Personnel information big data screening method and system based on person and certificate identification

Abstract

The invention provides a person information big data screening method and system based on person and certificate identification, and relates to the technical field of computers, and the method comprises the steps: firstly obtaining verification information of person and certificate identification equipment through a data collection interface; the person and certificate identification equipment is used for verifying and comparing a person and a certificate, and verification information comprises verification identification parameters; then on-site video data of the personnel information is called in the target video monitoring equipment based on the verification identification parameters; based on a BFS breadth-first algorithm, image retrieval of time and space dimensions is carried out on the field video data, and target personnel information matched with the verification information is determined; through the method, people and certificate identification and field personnel information screening and positioning are realized, the technical problems of high difficulty and high cost of personnel information screening and management are solved, unified service management for personnel information is realized, and the effects of reducing management difficulty and calculation cost are achieved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for screening big data of personnel information based on human evidence recognition. Background Art

[0002] With the large-scale and multi-dimensional advancement of smart port construction, information such as port personnel composition, personnel structure, personnel behavior, activity trajectory, and personnel work status is growing exponentially. The hazards of complex architectures in various platforms related to smart ports are hidden and continue to grow, especially in business scenarios where massive data processing occurs. This leads to an increase in system throughput, mutual influence of various functional modules, data duplication, and difficulty in maintenance. Therefore, big data screening can be combined to conduct personnel information screening and real-name authentication management at the port site.

[0003] Traditional personnel information big data screening technology is based on comparing a certain information that needs to be compared with the existing information in the database (middle platform, data lake). Each system information comparison requires the establishment of an independent retrieval and query system. At the same time, data query and data comparison are independent and non-continuous processes. In this process, neither unified service management can be achieved, nor hardware resources are occupied while repeatedly performing the same task. The traditional big data screening method uses the network to collect data, and then uses artificial intelligence to verify it, so as to realize the identification of people and documents. In the actual application of personnel management at the port site, the identification of people and documents is often only performed once at the entrance, and there is a lack of supervision of the behavior trajectory of personnel within the park.

[0004] In other words, existing technologies have technical problems such as difficulty and high cost in screening and managing personnel information. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for screening big data of personnel information based on human evidence recognition, so as to alleviate the technical problems existing in the prior art of the difficulty and high cost of screening and managing personnel information.

[0006] In the first aspect, an embodiment of the present invention provides a personnel information big data screening method based on human and document recognition, which is applied to a personnel big data screening system based on human and document recognition, and the method includes: obtaining verification information of a human and document recognition device through a data acquisition interface; the data acquisition interface is used to receive verification information from different types of human and document recognition devices; the human and document recognition device is used to realize verification and comparison between personnel and documents, and the verification information includes the verification and comparison results and verification and recognition parameters; based on the verification and recognition parameters, calling the on-site video data of the personnel information in the target video surveillance device; based on the BFS breadth-first algorithm, performing image retrieval on the time dimension and spatial dimension of the on-site video data respectively, and determining the target personnel information matching the verification information; the target personnel information includes: verification information of human and document recognition and target location information.

[0007] In some optional implementations, the above-mentioned data acquisition interface is embedded in the above-mentioned personnel big data screening system based on personal identification through an API; the verification information of the personal identification device is obtained through the data acquisition interface, including: the data acquisition interface receives verification records from different types of personal identification devices, and parses the above-mentioned verification records based on HTTP POST requests, and outputs verification information; the above-mentioned verification information includes: the results of verification and comparison and verification identification parameters; the above-mentioned verification identification parameters include: face recognition coding information, device identification parameters, personnel information parameters and verification parameters.

[0008] In some optional implementations, based on the above-mentioned verification and identification parameters, the on-site video data of personnel information is called in the target video surveillance device, including: based on the above-mentioned verification and identification parameters, determining the target video surveillance device, and configuring the SDK interface parameters; calling the on-site video data of personnel information in the above-mentioned target video surveillance device through the SDK interface.

