Human code association analysis method and device, computer equipment and storage medium

By constructing the target graph network structure and performing conditional entropy analysis and correlation analysis, the problem of low accuracy of face events and code events matching analysis is solved, efficient human code correlation analysis is achieved, and the efficiency of determining the degree of matching is improved.

CN119251529APending Publication Date: 2025-01-03SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411226167.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2025-01-03

AI Technical Summary

Technical Problem

In the monitoring site, the matching analysis of face events and code events is low, making it difficult to accurately determine face events and code events with a higher degree of matching.

Method used

By constructing the target graph network structure, based on conditional entropy analysis and correlation analysis, the first face code pair with high confidence and low uncertainty in the current time period are selected, and the second person with a higher degree of matching is further determined. Face code pairs to realize human code correlation analysis.

Benefits of technology

It improves the efficiency of determining the degree of matching between face events and code events, saves manpower and material resources, reduces the processing needs for a large amount of data, and realizes efficient and convenient human code correlation analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119251529A_ABST
    Figure CN119251529A_ABST
Patent Text Reader

Abstract

The invention discloses a person code association analysis method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring current person code data in a current time period; determining a target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period; on the basis of the target graph network structure, conditional entropy analysis is carried out on the current human code data of the current time period and the historical human code data of the historical time period, and M first human face code pairs corresponding to the current time period are determined; and performing correlation analysis on the M first face code pairs corresponding to the current time period, and determining N second face code pairs corresponding to the current time period. According to the method, a large amount of data does not need to be processed, the efficiency of human code correlation analysis is improved, and the second human face code pair with the high matching degree between the human face event and the code event can be accurately obtained through conditional entropy analysis and correlation analysis and twice analysis and screening, so that human code correlation analysis is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of event analysis, and in particular to a method, device, computer equipment and storage medium for analyzing the association between a person and a code. Background Art

[0002] With the continuous advancement of science and technology, face events and code events that occur at the same time and space in the monitored place are usually analyzed to determine face events and code events with a higher degree of matching, so as to facilitate more accurate monitoring of the monitored place. In the prior art, face events and code events are usually directly matched to determine face events and code events with a higher degree of matching. However, this method requires processing a large amount of data, resulting in a low accuracy in analyzing face events and code events. Therefore, how to more accurately determine face events and code events with a higher degree of matching is a technical problem that needs to be solved at present. Summary of the invention

[0003] The embodiments of the present invention provide a method, apparatus, computer device and storage medium for analyzing the association between a person and a code, so as to solve the problem of how to more accurately determine a face event and a code event with a high matching degree.

[0004] A person-code association analysis method, comprising:

[0005] Get the current person code data of the current time period;

[0006] Determine the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period;

[0007] Based on the target graph network structure, conditional entropy analysis is performed on the current person code data of the current time period and the historical person code data of the historical time period to determine M first face code pairs corresponding to the current time period, where M≥2;

[0008] Perform correlation analysis on the M first face code pairs corresponding to the current time period to determine N second face code pairs corresponding to the current time period, where N≥1.

[0009] Preferably, the determining of the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period includes:

[0010] The current person code data of the current time period and the historical person code data of the historical time period are combined to determine the target person code data corresponding to the current time period;

[0011] Based on the target person code data corresponding to the current time period, the target graph network structure is determined.

[0012] Preferably, the method of performing conditional entropy analysis on the current person code data of the current time period and the historical person code data of the historical time period based on the target graph network structure to determine the M first face code pairs corresponding to the current time period includes:

[0013] Acquire at least one target connectivity graph in the target graph network structure;

[0014] Performing conditional entropy analysis on each of the target connectivity graphs to determine a conditional entropy analysis result corresponding to each initial face code pair in each of the target connectivity graphs;

[0015] Based on the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph, the M first face code pairs corresponding to the current time period are determined.

[0016] Preferably, performing conditional entropy analysis on each target connectivity graph to determine the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph includes:

[0017] Based on each of the target connectivity graphs, determining, in each initial face-code pair of each target connectivity graph, a first conditional probability corresponding to a face event, a second conditional probability corresponding to a code event, and a joint probability corresponding to the initial face-code pair;

[0018] Based on the first conditional probability, the second conditional probability and the joint probability, a conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph is determined.

[0019] Preferably, the determining of the M first face code pairs corresponding to the current time period based on the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph includes:

[0020] The first M initial face code pairs with smaller conditional entropy analysis results in all the target connected graphs are determined as the M first face code pairs corresponding to the current time period.

[0021] Preferably, the performing correlation analysis on the M first face code pairs corresponding to the current time period to determine the N second face code pairs corresponding to the current time period includes:

[0022] Performing correlation analysis on the M first face code pairs to determine correlation analysis results corresponding to the M first face code pairs;

[0023] Based on the association analysis results corresponding to the M first face code pairs, N second face code pairs are determined.

[0024] Preferably, performing correlation analysis on the M first face code pairs to determine correlation analysis results corresponding to the M first face code pairs includes:

[0025] Perform logarithmic processing on the number of valid points and the number of occurrences of the M first face code pairs to obtain the first correlation degrees corresponding to the M first face code pairs;

[0026] Performing logarithmic processing on the number of occurrences and valid days of the M first face-code pairs to obtain the second correlation degrees corresponding to the M first face-code pairs;

[0027] According to the first association degrees corresponding to the M first face code pairs and the second association degrees corresponding to the M first face code pairs, the association degree analysis results corresponding to the M first face code pairs are obtained.

[0028] A person-code association analysis device, comprising:

[0029] The current person code data acquisition module is used to obtain the current person code data of the current time period;

[0030] A target graph network structure determination module determines the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period;

[0031] A first face code pair determination module, based on the target graph network structure, performs conditional entropy analysis on the current person code data of the current time period and the historical person code data of the historical time period to determine M first face code pairs corresponding to the current time period, where M≥2;

[0032] The second face code pair determination module is used to perform correlation analysis on the M first face code pairs corresponding to the current time period to determine the N second face code pairs corresponding to the current time period, where N≥1.

