A lost behavior judgment and alarm method and device based on data analysis

Abstract

The application relates to a lost behavior judgment and alarm method and device based on data analysis, which comprises the following steps: obtaining accompanying persons of target lost persons from original data, calculating intimacy data of the accompanying persons, constructing an intimacy database corresponding to each target lost person based on the intimacy data; obtaining real-time monitoring data, combining trajectory information in the original data to determine whether there is a lost behavior corresponding to the target lost person; when the lost behavior exists, combining the intimacy database to determine the lost level of the lost behavior, and performing an alarm operation corresponding to the lost level. By introducing the intimacy data of the accompanying persons related to the target lost person, the lost behavior level is determined based on the intimacy data, the alarm operation corresponding to the lost behavior level is performed, the accuracy of the lost behavior judgment is improved, and the possibility of the target lost person being lost is reduced.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method and apparatus for determining and alarming missing persons based on data analysis. Background Technology

[0002] For individuals who are prone to getting lost, such as children and the elderly, using a surveillance network composed of massive monitoring devices to determine their whereabouts has become a very mature technological means.

[0003] Currently, the mainstream method for determining missing persons mainly relies on algorithms to extract the human features of missing persons, then compare and search with existing image databases, and use the results with high similarity as target images for manual determination of missing behavior based on the target images.

[0004] The current process for determining missing persons relies solely on the screening of target images and manual judgment, which suffers from low efficiency and poor accuracy. Furthermore, there is no way to trigger an alarm after determining missing persons, which to some extent affects the possibility of finding them. Summary of the Invention

[0005] Therefore, it is necessary to provide a data analysis-based method and device for determining and alarming missing persons to address the aforementioned technical problems. By introducing the intimacy data of companions associated with the missing person, the method can assist in determining the level of missing behavior based on the intimacy data and perform alarm operations corresponding to the level of missing behavior. This can improve the accuracy of determining missing behavior and reduce the possibility of the missing person going missing.

[0006] Firstly, this application provides a data analysis-based method for determining and alerting missing persons behavior, the method comprising:

[0007] By filtering the raw data in the personnel files, the target missing persons were identified;

[0008] Obtain the companions of the target missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each target missing person based on the intimacy data;

[0009] Acquire real-time monitoring data and combine it with trajectory information in the original data to determine whether there is any missing behavior corresponding to the target missing person;

[0010] When the aforementioned missing behavior occurs, the missing level is determined by combining the intimacy database, and an alarm operation corresponding to the missing level is performed.

[0011] In some embodiments, the step of obtaining the companions of the target missing persons from the raw data, calculating the intimacy data of the companions, and constructing an intimacy database for each target missing person based on the intimacy data includes:

[0012] Identify individuals who appeared at the same time as the missing person as accompanying persons;

[0013] The accompanying data of the accompanying person and the target missing person appearing at the same time is extracted from the original data, and the intimacy data of the accompanying person is calculated based on the accompanying data;

[0014] A closeness database for each of the missing persons is constructed based on the closeness data of all the accompanying persons.

[0015] In some embodiments, the step of extracting accompanying data of the companion and the target missing person appearing simultaneously from the raw data, and calculating the intimacy data of the companion based on the accompanying data, includes:

[0016] Determine the feature vector of the accompanying person, and based on the feature vector, filter out the accompanying data corresponding to the accompanying person from the original data;

[0017] The intimacy data of the corresponding companion is calculated based on the preset intimacy weight value and the accompanying data.

[0018] In some embodiments, the step of acquiring real-time monitoring data and combining it with trajectory information in the raw data to determine whether there is missing behavior corresponding to the target missing person includes:

[0019] Based on the original data, construct a feature image corresponding to the target missing person;

[0020] Acquire real-time monitoring data, perform similarity calculation between the real-time monitoring data and the feature image, and obtain the target monitoring image in the real-time monitoring data in which the target missing person appears;

[0021] By comparing the shooting location information corresponding to the target monitoring image with the trajectory information in the original data, the missing parameters of the target missing person are obtained;

[0022] The missing person parameters are compared with a preset missing person threshold to determine whether there is a missing person behavior corresponding to the target missing person.