[0009] In some optional implementations, based on the BFS breadth-first algorithm, image retrieval is performed on the above-mentioned on-site video data in the time dimension and the space dimension respectively to determine the target person information matching the above-mentioned verification information, including: using FFStreamer to encode the above-mentioned on-site video data frame by frame to generate graphic data to be identified; based on the BFS breadth-first algorithm, the above-mentioned graphic data to be identified is decomposed according to the time dimension and the space dimension; based on the above-mentioned verification and identification parameters, image retrieval is performed on the decomposed time dimension and space dimension of the graphic data to be identified to determine the target person information matching the above-mentioned verification information.

[0010] In some optional implementations, the above-mentioned graphic data to be identified includes a queue node that matches a big data field; the above-mentioned queue node includes a number of vertices; the above-mentioned big data field is a target screening condition; the above-mentioned target screening condition corresponds to at least one personnel information feature.

[0011] In the second aspect, an embodiment of the present invention provides a personnel information big data screening system based on human and document identification, the system comprising: an application platform layer and a big data logic processing layer; the application platform layer is used to obtain verification information of the human and document identification device, and to call on-site video data of personnel information; the application platform layer is also used to clean the collected data and set rules for the data; the big data logic processing layer is used to process the data sent by the application platform layer; the big data logic processing layer comprises: enabling the collection module, the data verification module, the security verification module and the data docking module; the big data logic processing layer is also used to send the processed data to the application platform layer for data application.

[0012] In some optional implementations, the above system also includes: a basic equipment layer, and the above basic equipment layer includes: a person identification device and a video surveillance device; the above person identification device is used for personnel identity verification and face comparison verification; the above video surveillance device is used for video monitoring and video storage; the above basic equipment layer is connected to the above application platform layer.

[0013] In the third aspect, an embodiment of the present invention provides a personnel information big data screening device based on human and document recognition, including: a verification information acquisition module, used to obtain verification information of a human and document recognition device through a data acquisition interface; the above-mentioned data acquisition interface is used to receive verification information from different types of human and document recognition devices; the above-mentioned human and document recognition device is used to realize verification and comparison between personnel and documents, and the above-mentioned verification information includes the verification and comparison result and verification and recognition parameters; an on-site video data calling module, used to call on-site video data of personnel information in a target video surveillance device based on the above-mentioned verification and recognition parameters; a target personnel information determination module, used to perform image retrieval in the time dimension and space dimension of the above-mentioned on-site video data based on the BFS breadth-first algorithm, and determine the target personnel information that matches the above-mentioned verification information; the above-mentioned target personnel information includes: verification information of human and document recognition and target position information.

[0014] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0015] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to execute any method described in the first aspect above.

[0016] The present invention provides a method and system for screening personnel information big data based on human-document identification, the method comprising: firstly obtaining verification information of a human-document identification device through a data acquisition interface; the human-document identification device is used to realize verification and comparison between personnel and documents, and the verification information includes verification and comparison results and verification and identification parameters; then based on the verification and identification parameters, calling the on-site video data of the personnel information in the target video monitoring device; then based on the BFS breadth-first algorithm, performing image retrieval in the time dimension and the space dimension on the on-site video data respectively, and determining the target personnel information matching the verification information; the target personnel information includes: verification information of human-document identification and target position information, through the above method, human-document identification and on-site personnel information screening are realized, and on-site personnel can be located, thereby reducing the difficulty and cost of personnel information screening and management, realizing unified service-oriented management for personnel information, and reducing the effect of computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a method for screening big data of personnel information based on human evidence recognition provided by an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the structure of a personnel information big data screening system based on human evidence recognition provided by an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of the structure of a personnel information big data screening device based on human evidence recognition provided by an embodiment of the present invention;