[0033] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned human-code association analysis method when executing the computer program.

[0034] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the human-code association analysis method is implemented.

[0035] The above-mentioned person-code association analysis method, device, computer equipment and storage medium construct a target graph network structure, which can more comprehensively reflect the many-to-many and multi-level relationship between face events and code events. By performing conditional entropy analysis on the target graph network structure, M first face-code pairs with high credibility and low uncertainty corresponding to the current time period can be obtained more accurately, and the method does not need to analyze and screen face events and code events outside the target graph network structure, saving manpower and material resources, and is more efficient and convenient. In the current time period, the M first face-code pairs obtained by the conditional entropy analysis are analyzed for correlation, and N second face-code pairs with a high degree of matching between face events and code events are determined. There is no need to perform correlation analysis on a large amount of data, which can improve the efficiency of determining the second face-code pairs. In addition, the method performs correlation analysis on the first face-code pairs screened by the conditional entropy analysis, and further screens the first face-code pairs with high credibility and low uncertainty, so that the second face-code pairs with a high degree of matching can be obtained more accurately. The method constructs a target graph network structure, performs conditional entropy analysis based on the target graph network structure, obtains a first face-code pair, performs correlation analysis based on the first face-code pair, and obtains a second face-code pair with a high degree of matching between face events and code events. This method not only eliminates the need to process more data, thereby improving the efficiency of face-code correlation analysis, but also performs two analysis and screenings through conditional entropy analysis and correlation analysis, thereby being able to more accurately obtain the second face-code pair with a high degree of matching between face events and code events, thereby realizing face-code correlation analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0037] Figure 1 is a flow chart of a method for analyzing a person-code association in one embodiment of the present invention;

[0038] Figure 2 is another flow chart of a method for analyzing a person-code association in one embodiment of the present invention;

[0039] Figure 3 is another flow chart of a method for analyzing a person-code association in one embodiment of the present invention;

[0040] Figure 4 is another flow chart of a method for analyzing a person-code association in one embodiment of the present invention;

[0041] Figure 5 is another flow chart of a method for analyzing a person-code association in one embodiment of the present invention;

[0042] Figure 6 is another flow chart of a method for analyzing a person-code association in one embodiment of the present invention;

[0043] Figure 7 is a schematic diagram of a person-code association analysis device according to an embodiment of the present invention;

[0044] Figure 8 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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. 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.

[0046] The embodiment of the present invention provides a person-code association analysis method, which is applied in a person-code association analysis system. The person-code association analysis system includes a device for collecting face events and code events, and a computer device for executing the person-code association analysis method, for the purpose of more accurately determining face events and code events with a higher degree of matching.

[0047] Among them, face-code association analysis refers to the process of analyzing face events and code events that occur in the same time and space, and determining face events and code events with a high degree of matching that occur in the same time and space. The same time and space refers to the same monitoring range and the same time.

[0048] In an embodiment of the present invention, a face event is an event in which a face image corresponding to a target person is collected. A code event is an event in which code information corresponding to a target person is collected. Among them, a target person refers to a person who needs to be monitored. Each target person corresponds to a face event and a code event. Code information includes but is not limited to an ID card code, a QR code, and an identity code, which is used to characterize the identity of the target person. Understandably, in a monitoring scenario, at least two target persons usually appear in the same time and space, and face events and code events corresponding to at least two target persons are collected. However, since the correspondence between face events and code events cannot be directly identified, it is necessary to match and analyze the face events and code events collected in the same time and space to obtain face events and code events with a higher degree of matching, so as to monitor the target person more accurately through face events and code events with a higher degree of matching. Therefore, this embodiment provides a method for human-code association analysis to more accurately determine face events and code events with a higher degree of matching.

[0049] In one embodiment, if Figure 1 As shown, a method for analyzing the association between a person and a code is provided, and the method is applied in Figure 8 The computer device in the example is used as an example to illustrate, including the following steps:

[0050] S101: Obtain the current person code data of the current time period;

[0051] S102: Determine the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period;

[0052] S103: Based on the target graph network structure, conditional entropy analysis is performed on the current person code data of the current time period and the historical person code data of the historical time period to determine M first face code pairs corresponding to the current time period, where M≥2;

[0053] S104: performing correlation analysis on the M first face code pairs corresponding to the current time period to determine N second face code pairs corresponding to the current time period, where N≥1.

[0054] Among them, the current time period refers to the time period in which the human code association analysis is currently required. The target period refers to the time period for performing the human code association analysis. The time period refers to a fixed time length preset within a target period. Understandably, in order to save storage space, control the amount of data for human code association analysis, and improve the efficiency of human code association analysis, dynamic human code association analysis is performed according to a certain target period. For example, the target period is set to 90 days. Within the 90-day target period, the first day is the first time period, and the 90th day is the last time period. If the current time period is the 90th day, it is determined that the target period ends. After the current target period ends, the next target period is updated to the current target period, and the second time period (i.e., the second day) in the previous target period is determined as the first time period (i.e., the first day) of the current target period, and so on, to obtain each target period, so as to realize dynamic human code association analysis for each target period.

[0055] The current face code data refers to the data generated by the combination of face events and code events that occur in the same time and space in the current time period, including but not limited to the initial face code pair, and the data corresponding to the face event and code event in the initial face code pair. Among them, the initial face code pair refers to the combination of face events and code events that appear in the same time and space in the current time period and the historical time period. The historical time period refers to all time periods before the current time period in the target period.

[0056] As an example, in step S101, the computer device obtains the current person code data corresponding to the current time period in at least one monitoring range in the same time and space, wherein the current time period can be any time period from the first time period to the last time period in the target cycle. For example, if the monitoring range includes monitoring range A, monitoring range B, and monitoring range C, the current person code data consisting of the face events and code events that appear simultaneously in monitoring range A, monitoring range B, and monitoring range C in the current time period are respectively obtained. For example, if in monitoring range A, a face event and b code events appear simultaneously in the current time period, the computer device combines a face event and b code events to obtain the number of initial face code pairs as a*b, and obtains the data corresponding to a*b initial face code pairs. In this example, the data corresponding to a*b initial face code pairs and a*b initial face code pairs constitute the current person code data. Similarly, the current person code data corresponding to the current time period in monitoring range B and the current person code data corresponding to the current time period in monitoring range C are respectively obtained in the above manner.

