of each key target object, the weight sum of a single key target object is further obtained, and the formula is as follows:

[0043] f(k)=a∑k i +b

[0044] Among them, k i is the weight ratio of a single feature, and a and b are weight coefficients.

[0045] In a second aspect, an embodiment of the present invention discloses a hidden risk personnel mining system based on behavior trajectory data, including: a personnel trajectory library generation unit, a target object library generation unit, a static label library construction unit, a dynamic label library construction unit, a label weight value calculation unit and a hidden risk personnel mining unit; wherein:

[0046] A personnel trajectory library generation unit is used to obtain data captured by a front-end sensing device after personnel identification, and store the data to generate a personnel trajectory library;

[0047] A target object library generation unit, used to screen the personnel trajectory library based on user needs and generate a key target object library;

[0048] A static tag library construction unit, used to mark the business attributes of the personnel in the key target object library and construct a static tag library;

[0049] A dynamic tag library construction unit is used to mark the behavior attribute frequency of people in the key target object library and build a dynamic tag library;

[0050] A label weight value calculation unit, used to calculate the weight values ​​of each label in the static label library and the dynamic label library by using a priority graph algorithm and a TF-IDF algorithm respectively;

[0051] The hidden risk personnel mining unit is used to calculate the respective label scores according to the respective label weight values ​​and the hit conditions of the key target object library in the static label library and the dynamic label library, and mine the hidden risk personnel through the label scores.

[0052] In a third aspect, an embodiment of the present invention discloses an electronic device, including:

[0053] one or more processors;

[0054] A memory for storing one or more programs;

[0055] When the one or more programs are executed by the one or more processors, the one or more processors implement the mining method.

[0056] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0057] The embodiment of the present invention discloses a method for mining hidden risk personnel based on behavior trajectory data, including: obtaining data captured by a front-end sensing device after personnel identity recognition, and storing the data to generate a personnel trajectory library; screening the personnel trajectory library based on user needs to generate a key target object library; marking the business attributes of personnel in the key target object library to build a static tag library; marking the behavioral attribute frequency of personnel in the key target object library to build a dynamic tag library; using the priority graph algorithm and the TF-IDF algorithm to calculate the weight values ​​of each tag in the static tag library and the dynamic tag library respectively; calculating the respective tag scores according to the weight values ​​of each tag and the hit situation of the key target object library in the static tag library and the dynamic tag library, and mining the hidden risk personnel through the tag scores. The method disclosed in the present invention can fully integrate data from various relevant departments, highlight data advantages, and help improve the work efficiency and results of practical departments in the field.

[0058] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0060] Figure 1 This is a flow chart of a method for mining hidden risk personnel based on behavior trajectory data in Example 1 of the present invention;

[0061] Figure 2 This is a structural block diagram of an electronic device in Example 3 of the present invention. DETAILED DESCRIPTION

[0062] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0063] Example 1

[0064] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a method for mining hidden risk personnel based on behavior trajectory data, such as Figure 1 ,include:

[0065] S100. Obtain the data captured by the front-end sensing device after the person's identity is identified, and store the data to generate a person's trajectory library; in S100 of this embodiment, after the front-end sensing device captures the data after the person's identity is identified, the data after the person's identity is combined with the basic attributes of the person, a target object library is constructed and the relevant results are stored in the database; the basic attributes of the person include at least age range and gender. It can be understood that the front-end sensing device in the embodiment of the present invention includes at least a camera installed by the relevant department at each intersection or community, which captures the image information of the passing person through the camera, compares it with the background person image database, identifies the identity of the passing person, and stores the trajectory after the person's identity is identified to generate a person trajectory library.

[0066] S200. Filter the personnel trajectory library based on user needs to generate a key target object library; In S200 of this embodiment, the personnel trajectory library is filtered based on user needs to obtain a key target object library, and the specific method includes: filtering the personnel trajectory library twice according to user needs, and the user needs at least include the age group and gender of the personnel. For example, when the user needs to find the trajectory of boys aged 18 to 22, the personnel trajectory library can be filtered, and the filtering conditions can be set to boys, aged 18 to 22, and a key target object library can be generated.

[0067] S300. Mark the business attributes of the personnel in the key target object library to build a static tag library;

[0075] S400. Mark the behavior attribute frequency of the personnel in the key target object library and build a dynamic tag library;

[0084] S500. Calculate the weight values ​​of each tag in the static tag library and the dynamic tag library using the priority graph algorithm and the TF-IDF algorithm respectively;

[0085] In S500 of this embodiment, a priority graph algorithm is used to calculate the weight value of each tag in the static tag library. The specific method includes: comparing the static tags in pairs, and assigning a corresponding score to each tag according to the comparison result; if tag Xi is more important than tag Xj, Xi gets 1 point; if both are equally important, Xi gets 0.5 points; if tag Xj is more important than tag Xi, Xi gets 0 points. Through a series of comparisons and scoring, the weight value of each tag is obtained, thereby determining the importance ranking of the tags.