[0021] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0023] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. Some embodiments of the present invention are described in detail below in conjunction with the drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0025] With the large-scale and multi-dimensional advancement of smart port construction, information such as port personnel composition, personnel structure, personnel behavior, activity trajectory, and personnel work status is growing exponentially. The hazards of complex architectures in various platforms related to smart ports are hidden and growing continuously, especially in the business scenario of massive data processing, which leads to an increase in system throughput, mutual influence of various functional modules, and data duplication and maintenance difficulties. Therefore, the port site can be screened for personnel information and real-name authentication management in combination with big data screening. Traditional personnel information big data screening technology is based on the comparison of a certain information that needs to be compared with the existing information in the database (middle platform, data lake). Each system information comparison requires the establishment of an independent retrieval and query system. At the same time, data query and data comparison are independent and non-continuous processes. In this process, unified service management cannot be achieved, and hardware resources are occupied while repeating the same task. Usually, the big data screening method uses the network to collect data, and then uses artificial intelligence to verify it, so as to realize person-document identification. In the actual application of personnel management at the port site, person-document identification is often only performed once at the entrance, and there is a lack of supervision of personnel behavior trajectories within the park. In other words, existing technologies have technical problems such as difficulty and high cost in screening and managing personnel information.

[0026] Based on this, an embodiment of the present invention provides a method and system for screening big data of personnel information based on human evidence recognition to solve the above problems.

[0027] To facilitate understanding of this embodiment, firstly, a method for screening big data of personnel information based on human evidence recognition disclosed in an embodiment of the present invention is introduced in detail, see Figure 1 The flowchart of a method for screening big data of personnel information based on human evidence recognition is shown. The method is applied to a big data screening system for personnel information based on human evidence recognition and can be executed by an electronic device. The method mainly includes the following steps S110 to S130:

[0028] S110: Obtain verification information of the person identification device through the data collection interface;

[0029] The data acquisition interface is used to receive verification information from different types of human-document identification devices; the human-document identification devices are used to verify and compare personnel with documents, and the verification information includes the verification and comparison results and verification and identification parameters;

[0030] Among them, the data collection interface can be embedded in the personnel big data screening system based on human identification through API. The data collection interface supports HTTP Post requests and interprets the received data according to the corresponding format specifications.

[0031] In one embodiment, verification information of a person identification device is obtained through a data acquisition interface, including: the data acquisition interface receives verification records from different types of person identification devices, and parses the verification records based on HTTP POST requests, and outputs verification information; the verification information includes: the results of verification comparison and verification identification parameters; the verification identification parameters include: face recognition coding information, device identification parameters, personnel information parameters and verification parameters.

[0032] As a specific example, face recognition coding information may include: a large picture of on-site recognition, a picture captured from the on-site photo, an ID photo taken on-site, etc.; device identification parameters may include: the device's unique serial number (deviceNo string), the device identification (machineCode string); personnel information parameters may include: verification type (validateType Int), name, gender, ethnicity, date of birth, ID address, ID number, issuing authority, ID validity date, ID portrait, on-site collected fingerprint image, etc.; verification parameters generally include: face verification score, face verification result, fingerprint verification score, fingerprint verification result, whether the ID is expired, whether the person is on the internal blacklist, verification time, etc.

[0033] S120: Based on the verification identification parameter, calling the on-site video data of the personnel information in the target video surveillance device;

[0034] In one embodiment, based on the verification and identification parameters, the live video data of the personnel information is called in the target video surveillance device, including: based on the verification and identification parameters, determining the target video surveillance device and configuring the SDK interface parameters; calling the live video data of the personnel information in the target video surveillance device through the SDK interface.

[0035] Before configuring the SDK interface parameters, first create a Github repository, then call the SDK value and configure it as follows:

[0036] setmUrl method: set the production video acquisition address;

[0037] setFrameRate method: sets the frame rate of production video capture;

[0038] setMaxAverageVideoBitrate method: sets the maximum bitrate, that is, the target bitrate;

[0039] setMinAverageVideoBitrate method: set the minimum bit rate;

[0040] setInitAverageVideoBitrate method: set the initial bit rate;

[0041] setAudioBitrate method: set the audio bitrate;

[0042] setVideoResolution method: set the size of the streaming video: 360P / 480P / 540P / 720P;

[0043] setEncodeMethod method: set the video encoding method: hard coding / soft coding;

[0044] setSampleAudioRateInHz method: sets the audio frequency;

[0045] setDefaultLandscape method: set the production video direction: horizontal / vertical;

[0046] setFrontCameraMirror method: set the camera direction: front / rear.