[0057] Among them, historical person-code data refers to the data generated by the combination of face events and code events that appear in the same time and space in each time period within the historical time period. The target graph network structure refers to the graph network structure corresponding to face events and code events that appear in the same time and space, which is constructed based on the current person-code data and historical person-code data. Understandably, in the target graph network structure, nodes represent face events and code events, and the node pairs in the target graph network structure represent the initial face-code pairs composed of face events and code events that appear in the same time and space in the current time period and the historical time period, and each node pair includes the current person-code data and historical person-code data of each initial face-code pair. Understandably, if a face events and b code events are collected in the same time and space within a time period, a face events and b code events are combined to obtain a*b initial face-code pairs. If face events A1 and A2, and code events B1 and B2 appear in the same time and space in the current time period and the historical time period, the face events A1 and A2, and code events B1 and B2 are combined to obtain four initial face code pairs, namely A1 and B1, A1 and B2, A2 and B1, and A2 and B2.

[0058] As an example, in step S102, the computer device constructs a node pair corresponding to each initial face code pair based on the initial face code pairs that appear in the same time and space in the current time period and the current face code data corresponding to each initial face code pair, and the initial face code pairs that appear in the same time and space in the historical time period and the historical face code data corresponding to each initial face code pair, and each node pair constitutes the target graph network structure corresponding to the current time period. Among them, each node pair represents the initial face code pair in the current time period and the historical time period. In this example, constructing the target graph network structure can more comprehensively reflect the many-to-many and multi-level relationship between face events and code events, and facilitates the screening and analysis of the target graph network structure to more accurately obtain the first face code pair.

[0059] The conditional entropy analysis refers to the analysis process of determining the conditional entropy corresponding to each initial face-code pair in the target graph network structure. The first face-code pair refers to the face-code pair consisting of face events and code events obtained by screening the initial face-code pairs in the target graph network structure.

[0060] As an example, in step S103, the computer device performs conditional entropy analysis on the current person code data and historical person code data corresponding to the initial face code pair in the target graph network structure corresponding to the current time period, determines the analysis result corresponding to each initial face code pair, and screens all the initial face code pairs in the target graph network structure according to the analysis result to determine the M first face code pairs corresponding to the current time period, where M≥2. It can be understood that the conditional entropy of the initial face code pair can reflect the credibility and uncertainty of the match between the face event and the code event in the initial face code pair. The lower the conditional entropy, the higher the credibility and the lower the uncertainty of the match between the face event and the code event. Wherein, matching means that the face event and the code event correspond to the same target person. In this example, conditional entropy analysis is used to screen M first face-code pairs with high credibility and low uncertainty. This method can more accurately obtain M first face-code pairs with high credibility and low uncertainty corresponding to the current time period by performing conditional entropy analysis on the target graph network structure. Moreover, this method does not need to analyze and screen face events and code events outside the target graph network structure, thus saving manpower and material resources and being more efficient and convenient.

[0061] The correlation analysis refers to the analysis process of determining the correlation between the face event and the code event in each first face-code pair. The second face-code pair refers to the face-code pair obtained by screening the first face-code pair.

[0062] As an example, in step S104, the computer device performs correlation analysis on the M first face code pairs screened in the current time period, obtains the correlation corresponding to each first face code pair, and analyzes and screens the M first face code pairs according to the correlation corresponding to each first face code pair, and determines the second face code pair corresponding to the current time period, which has a higher degree of matching between the face event and the code event. In this example, the computer device determines whether the current time period is the last time period of the target cycle. If the current time period is not the last time period of the target cycle, then continue to execute steps S101 to S104, that is, continue to obtain the second face code pair corresponding to each current time period in the target cycle, until the current time period is the last time period in the target cycle, and determine the second face code pair corresponding to the last time period as the second face code pair corresponding to the target cycle. It can be understood that the higher the correlation corresponding to the first face code pair, the higher the correlation between the face event and the code event in the first face code pair, that is, the higher the matching degree. The second face code pair includes face events and code events with a higher degree of matching. In this example, the M first face-code pairs obtained by the conditional entropy analysis in the current time period are subjected to correlation analysis to determine N second face-code pairs with a high degree of matching between face events and code events. This method does not require correlation analysis on a large amount of data, and can improve the efficiency of determining the second face-code pairs. In addition, this method performs correlation analysis on the first face-code pairs screened by the conditional entropy analysis, further screens the first face-code pairs with higher credibility and lower uncertainty, and can more accurately obtain the second face-code pairs with a higher degree of matching.

[0063] In this embodiment, the target graph network structure is constructed, which can more comprehensively reflect the many-to-many and multi-level relationship between face events and code events. By performing conditional entropy analysis on the target graph network structure, M first face code pairs with high credibility and low uncertainty corresponding to the current time period can be obtained more accurately, and the method does not need to analyze and screen face events and code events outside the target graph network structure, saving manpower and material resources, and is more efficient and convenient. In the current time period, the M first face code pairs obtained by the conditional entropy analysis are analyzed for correlation, and N second face code pairs with a high degree of matching between face events and code events are determined. There is no need to perform correlation analysis on a large amount of data, which can improve the efficiency of determining the second face code pairs, and the method performs correlation analysis on the first face code pairs screened by the conditional entropy analysis, and further screens the first face code pairs with high credibility and low uncertainty, so that the second face code pairs with a high degree of matching can be obtained more accurately. The method constructs a target graph network structure, performs conditional entropy analysis based on the target graph network structure, obtains a first face-code pair, performs correlation analysis based on the first face-code pair, and obtains a second face-code pair with a high degree of matching between face events and code events. This method not only eliminates the need to process more data, thereby improving the efficiency of face-code correlation analysis, but also performs two analysis and screenings through conditional entropy analysis and correlation analysis, thereby being able to more accurately obtain the second face-code pair with a high degree of matching between face events and code events, thereby realizing face-code correlation analysis.