[0086] In S500, the TF-IDF algorithm is used to calculate the weight value of each tag in the dynamic tag library. The specific method includes:

[0087] The first step is to introduce the concept of TF eigenvalue frequency algorithm. TF eigenvalue frequency represents the frequency of occurrence of a certain type of feature in the total feature system. The specific formula is as follows:

[0088]

[0089] w(p,t)=∑x i p∈target person,x i ∈ the i-th eigenvalue

[0090] t i ∈All tags of this person

[0091] Among them, w(p,t) represents the total number of occurrences of a certain characteristic value of p personnel, ∑w(p,t i ) represents the total number of occurrences of all eigenvalues ​​of p persons;

[0092] The second step is to introduce the IDF inverse eigenvalue frequency scarcity algorithm in all eigenvalues. The specific formula is as follows:

[0093] p j ∈All staff

[0094] Among them, ∑∑w(p j ,t i ) represents the total number of eigenvalues ​​of all key target objects, ∑w(p j ,t) represents the sum of a certain characteristic value of all personnel;

[0095] The third step is to calculate the weight ratio of a single feature. The specific formula is as follows:

[0096]

[0097] Among them, w(p,t) represents the total number of occurrences of a certain characteristic value of p personnel, ∑w(p,t i) represents the total number of occurrences of all eigenvalues ​​of p persons, ∑∑w(p j ,t i ) represents the total number of eigenvalues ​​of all key target objects, ∑w(p j ,t) represents the sum of a certain characteristic value of all personnel.

[0098] S600. Calculate the respective label scores according to the label weight values ​​and the hit status of the key target object library in the static label library and the dynamic label library, and mine the hidden risk personnel through the label scores.

[0099] In this embodiment, after obtaining the weight values ​​of each tag in the static tag library and the dynamic tag library in S500, the respective tag scores are calculated according to the weight values ​​of each tag and the hit status of the key target object library in the static tag library and the dynamic tag library.

[0100] The embodiment of the present invention discloses a method for mining hidden risk personnel based on behavior trajectory data, including: obtaining data captured by a front-end sensing device after personnel identity recognition, and storing the data to generate a personnel trajectory library; screening the personnel trajectory library based on user needs to generate a key target object library; marking the business attributes of personnel in the key target object library to build a static tag library; marking the behavioral attribute frequency of personnel in the key target object library to build a dynamic tag library; using the priority graph algorithm and the TF-IDF algorithm to calculate the weight values ​​of each tag in the static tag library and the dynamic tag library respectively; calculating the respective tag scores according to the weight values ​​of each tag and the hit situation of the key target object library in the static tag library and the dynamic tag library, and mining the hidden risk personnel through the tag scores. The method disclosed in the present invention can fully integrate data from various relevant departments, highlight data advantages, and help improve the work efficiency and results of practical departments in the field.

[0101] Example 2

[0102] Based on the method for mining hidden risk personnel based on behavior trajectory data in Example 1, this embodiment discloses a system for mining hidden risk personnel based on behavior trajectory data, which is characterized by comprising: a personnel trajectory library generation unit, a target object library generation unit, a static label library construction unit, a dynamic label library construction unit, a label weight value calculation unit and a hidden risk personnel mining unit; wherein:

[0103] A personnel trajectory library generation unit is used to obtain data captured by a front-end sensing device after personnel identification, and store the data to generate a personnel trajectory library;

[0104] A target object library generation unit, used to screen the personnel trajectory library based on user needs and generate a key target object library;

[0105] A static tag library construction unit, used to mark the business attributes of the personnel in the key target object library and construct a static tag library;

[0106] A dynamic tag library construction unit is used to mark the behavior attribute frequency of people in the key target object library and build a dynamic tag library;

[0107] A label weight value calculation unit, used to calculate the weight values ​​of each label in the static label library and the dynamic label library by using a priority graph algorithm and a TF-IDF algorithm respectively;

[0108] The hidden risk personnel mining unit is used to calculate the respective label scores according to the respective label weight values ​​and the hit conditions of the key target object library in the static label library and the dynamic label library, and mine the hidden risk personnel through the label scores.

[0109] Among them, the specific working principles of the personnel trajectory library generation unit, the target object library generation unit, the static label library construction unit, the dynamic label library construction unit, the label weight value calculation unit and the hidden risk personnel mining unit have been introduced in detail in Example 1, and will not be repeated in this embodiment.

[0110] Example 3

[0111] Based on the same inventive concept, an embodiment of the present disclosure also provides an electronic device. Figure 2 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Figure 2 As shown, an embodiment of the present disclosure provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any optimization method in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, and are configured to implement information interaction between the processor and the memory.

[0112] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus), etc.

[0113] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0114] In some embodiments, the one or more processors 101 include a field programmable gate array.

[0115] According to an embodiment of the present disclosure, a computer-readable medium is further provided, wherein a computer program is stored on the computer-readable medium, wherein when the program is executed by a processor, the steps in any optimization method in the above-mentioned embodiment are implemented.