[0047] A Camera is defined inside the SDK, which implements a callback interface for acquiring data for each frame. The data is then thrown out in the callback method. At the same time, each frame of data is processed twice and encoded using FFStreamer.

[0048] S130: Based on the BFS breadth-first algorithm, image retrieval is performed on the on-site video data in the time dimension and the space dimension respectively to determine the target person information that matches the verification information; the target person information includes: verification information for witness identification and target location information.

[0049] In one embodiment, S130 performs image retrieval in the time dimension and the space dimension on the on-site video data based on the BFS breadth-first algorithm to determine the target person information matching the verification information, including:

[0050] (S131) ​​using FFStreamer to encode the live video data frame by frame to generate the graphic data to be identified;

[0051] (S132) Decomposing the to-be-identified graphic data according to the time dimension and the space dimension based on the BFS breadth-first algorithm;

[0052] (S133) Based on the verification and recognition parameters, image retrieval is performed on the decomposed graphic data to be recognized in the time dimension and space dimension to determine the target person information that matches the verification information.

[0053] In one embodiment, the graphic data to be identified includes a queue node that matches a big data field; the queue node includes a number of vertices; the big data field is a target screening condition; the target screening condition corresponds to at least one personnel information feature.

[0054] Use FFStreamer to encode the live video data frame by frame, that is, form the graph into a nonlinear table structure, in which: the elements are called vertices; the relationship between vertices is called edges; the number of edges connected to the vertices is called the degree of the vertex; the in-degree of the vertex: indicates how many edges point to a vertex; the out-degree of the vertex: indicates how many edges a vertex has pointing to other vertices.

[0055] After the personnel information is encoded by FFStreamer, a queue node matching the big data field is formed. The queue nodes are combined and the initial node is defined. The BFS breadth-first-search algorithm is used to start from the initial node and reversely search for nodes in combination with the encoding rules to find a legal and feasible point that can be reached in one step (if there are other conditions and restrictions, return to the initial node), add it to the algorithm processing queue, and then pop up the initial node. The search operation is performed on the node nodes in the queue in turn until the queue is empty.

[0056] The time complexity of breadth-first search is O(V+E), where V is the number of vertices and E is the number of edges. The space complexity of breadth-first search is O(V), and it is necessary to use queues, visited arrays, and route arrays to store vertex data, and their size will not exceed the number of vertices.

[0057] In the BFS algorithm process, the concepts related to the Dijkstra algorithm are applied to establish the S set based on personnel information: when the shortest path from s to x (x∈V) is found, then x∈S. When all vertices enter the S set, the algorithm ends.

[0058] Initially: S = {s}, the algorithm ends when S = V;

[0059] The shortest path from s to u relative to S: refers to the shortest path from s to u that only passes through vertices in S;

[0060] dist[u]: the shortest path length from s to u relative to S;

[0061] short[u]: the length of the shortest path from s to u (the final solution of the algorithm);

[0062] dist[u]≥short[u];

[0063] The Dijkstra algorithm uses a greedy algorithm mode formed by associating BFS with application tag data. The algorithm process is to continuously expand the S set by calculating dist[u]. At the same time, dist[u] will be continuously optimized and improved until dist[u] = short[u], and put it into S. When all vertices are put into S set, the algorithm ends. After traversing all vertices, the retrieval of the graphic data to be identified is completed, the facial feature points in the image are retrieved and matched, and the retrieval results are output.