[0064] In one embodiment, if Figure 2 As shown, step S102, i.e., determining the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period, includes:

[0065] S201: merging the current person code data of the current time period and the historical person code data of the historical time period to determine the target person code data corresponding to the current time period;

[0066] S202: Determine the target graph network structure based on the target person code data corresponding to the current time period.

[0067] The target person code data refers to the data obtained by merging the current person code data and the historical person code data.

[0068] As an example, in step S201, the computer device merges the same current person code data and historical person code data within the target period to obtain the target person code data corresponding to the current time period after the merge; or, after merging the current person code data and the historical person code data to obtain the merged data, the merged data is filtered according to preset filtering conditions to obtain the target person code data corresponding to the current time period.

[0069] In this example, the current person code data and historical person code data include but are not limited to the number of valid points of the initial face code pair, the number of occurrences of the initial face code pair, and the number of valid days of the initial face code pair. Among them, the number of valid points refers to the number of locations where the face code pair composed of face events and code events occurring in the same time and space appears. The number of occurrences refers to the number of times the face code pair composed of face events and code events occurring in the same time and space appears. The valid days refer to the number of days that the face code pair composed of face events and code events occurring in the same time and space appears. Understandably, if an initial face code pair composed of face events and code events occurring in the same time and space appears twice in monitoring range A on the first day and three times in monitoring range B on the third day during the current time period and the historical time period, the initial face code pair appears in a time period of 3 days, then the number of valid points is 2, the number of occurrences is 5, and the number of valid days is 3.

[0070] In this example, the computer device performs cumulative merging processing on the number of valid points of the initial face code pair in the current time period and the number of valid points of the initial face code pair in the historical time period, performs cumulative merging processing on the number of occurrences of the initial face code pair in the current time period and the number of occurrences of the initial face code pair in the historical time period, and performs cumulative merging processing on the number of valid days of the initial face code pair in the current time period and the number of valid days of the initial face code pair in the historical time period, and obtains the number of valid points of each initial face code pair, the number of occurrences of each initial face code pair, and the number of valid days of each initial face code pair after cumulative merging processing. In this example, the preset screening conditions include but are not limited to the current time period and the historical time period, the number of valid points of each initial face code pair is not less than the preset number of points threshold, the number of occurrences of each initial face code pair is not less than the preset number of times threshold, and / or the number of valid days of each initial face code pair is not less than the preset number of days threshold. The computer device determines whether the number of valid points of each initial face code pair after cumulative merging processing, the number of occurrences of each initial face code pair and / or the valid days of each initial face code pair meet the preset filtering conditions according to the preset filtering conditions, retains the initial face code pairs that meet the preset filtering conditions, and the data such as the number of valid points, the number of occurrences and the valid days of each initial face code pair after cumulative merging processing, and determines the initial face code pairs that meet the preset filtering conditions, and the number of valid points, the number of occurrences and the valid days of each initial face code pair after cumulative merging processing as the target face code data corresponding to the current time period.

[0071] In this example, the current person code data of the current time period and the historical person code data of the historical time period are merged and filtered to obtain the target person code data corresponding to the current time period. The data is merged and filtered to retain the data that meets the requirements, reduce the amount of data processing, and facilitate more efficient construction of the target graph network structure.

[0072] As an example, in step S202, the computer device processes the target person code data corresponding to the current time period to determine the target graph network structure. Understandably, the target graph network structure is used to more intuitively reflect whether the face event and the code event co-occur in the same time and space. Therefore, in the initial face code pair, the face event and the code event are determined as nodes of the target graph network structure. If there is an edge connection between the nodes, the face event corresponding to the node and the code event co-occur in the same time and space, and the face event and the code event constitute the initial face code pair. If there is no edge connection between the nodes, the face event and the code event corresponding to the node do not co-occur in the same time and space, and the face event and the code event cannot constitute the initial face code pair. In this example, the computer device constructs a target graph network structure based on the initial face code pair in the target person code data, determines the face events and code events contained in the initial face code pair as nodes of the target graph network structure, and the initial face code pair is the node pair of the target graph network structure. The number of valid points, the number of occurrences, or the number of valid days of each initial face code pair in the target person code data is determined as the weight between the node pairs corresponding to each initial face code pair. In this example, the target graph network structure is determined to facilitate a more accurate conditional entropy analysis based on the target graph network structure.

[0073] In this embodiment, the data is merged and processed, and the data that meets the requirements is retained, thereby reducing the amount of data processing, facilitating more efficient construction of the target graph network structure, determining the target graph network structure, and facilitating more accurate conditional entropy analysis based on the target graph network structure.

[0074] In one embodiment, if Figure 3 As shown, step S103, i.e., based on the target graph network structure, conditional entropy analysis is performed on the current person code data of the current time period and the historical person code data of the historical time period to determine the M first face code pairs corresponding to the current time period, including:

[0075] S301: Acquire at least one target connectivity graph in a target graph network structure;

[0076] S302: Performing conditional entropy analysis on each target connectivity graph to determine a conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph;

[0077] S303: Based on the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph, determine M first face code pairs corresponding to the current time period.

[0078] The target connectivity graph refers to the connectivity graph in the target graph network structure.

[0079] As an example, in step S301, the computer device divides the target graph network structure into connected graphs according to the method of dividing connected graphs, and obtains at least one target connected graph in the target graph network structure. In the target graph network structure, there may be partially connected nodes and partially disconnected nodes. For example, if the face event A1 in the target graph network structure is connected to the code event B1 and the code event B2 respectively, and is not connected to the code event B3, and the face event A2 is connected to the code event B3, and is not connected to the code event B1 and the code event B2, then according to the method of dividing the connected graph, the face event A1 and the code event B1 and the code event B2 constitute a target connected graph, and the face event A2 and the code event B3 constitute another target connected graph. According to the above method, the target graph network structure is divided into connected graphs to obtain at least one target connected graph in the target graph network structure.