[0116] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0117] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0118] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0119] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0120] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0121] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A method for mining hidden risk personnel based on behavioral trajectory data, characterized in that: include: S100. Obtaining data captured by the front-end sensing device after personnel identification, and storing the data to generate a personnel trajectory library; S200. Screening the personnel trajectory library based on user needs to generate a key target object library; S300. Mark the business attributes of the personnel in the key target object library to build a static tag library; S400. Mark the behavior attribute frequency of the personnel in the key target object library and build a dynamic tag library; S500. Calculate the weight values ​​of each tag in the static tag library and the dynamic tag library using the priority graph algorithm and the TF-IDF algorithm respectively; S600. Calculate the respective label scores according to the label weight values ​​and the hit conditions of the key target object library in the static label library and the dynamic label library, and mine the hidden risk personnel through the label scores.

2. The method for mining hidden risk personnel based on behavior trajectory data according to claim 1, characterized in that: In S100, after the front-end sensing device captures the data after personnel identity recognition, it combines the data after personnel identity recognition with the basic attributes of the personnel, constructs a target object library and stores the relevant results in the database; the basic attributes of the personnel include at least age range and gender.

3. The method for mining hidden risk personnel based on behavior trajectory data as claimed in claim 1, characterized in that: In S200, the personnel trajectory library is screened based on user needs to obtain a key target object library. The specific method includes: performing secondary filtering on the personnel trajectory library according to user needs. The user needs at least include age group and gender of personnel.

4. The method for mining hidden risk personnel based on behavior trajectory data according to claim 1, characterized in that: In S500, a priority graph algorithm is used to calculate the weight value of each tag in the static tag library. The specific method includes: comparing the static tags in pairs, and assigning a corresponding score to each tag according to the comparison result; if tag Xi is more important than tag Xj, Xi gets 1 point; if the two are equally important, Xi gets 0.5 points; if tag Xj is more important than tag Xi, Xi gets 0 points. Through a series of comparisons and scoring, the weight value of each tag is obtained, thereby determining the importance ranking of the tags.

5. The method for mining hidden risk personnel based on behavior trajectory data as claimed in claim 1, characterized in that: In S500, the TF-IDF algorithm is used to calculate the weight value of each tag in the dynamic tag library. The specific method includes: The first step is to introduce the concept of TF eigenvalue frequency algorithm. TF eigenvalue frequency represents the frequency of occurrence of a certain type of feature in the total feature system. The specific formula is as follows: w(p,t)=∑x i p∈target person,x i ∈ the i-th eigenvalue t i ∈All tags of this person Among them, w(p,t) represents the total number of occurrences of a certain characteristic value of p personnel, ∑w(p,t i ) represents the total number of occurrences of all eigenvalues ​​of p persons; The second step is to introduce the IDF inverse eigenvalue frequency scarcity algorithm in all eigenvalues. The specific formula is as follows: p j ∈All staff Among them, ∑∑w(p j ,t i ) represents the total number of eigenvalues ​​of all key target objects, ∑w(p j ,t) represents the sum of a certain characteristic value of all personnel; The third step is to calculate the weight ratio of a single feature. The specific formula is as follows: Among them, w(p,t) represents the total number of occurrences of a certain characteristic value of p personnel, ∑w(p,t i ) represents the total number of occurrences of all eigenvalues ​​of p persons, ∑∑w(p j ,t i ) represents the total number of eigenvalues ​​of all key target objects, ∑w(p j ,t) represents the sum of a certain characteristic value of all personnel.

6. The method for mining hidden risk personnel based on behavior trajectory data according to claim 1, characterized in that: In S500, the TF-IDF algorithm is used to calculate the weight values ​​of each tag in the dynamic tag library. The specific method also includes: after obtaining the weight proportion of each feature value of each key target object, further obtaining the weight sum of a single key target object, the formula is as follows: f(k)=a∑k i +b Among them, k i is the weight ratio of a single feature, and a and b are weight coefficients.

7. A hidden risk personnel mining system based on behavioral trajectory data, characterized in that: include: Personnel trajectory library generation unit, target object library generation unit, static label library construction unit, dynamic label library construction unit, label weight value calculation unit and hidden risk personnel mining unit; wherein: A personnel trajectory library generation unit is used to obtain data captured by a front-end sensing device after personnel identification, and store the data to generate a personnel trajectory library; A target object library generation unit, used to screen the personnel trajectory library based on user needs and generate a key target object library; A static tag library construction unit, used to mark the business attributes of the personnel in the key target object library and construct a static tag library; A dynamic tag library construction unit is used to mark the behavior attribute frequency of people in the key target object library and build a dynamic tag library; A label weight value calculation unit, used to calculate the weight values ​​of each label in the static label library and the dynamic label library by using a priority graph algorithm and a TF-IDF algorithm respectively; The hidden risk personnel mining unit is used to calculate the respective label scores according to the respective label weight values ​​and the hit conditions of the key target object library in the static label library and the dynamic label library, and mine the hidden risk personnel through the label scores.

8. An electronic device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 6.

Images