[0064] The embodiment of the present invention provides a personnel information big data screening method based on human and document recognition. First, verification information of a human and document recognition device is obtained through a data acquisition interface; the human and document recognition device is used to realize verification and comparison between personnel and documents, and the verification information includes the verification and comparison result and the verification and recognition parameters; then, based on the verification and recognition parameters, the on-site video data of the personnel information is called in the target video surveillance device; then, based on the BFS breadth-first algorithm, image retrieval of the on-site video data in the time dimension and the space dimension is performed respectively to determine the target personnel information matching the verification information; the target personnel information includes: verification information of human and document recognition and target location information. Through the above method, human and document recognition and on-site personnel information screening are realized, and on-site personnel can be located, which reduces the difficulty and cost of personnel information screening and management, realizes unified service management for personnel information, and reduces the effect of computing resources.

[0065] The personnel information big data screening method based on human-document recognition provided in this embodiment uses human-document recognition to realize face and document verification and comparison, adopts POST form-data format to extract face recognition code in human-document recognition, associates production site video surveillance system SKD call code, and uses BFS graph retrieval algorithm and Dijkstra big data fusion technology to realize breadth-first analysis algorithm for video image retrieval and recognition. It can achieve the recognition of unsafe behaviors under human-document recognition data and on-site video surveillance, and avoid various incompatibilities and repeated development problems of multiple devices, multiple systems, and multiple interfaces.

[0066] In addition, the present invention also provides a personnel information big data screening system based on human evidence recognition, see Figure 2 As shown, the system includes: an application platform layer and a big data logic processing layer;

[0067] The application platform layer is used to obtain verification information from the person identification device and to call on-site video data of personnel information; the application platform layer is also used to clean the collected data and set rules for the data;

[0068] The big data logic processing layer is used to process the data sent by the application platform layer; the big data logic processing layer includes: enabling the collection module, the data verification module, the security verification module and the data docking module; the big data logic processing layer is also used to send the processed data to the application platform layer for data application.

[0069] In one embodiment, the system also includes: a basic equipment layer, the basic equipment layer includes: a person identification device and a video surveillance device; the person identification device is used to perform personnel identity verification and face comparison verification; the video surveillance device is used to perform video monitoring and video storage; the basic equipment layer is connected to the application platform layer.

[0070] At the data collection interface level, the above system can be embedded through API to form a record receiving interface that supports HTTP Post requests and interprets the received data according to the corresponding format specifications; this interface is used to receive verification records of various types of human identification devices, where the specific parameters are:

[0071] Device request method: HTTP Post;

[0072] ContentType: application / x-www-form-urlencoded;

[0073] Character encoding: charset=utf-8;

[0074] The data interface fields are described as follows:

[0075] deviceNo string The unique serial number of the device;

[0076] validateType Int verification type: 0 real name verification 2 online certificate verification;

[0077] machineCode string device identifier, indicating which device uploaded the record;

[0078] name string name;

[0079] sex string, gender, for example: male, female, unknown;

[0080] nation string, nation, for example: Han;

[0081] born string Date of birth, in the format of "yyyy-MM-dd-yyy", for example: January 1, 2019;

[0082] address string ID address;

[0083] certNumber string certificate number;

[0084] Police string Issuing authority, for example: Public Security Bureau of XX District, XX City

[0085] startDate string The valid start date of the certificate, in the format of "yyyy.MM.dd", for example: 2019.01.01;

[0086] endDate string: the expiration date of the certificate, in the format of "yyyy.MM.dd", for example: 2019.01.01 or "valid forever";

[0087] headImg string ID card headshot, image converted to base64 string;

[0088] cameraImg string The scene recognition image is converted to base64 string;

[0089] workImg string After the on-site photo is captured, the image is converted to a base64 string;

[0090] frontImg string: A photo of the ID card taken on site, reserved field, the image is converted to a base64 string;

[0091] fingerCollectImg string collects fingerprint images on site and converts the images into base64 strings;

[0092] faceScore int face verification score (score range 0 to 1), for example: 0.86;