[0080] The conditional entropy analysis result refers to the conditional entropy of the initial face code pair.

[0081] As an example, in step S302, the computer device performs conditional entropy analysis on each target connectivity graph, determines the conditional entropy corresponding to each initial face code pair in each target connectivity graph, and determines the conditional entropy corresponding to each initial face code pair as the conditional entropy analysis result. In this example, performing conditional entropy analysis on each target connectivity graph can reduce the amount of data for calculating the conditional entropy corresponding to the initial face code pair, so that the conditional entropy analysis result corresponding to the initial face code pair is more accurate.

[0082] As an example, in step S303, the computer device analyzes the conditional entropy analysis results corresponding to each initial face code pair in each target connectivity graph, and determines the M first face code pairs corresponding to the current time period. In this example, the computer device can filter each initial face code pair in each target connectivity graph according to a preset conditional entropy range to obtain the M first face code pairs corresponding to the current time period. In this example, the conditional entropy analysis results corresponding to each initial face code pair in each target connectivity graph are analyzed, and the initial face code pairs are filtered to obtain the M first face code pairs corresponding to the current time period, thereby reducing the amount of data and facilitating the improvement of the efficiency of face code association analysis.

[0083] In this embodiment, a target connectivity graph in the target graph network structure is obtained, and the conditional entropy analysis results corresponding to each initial face code pair in each target connectivity graph are analyzed. The initial face code pairs are screened to obtain M first face code pairs corresponding to the current time period, which can reduce the amount of data and facilitate improving the efficiency of face code association analysis.

[0084] In one embodiment, if Figure 4As shown, step S302, i.e., performing conditional entropy analysis on each target connectivity graph to determine the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph, includes:

[0085] S401: Based on each target connectivity graph, determining, in each initial face-code pair of each target connectivity graph, a first conditional probability corresponding to a face event, a second conditional probability corresponding to a code event, and a joint probability corresponding to the initial face-code pair;

[0086] S402: Determine a conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph based on the first conditional probability, the second conditional probability and the joint probability.

[0087] The first conditional probability refers to the probability that the face event occurs in the same time and space when the code event occurs. The second conditional probability refers to the probability that the code event occurs in the same time and space when the face event occurs. The joint probability refers to the probability that the face event and the code event occur in the same time and space.

[0088] As an example, in step S401, the computer device obtains the number of occurrences of each node pair (i.e., the initial face code pair formed by the face event and the code event) in each target connected graph based on the target person code data corresponding to each initial face code pair in the target graph network structure, accumulates the number of occurrences of the node pairs corresponding to the same face event to obtain the number of occurrences of the same face event, accumulates the number of occurrences of all face events to obtain the total number of occurrences of all face events; accumulates the number of occurrences of the node pairs corresponding to the same code event to obtain the number of occurrences of the same code event; accumulates the number of occurrences of all code events to obtain the total number of occurrences of all code events; accumulates the number of occurrences of all node pairs to obtain the total number of occurrences of all node pairs in the target connected graph. Then, the computer device calculates the number of occurrences c of the kth node pair in a target connected graph. k The total number of occurrences of all node pairs in the target connected graph is processed by ratio processing, and the joint probability P3 corresponding to the initial face code pair in the kth node pair is obtained. k / C. According to the above method, the joint probability P3 corresponding to the initial face code pair in each node pair in each target connected graph is obtained. The number of occurrences of the i-th face event d i The first conditional probability P1=d corresponding to the ith face event is obtained by performing ratio processing with the total number of occurrences of all face events D. i / D, according to the above method, the first conditional probability P1 corresponding to each face event in each target connected graph is obtained. The number of occurrences of the jth code event e j The ratio of the total number of occurrences of all face events E is processed to obtain the second conditional probability P2 corresponding to the jth code event = ej / E, according to the above method, the second conditional probability P2 corresponding to each code event in each target connected graph is obtained.

[0089] Among them, the total number of occurrences of all face events refers to the sum of the number of occurrences of all face events in the target connected graph. The total number of occurrences of all code events refers to the sum of the number of occurrences of all code events in the target connected graph. The total number of occurrences of all node pairs refers to the sum of the number of occurrences of all initial face-code pairs (node ​​pairs) in the target connected graph. In this example, the kth node pair is a node pair corresponding to an initial face-code pair consisting of the i-th face event and the j-th code event co-occurring in the same space and time in a target connected graph. The number of occurrences of the kth node pair is c k , in the target connected graph corresponding to the k-th node pair, the number of occurrences of the i-th face event is d i , in the target connected graph corresponding to the kth node pair, the number of occurrences of the jth code event is e j , the total number of occurrences of all face events is D, the total number of occurrences of all code events is E, and the total number of occurrences of all node pairs in the target connectivity graph is C.

[0090] As an example, in step S402, the computer device performs conditional entropy analysis on the first conditional probability corresponding to the face event in each initial face code pair, the second conditional probability corresponding to the code event in each initial face code pair, and the joint probability corresponding to each initial face code pair, and determines the conditional entropy corresponding to each initial face code pair in each target connected graph, and determines the conditional entropy as the conditional entropy analysis result corresponding to each initial face code pair in each target connected graph. It can be understood that the conditional entropy is used to indicate the credibility and uncertainty between the face event and the code event in the face code pair. The lower the conditional entropy, the higher the credibility and the smaller the uncertainty between the face event and the code event in the face code pair. Therefore, the conditional entropy corresponding to each initial face code pair is determined as the conditional entropy analysis result corresponding to each initial face code pair, so as to facilitate the more accurate screening of the initial face code pairs based on the conditional entropy corresponding to each initial face code pair. In this example, the kth initial face code pair includes the ith face event and the jth code event, and the first conditional probability P1 corresponding to the ith face event = d i / D, the second conditional probability P2 corresponding to the jth code event = e j / E, the joint probability P3 corresponding to the initial face code pair in the kth node pair = c k / C, then the conditional entropy analysis result corresponding to the kth initial face code pair is H: H = (-P3*log(P1)) + (-P3*log(P2)). In this example, the conditional entropy analysis result corresponding to each initial face code pair is obtained to facilitate more accurate analysis and screening of the initial face code pairs to obtain the first face code pair.

[0091] In this embodiment, the conditional entropy analysis result corresponding to each initial face code pair is obtained, so as to analyze and screen the initial face code pairs more accurately and obtain the first face code pair.

[0092] In one embodiment, step S303, i.e., determining the M first face code pairs corresponding to the current time period based on the conditional entropy analysis results corresponding to each initial face code pair in each target connected graph, includes: determining the first M initial face code pairs with smaller conditional entropy analysis results in all target connected graphs as the M first face code pairs corresponding to the current time period.

[0093] As an example, after obtaining the conditional entropy analysis results corresponding to the initial face code pairs in each target connected graph, the computer device sorts the conditional entropy analysis results corresponding to the initial face code pairs in all target connected graphs according to the ascending order of the conditional entropy analysis results, and determines the initial face code pairs corresponding to the first M conditional entropy analysis results as the M first face code pairs corresponding to the current time period. In this example, the conditional entropy corresponding to each initial face code pair is determined as the conditional entropy analysis result corresponding to each initial face code pair. Understandably, the conditional entropy is used to indicate the credibility and uncertainty between the face events and code events in the face code pair. The larger the conditional entropy, the lower the credibility and the greater the uncertainty between the face events and code events in the face code pair. The credibility between the face events with a higher matching degree and the code events is higher, and the uncertainty should be as small as possible. Therefore, the first M initial face code pairs with smaller conditional entropy analysis results are determined as the first face code pairs, so as to achieve a more accurate screening of each initial face code pair in the target connected graph, so as to obtain face events and code events with a higher matching degree.

[0094] In this embodiment, the first M initial face code pairs with smaller conditional entropy analysis results are determined as the first face code pairs, so as to facilitate further more accurate screening based on the first face code pairs to determine the second face code pairs with a higher matching degree.

[0095] In one embodiment, if Figure 5 As shown, step S104, performing correlation analysis on the M first face code pairs corresponding to the current time period to determine the N second face code pairs corresponding to the current time period, includes:

[0096] S501: performing correlation analysis on the M first face code pairs to determine correlation analysis results corresponding to the M first face code pairs;

[0097] S502: Determine N second face code pairs based on the correlation analysis results corresponding to the M first face code pairs.

[0098] The correlation analysis result is the correlation between the face event and the code event in the first face-code pair.

[0099] As an example, in step S501, the computer device performs a correlation analysis on the M first face code pairs obtained by screening based on the conditional entropy analysis result, determines the correlation corresponding to the M first face code pairs, and determines the correlation corresponding to each first face code pair as the correlation analysis result corresponding to each first face code pair. Understandably, the correlation is used to represent the correlation degree between the face event and the code event in the first face code pair, which can more accurately reflect the matching degree between the face event and the code event. Determining the correlation as the correlation analysis result corresponding to the first face code pair facilitates more accurate screening of the first face code pair to obtain a second face code pair with a higher matching degree.

[0100] As an example, in step S502, the computer device analyzes the correlation analysis results corresponding to each first face code pair to determine the N second face code pairs corresponding to the current time period, where M≥N. In this example, the computer device can filter each first face code pair according to the preset correlation range to obtain the N second face code pairs corresponding to the current time period. In this example, each first face code pair obtained by the conditional entropy analysis is filtered to obtain the N second face code pairs corresponding to the current time period, which has a small amount of data processing, is more efficient and convenient, and the first face code pairs obtained by the first screening are screened twice, which can more accurately determine the second face code pairs with a higher degree of matching between the face event and the code event.

[0101] In this embodiment, each first face-code pair obtained by the conditional entropy analysis is subjected to correlation analysis and screening to obtain N second face-code pairs corresponding to the current time period. The amount of data processing is small, and the method is more efficient and convenient. In addition, the first face-code pairs obtained by the first screening are subjected to a second screening, so that the second face-code pairs with a higher degree of matching between the face event and the code event can be determined more accurately.

[0102] In one embodiment, if Figure 6 As shown, step S501, i.e., performing correlation analysis on the M first face code pairs to determine the correlation analysis results corresponding to the M first face code pairs, includes:

[0103] S601: performing logarithmic processing on the number of valid points and the number of occurrences of the M first face code pairs to obtain first correlation degrees corresponding to the M first face code pairs;

[0104] S602: performing logarithmic processing on the number of occurrences and valid days of the M first face code pairs to obtain second association degrees corresponding to the M first face code pairs;

[0105] S603: Obtain correlation analysis results corresponding to the M first face code pairs according to the first correlation degrees corresponding to the M first face code pairs and the second correlation degrees corresponding to the M first face code pairs.

[0106] The first correlation refers to the correlation between the face event and the code event in the first face-code pair determined based on the number of valid points and the number of occurrences. In this example, the target person-code data includes the number of valid points, the number of occurrences, and the number of valid days corresponding to the initial face-code pair. Since the first face-code pair is a face-code pair obtained by screening the initial face-code pair, the first face-code pair has corresponding target person-code data with the number of valid points, the number of occurrences, and the number of valid days.

[0107] As an example, in step S601, the computer device performs logarithmic processing on the number of valid points of each first face code pair and the number of occurrences of each first face code pair in the M first face code pairs to obtain the first correlation degree corresponding to each first face code pair in the M first face code pairs. For example, in the first face code pair, the number of valid points is Q and the number of occurrences is Z, then the first correlation degree w1 corresponding to the first face code pair is: W1 = log Z Q. According to the above method, the first correlation degree corresponding to each first face code pair among the M first face code pairs is determined.