[0093] faceResult int face verification result, for example: 0 means failed; 1 means passed; 2 means not verified;

[0094] fingerScore int fingerprint verification score (score range 0 to 1), for example: 0.86;

[0095] fingerResult int fingerprint verification result, for example: 0 for failure; 1 for pass; 2 for verification;

[0096] isCertOut int Whether the certificate has expired, for example: 0 means not expired; 1 means expired;

[0097] isBlack int Whether the person is on the internal blacklist, for example: 0 means not on the blacklist; 1 means on the blacklist;

[0098] createDate string verification time, the format is "yyyy-MM-dd";

[0099] createTime string Verification time, in the format of "yyyy-MM-dd HH:mm:ss".

[0100] At the data relationship management level, this technology targets the big data characteristics of personnel information and supports secondary rule definition for the characteristic meta-attributes that constitute the data standard, including but not limited to multi-dimensional attribute definitions such as measurement, value, synonym library, verification, threshold, page presentation, prefix and suffix symbols, and appendix value. It can also support setting changes and attribute maintenance rule settings according to different application scenarios. In terms of data relationship presentation, the complete topological structure between data is formed and referenced using one-to-one, one-to-many, many-to-many and other methods, presenting the complex logic between data in a lightweight way to data users.

[0101] At the data verification level, an independent data verification rule engine technology is used to separate the data verification rule logic from the technology of application developers. This can effectively improve the maintainability of verification rules that implement complex logic, meet the use of agile or iterative verification rule setting processes in different application scenarios, and simultaneously complete verification and certification of verification rule conflicts and verification rule order. By setting a simple scripting language rule window, new rules can be added and imported based on this window, and embedded development of general development languages ​​can be achieved through APIs.

[0102] Hadoop provides reliable storage HDFS and MapReduce programming paradigm for large-scale parallel data processing. Hbase implements large-scale distributed NoSQL database and provides random access to large amounts of unstructured and semi-structured massive data.

[0103] The present embodiment provides a personnel information big data screening system based on human evidence recognition, which is positioned as a tool set for providing accurate information to data applications through data extraction, data processing, and data analysis. It can accurately extract data from massive data through a continuously improved data feature library, and then perform in-depth processing of big data to quickly understand the characteristics, behaviors, and result judgments of the target audience, and provide result support for the decision-making of system applications.

[0104] In addition, the embodiment of the present invention provides a personnel information big data screening device based on human evidence recognition, see Figure 3 As shown, the device comprises:

[0105] The verification information acquisition module 310 is used to obtain the verification information of the person-document identification device through the data acquisition interface; the data acquisition interface is used to receive the verification information from different types of person-document identification devices; the person-document identification device is used to realize the verification and comparison between the person and the document, and the verification information includes the verification and comparison results and the verification and identification parameters;

[0106] A live video data calling module 320, for calling live video data of personnel information in a target video surveillance device based on verification identification parameters;

[0107] The target person information determination module 330 is used to perform image retrieval in the time dimension and the space dimension of the on-site video data based on the BFS breadth-first algorithm to determine the target person information that matches the verification information; the target person information includes: verification information for witness identification and target location information.

[0108] The personnel information big data screening device based on witness identification provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application, its implementation principle and the technical effect produced are the same as those in the aforementioned method embodiment. For the sake of brief description, for the parts not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. The personnel information big data screening device based on witness identification provided in the embodiment of the present application has the same technical features as the personnel information big data screening method based on witness identification provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0109] An embodiment of the present application further provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0110] Figure 4 A structural schematic diagram of an electronic device provided in an embodiment of the present application, the electronic device 400 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0111] The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0112] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0113] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the process definition device disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0114] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 40. The above processor 40 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor to execute, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0115] Corresponding to the above method, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the steps of the above method.

[0116] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0119] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0120] It should be noted that similar numbers and letters represent similar items in the accompanying drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for screening big data of personnel information based on human evidence recognition, characterized in that: Applied to a personnel big data screening system based on human evidence recognition, the method comprises: The verification information of the person-document identification device is obtained through the data acquisition interface; the data acquisition interface is used to receive the verification information from different types of person-document identification devices; the person-document identification device is used to verify and compare the person and the document, and the verification information includes the verification and comparison results and the verification and identification parameters; Based on the verification identification parameters, calling the on-site video data of the personnel information in the target video surveillance device; Based on the BFS breadth-first algorithm, image retrieval is performed on the on-site video data in the time dimension and the space dimension respectively to determine the target person information matching the verification information; the target person information includes: verification information for witness identification and target location information.

2. The method for screening big data of personnel information based on human evidence recognition according to claim 1 is characterized in that: The data collection interface is embedded in the personnel big data screening system based on human evidence recognition through an API; The verification information of the person identification device is obtained through the data collection interface, including: The data acquisition interface receives verification records from different types of identity verification devices, parses the verification records based on HTTP POST requests, and outputs verification information; the verification information includes: verification and comparison results and verification identification parameters; the verification identification parameters include: face recognition coding information, device identification parameters, personnel information parameters and verification parameters.

3. The method for screening big data of personnel information based on human evidence recognition according to claim 2 is characterized in that: Based on the verification and identification parameters, calling the on-site video data of the personnel information in the target video surveillance device includes: Based on the verification and identification parameters, determine the target video surveillance device and perform SDK interface parameter configuration; The on-site video data of the personnel information is called in the target video surveillance device through the SDK interface.

4. The method for screening big data of personnel information based on human evidence recognition according to claim 2 is characterized in that: Based on the BFS breadth-first algorithm, image retrieval is performed on the on-site video data in the time dimension and the space dimension respectively to determine the target person information matching the verification information, including: Utilize FFStreamer to encode the on-site video data frame by frame to generate graphic data to be identified; Decomposing the to-be-identified graphic data according to the time dimension and the space dimension based on the BFS breadth-first algorithm; Based on the verification and recognition parameters, image retrieval is performed on the decomposed time dimension and space dimension of the to-be-recognized graphic data to determine the target person information that matches the verification information.

5. The method for screening big data of personnel information based on human evidence recognition according to claim 4 is characterized in that: The graphic data to be identified includes a queue node that matches a big data field; the queue node includes a plurality of vertices; the big data field is a target screening condition; the target screening condition corresponds to at least one personnel information feature.

6. A personnel information big data screening system based on human evidence recognition, characterized in that: The system includes: an application platform layer and a big data logic processing layer; The application platform layer is used to obtain verification information of the person identification device and to call the on-site video data of the personnel information; the application platform layer is also used to clean the collected data and set rules for the data; The big data logic processing layer is used to process the data sent by the application platform layer; the big data logic processing layer includes: enabling collection module, data verification module, security verification module and data docking module; the big data logic processing layer is also used to send the processed data to the application platform layer for data application.

7. The personnel information big data screening system based on human evidence recognition according to claim 6 is characterized in that: The system also includes: a basic equipment layer, which includes: a person identification device and a video surveillance device; the person identification device is used to verify the identity of a person and compare and verify a face; the video surveillance device is used to perform video surveillance and video storage; the basic equipment layer is connected to the application platform layer.

8. A personnel information big data screening device based on human evidence recognition, characterized in that: include: A verification information collection module is used to obtain verification information of a person identification device through a data collection interface; The data acquisition interface is used to receive verification information from different types of human-document identification devices; the human-document identification devices are used to verify and compare personnel with documents, and the verification information includes verification and comparison results and verification and identification parameters; A live video data calling module, used to call live video data of personnel information in a target video surveillance device based on the verification identification parameters; A target person information determination module is used to perform image retrieval in the time dimension and the space dimension on the on-site video data based on a BFS breadth-first algorithm to determine the target person information that matches the verification information; The target person information includes: verification information of person identification and target location information.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method according to any one of claims 1 to 5.

Images