[0108] The second correlation degree refers to the correlation degree between the face event and the code event in the first face-code pair determined based on the number of occurrences and the number of valid days.

[0109] As an example, in step S602, the computer device performs logarithmic processing on the number of occurrences of each first face code pair and the number of valid days of each first face code pair in the M first face code pairs to obtain the second correlation degree corresponding to each first face code pair. For example, in the first face code pair, the number of valid days is R and the number of occurrences is Z, then the second correlation degree w2 corresponding to the first face code pair is: w2=log Z R. According to the above method, the second correlation degree corresponding to each first face code pair among the M first face code pairs is determined.

[0110] As an example, in step S603, the computer device performs weighted processing on the first correlation degree and the second correlation degree of each of the M first face code pairs to obtain the correlation degree analysis result of each of the M first face code pairs. In this example, for a first face code pair, if the first correlation degree w1 corresponding to the first face code pair is: w1 = log Z Q, the second correlation w2 is: W2 = log ZR, then the correlation analysis result of the first face code pair is: ω=α·w1+β·w2, where 0<α<1, 0<β<1. For example, α=0.5, β=0.2. According to the above method, the correlation analysis result corresponding to each of the M first face code pairs is determined.

[0111] In this embodiment, the first correlation degrees and the second correlation degrees corresponding to M first face code pairs are obtained, and the correlation degree analysis result corresponding to each first face code pair is determined more accurately based on the first correlation degree corresponding to each first face code pair, so as to facilitate the subsequent more accurate screening of the first face code pairs based on the correlation degree analysis result, and obtain the second face code pairs with a higher degree of matching between the face event and the code event.

[0112] In one embodiment, step S502, i.e., determining N second face code pairs based on the correlation analysis results corresponding to the M first face code pairs, includes: determining the first N first face code pairs with larger correlation analysis results among the M first face code pairs as the N second face code pairs.

[0113] As an example, after obtaining the correlation analysis results corresponding to the M first face-code pairs, the computer device sorts the correlation analysis results corresponding to the M first face-code pairs in descending order of the correlation analysis results, and determines the initial face-code pairs corresponding to the first N correlation analysis results as the N second face-code pairs corresponding to the current time period, thereby obtaining the second face-code pairs with a higher degree of matching between the face event and the code event. Understandably, the correlation analysis result is used to represent the correlation between the face event and the code event in the first face-code pair. The larger the correlation analysis result, the higher the correlation between the face event and the code event in the corresponding first face-code pair, and the higher the degree of matching. Therefore, the first N first face-code pairs with higher correlation analysis results are determined as the second face-code pairs with a higher degree of matching, so that the face event and the code event with a higher degree of matching can be determined more accurately, thereby achieving more accurate screening of the first face-code pairs.

[0114] In this embodiment, among the M first face-code pairs with high credibility and low uncertainty, the first N first face-code pairs with large correlation analysis results are determined as the N second face-code pairs corresponding to the current time period, which can more accurately screen out the N second face-code pairs with high credibility and high correlation, and can make the face events and code events determined by the N first face-code pairs have a high degree of matching. This method does not need to analyze and process a large amount of data, and can more accurately obtain the second face-code pairs composed of N face events and code events with a high degree of matching, saving human and material resources, and is more efficient and convenient.

[0115] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0116] In one embodiment, a person-code association analysis device is provided, which corresponds one-to-one to the person-code association analysis method in the above embodiment. Figure 7 As shown, the person-code association analysis device includes a current person-code data acquisition module 701, a target graph network structure determination module 702, a first face-code pair determination module 703, and a second face-code pair determination module 704. Each functional module is described in detail as follows:

[0117] The current person code data acquisition module 701 is used to acquire the current person code data of the current time period;

[0118] The target graph network structure determination module 702 determines the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period;

[0119] The first face code pair determination module 703 performs conditional entropy analysis on the current person code data of the current time period and the historical person code data of the historical time period based on the target graph network structure, and determines M first face code pairs corresponding to the current time period, where M≥2;

[0120] The second face code pair determination module 704 is used to perform correlation analysis on the M first face code pairs corresponding to the current time period to determine N second face code pairs corresponding to the current time period, where N≥1.

[0121] In one embodiment, the target graph network structure determination module 702 includes:

[0122] The target person code data determination submodule is used to combine the current person code data of the current time period and the historical person code data of the historical time period to determine the target person code data corresponding to the current time period;

[0123] The target graph network structure determination submodule determines the target graph network structure based on the target person code data corresponding to the current time period.

[0124] In one embodiment, the first face code pair determination module 703 includes:

[0125] A target connectivity graph acquisition submodule, used to acquire at least one target connectivity graph in a target graph network structure;

[0126] A conditional entropy analysis result determination submodule is used to perform conditional entropy analysis on each target connectivity graph to determine the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph;

[0127] The first face code pair determination submodule determines M first face code pairs corresponding to the current time period based on the conditional entropy analysis results corresponding to each initial face code pair in each target connectivity graph.

[0128] In one embodiment, the conditional entropy analysis result determination submodule includes:

[0129] A probability determination unit, based on each target connectivity graph, determines, in each initial face-code pair of each target connectivity graph, a first conditional probability corresponding to a face event, a second conditional probability corresponding to a code event, and a joint probability corresponding to the initial face-code pair;

[0130] The conditional entropy analysis result determination unit determines the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph based on the first conditional probability, the second conditional probability and the joint probability.

[0131] In one embodiment, the first face code pair determination submodule includes:

[0132] The first face code pair determination unit is used to determine the first M initial face code pairs with smaller conditional entropy analysis results in all target connected graphs as the M first face code pairs corresponding to the current time period.

[0133] In one embodiment, the second face code pair determination module 704 includes:

[0134] A correlation analysis result determination submodule is used to perform correlation analysis on the M first face code pairs to determine the correlation analysis results corresponding to the M first face code pairs;

[0135] The second face code pair determination submodule determines N second face code pairs based on the correlation analysis results corresponding to the M first face code pairs.

[0136] In one embodiment, the correlation analysis result determination submodule includes:

[0137] A first correlation determination unit is used to perform logarithmic processing on the number of valid points and the number of occurrences of the M first face code pairs to obtain first correlations corresponding to the M first face code pairs;

[0138] A second correlation determination unit is used to perform logarithmic processing on the number of occurrences and valid days of the M first face code pairs to obtain second correlations corresponding to the M first face code pairs;

[0139] The correlation analysis result determining unit is used to obtain correlation analysis results corresponding to the M first face code pairs according to the first correlations corresponding to the M first face code pairs and the second correlations corresponding to the M first face code pairs.

[0140] In one embodiment, the second face code pair determination submodule includes:

[0141] The second face code pair determination unit is used to determine the first N first face code pairs with larger correlation analysis results among the M first face code pairs as N second face code pairs.

[0142] For the specific definition of the human-code association analysis device, please refer to the definition of the human-code association analysis method above, which will not be repeated here. Each module in the above-mentioned human-code association analysis device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0143] In one embodiment, a computer device is provided, whose internal structure diagram can be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data used or generated during the execution of the human-code association analysis method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a human-code association analysis method is implemented.

[0144] In one embodiment, if Figure 8 As shown, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for analyzing the association between a person and a code in the above embodiment is implemented. For example, Figure 1 S101-S104 as shown, or Figures 2 to 6 Alternatively, when the processor executes the computer program, the functions of each module / unit in the embodiment of the human-code association analysis device are realized, for example Figure 7 The functions of the current person code data acquisition module 701, the target graph network structure determination module 702, the first face code pair determination module 703 and the second face code pair determination module 704 are not described here to avoid repetition.

[0145] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for analyzing the association between a person and a code in the above embodiment is implemented. For example, Figure 1 S101-S104 as shown, or Figures 2 to 6 Alternatively, when the computer program is executed by the processor, the functions of each module / unit in the embodiment of the above-mentioned human-code association analysis device are realized, for example Figure 7 The functions of the current person code data acquisition module 701, the target graph network structure determination module 702, the first face code pair determination module 703 and the second face code pair determination module 704 are not described here to avoid repetition. The computer-readable storage medium may be non-volatile or volatile.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0147] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0148] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for analyzing the association between a person and a code, characterized in that: include: Get the current person code data of the current time period; Determine the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period; Based on the target graph network structure, conditional entropy analysis is performed on the current person code data of the current time period and the historical person code data of the historical time period to determine M first face code pairs corresponding to the current time period, where M≥2; Perform correlation analysis on the M first face code pairs corresponding to the current time period to determine N second face code pairs corresponding to the current time period, where N≥1.

2. The method for analyzing the association between a person and a code according to claim 1, wherein: The determining of the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period includes: The current person code data of the current time period and the historical person code data of the historical time period are combined to determine the target person code data corresponding to the current time period; Based on the target person code data corresponding to the current time period, the target graph network structure is determined.

3. The method for analyzing the association between a person and a code according to claim 1, wherein: The method of performing conditional entropy analysis on the current person code data of the current time period and the historical person code data of the historical time period based on the target graph network structure to determine M first face code pairs corresponding to the current time period includes: Acquire at least one target connectivity graph in the target graph network structure; Performing conditional entropy analysis on each of the target connectivity graphs to determine a conditional entropy analysis result corresponding to each initial face code pair in each of the target connectivity graphs; Based on the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph, the M first face code pairs corresponding to the current time period are determined.

4. The method for analyzing the association between a person and a code according to claim 3, wherein: The conditional entropy analysis is performed on each target connectivity graph to determine the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph, including: Based on each of the target connectivity graphs, determining, in each initial face-code pair of each target connectivity graph, a first conditional probability corresponding to a face event, a second conditional probability corresponding to a code event, and a joint probability corresponding to the initial face-code pair; Based on the first conditional probability, the second conditional probability and the joint probability, a conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph is determined.

5. The method for analyzing the association between a person and a code according to claim 3, wherein: The method of determining the M first face code pairs corresponding to the current time period based on the conditional entropy analysis result corresponding to each initial face code pair in each target connectivity graph includes: The first M initial face code pairs with smaller conditional entropy analysis results in all the target connected graphs are determined as the M first face code pairs corresponding to the current time period.

6. The method for analyzing the association between a person and a code according to claim 1, wherein: The performing correlation analysis on the M first face code pairs corresponding to the current time period to determine the N second face code pairs corresponding to the current time period includes: Performing correlation analysis on the M first face code pairs to determine correlation analysis results corresponding to the M first face code pairs; Based on the association analysis results corresponding to the M first face code pairs, N second face code pairs are determined.

7. The method for analyzing the association between a person and a code according to claim 6, wherein: The performing correlation analysis on the M first face code pairs to determine the correlation analysis results corresponding to the M first face code pairs includes: Perform logarithmic processing on the number of valid points and the number of occurrences of the M first face code pairs to obtain the first correlation degrees corresponding to the M first face code pairs; Performing logarithmic processing on the number of occurrences and valid days of the M first face-code pairs, to obtain the second correlation degrees corresponding to the M first face-code pairs; According to the first association degrees corresponding to the M first face code pairs and the second association degrees corresponding to the M first face code pairs, the association degree analysis results corresponding to the M first face code pairs are obtained.

8. A person-code association analysis device, characterized in that: include: The current person code data acquisition module is used to obtain the current person code data of the current time period; A target graph network structure determination module determines the target graph network structure based on the current person code data of the current time period and the historical person code data of the historical time period; A first face code pair determination module, based on the target graph network structure, performs conditional entropy analysis on the current person code data of the current time period and the historical person code data of the historical time period to determine M first face code pairs corresponding to the current time period, where M≥2; The second face code pair determination module is used to perform correlation analysis on the M first face code pairs corresponding to the current time period to determine the N second face code pairs corresponding to the current time period, where N≥1.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the human-code association analysis method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for analyzing the association between a person and a code as described in any one of claims 1 to 7 is implemented.