[0023] In some embodiments, constructing a feature image corresponding to the target missing person based on the raw data includes:

[0024] Feature extraction is performed on the original data to obtain the target feature vector corresponding to the target missing person;

[0025] Based on the target feature vector, a feature image corresponding to the target missing person is constructed.

[0026] In some embodiments, when the missing behavior occurs, determining the missing level of the missing behavior based on the intimacy database and performing an alarm operation corresponding to the missing level includes:

[0027] When the aforementioned missing behavior exists, obtain the location parameters of the location where the missing behavior occurred;

[0028] Identify the target companion appearing in the real-time monitoring data, and retrieve the corresponding intimacy data of the target companion from the intimacy database;

[0029] The degree of disappearance is determined based on the location parameters and the intimacy data of the person accompanying the target;

[0030] Based on the intimacy database, a contact sequence corresponding to the target missing person is constructed;

[0031] Select the contact corresponding to the missing person level from the contact sequence and perform an alarm operation.

[0032] In some embodiments, constructing a contact sequence corresponding to the target missing person based on the intimacy database includes:

[0033] Select accompanying persons who meet the contact threshold requirements from the intimacy database;

[0034] A contact sequence for the target missing person is constructed based on the companions of the sample, ranked from highest to lowest intimacy value.

[0035] Secondly, this application also provides a data analysis-based missing person behavior determination and alarm device, the device comprising:

[0036] The personnel identification module is used to filter the raw data in personnel files to identify the target missing persons;

[0037] The database construction module is used to obtain the companions of the target missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each target missing person based on the intimacy data.

[0038] The behavior determination module is used to acquire real-time monitoring data and combine it with the trajectory information in the original data to determine whether there is a missing behavior corresponding to the target missing person.

[0039] The alarm module is used to determine the level of the missing behavior by combining the intimacy database when the missing behavior exists, and to perform an alarm operation corresponding to the missing level.

[0040] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0041] By filtering the raw data in the personnel files, the target missing persons were identified;

[0042] Select the tag data of the target missing persons from the raw data, and determine the closeness database of each target missing person based on the tag data;

[0043] Based on the trajectory information in the raw data, the accompanying data of the target missing person is extracted, and the level of missing behavior of the target missing person is determined by combining it with the closeness database;

[0044] Based on the level of missing behavior and combined with the intimacy database, different levels of missing person alarm processing are carried out.

[0045] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0046] By filtering the raw data in the personnel files, the target missing persons were identified;

[0047] Select the tag data of the target missing persons from the raw data, and determine the closeness database of each target missing person based on the tag data;

[0048] Based on the trajectory information in the raw data, the accompanying data of the target missing person is extracted, and the level of missing behavior of the target missing person is determined by combining it with the closeness database;

[0049] Based on the level of missing behavior and combined with the intimacy database, different levels of missing person alarm processing are carried out.

[0050] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0051] By filtering the raw data in the personnel files, the target missing persons were identified;

[0052] Select the tag data of the target missing persons from the raw data, and determine the closeness database of each target missing person based on the tag data;

[0053] Based on the trajectory information in the raw data, the accompanying data of the target missing person is extracted, and the level of missing behavior of the target missing person is determined by combining it with the closeness database;

[0054] Based on the level of missing behavior and combined with the intimacy database, different levels of missing person alarm processing are carried out.

[0055] By introducing the concept and generation method based on intimacy data, and combining it with accompanying data to accurately determine missing behavior, the accuracy of missing behavior early warning can be improved compared with existing technologies. At the same time, by establishing alarm operations corresponding to the level of missing behavior, alarms can be sent to the corresponding level of contacts as soon as missing behavior is determined, thereby increasing the possibility of finding missing persons. Attached Figure Description

[0056] Figure 1 This is an application environment diagram of a data analysis-based missing behavior determination and alarm method in one embodiment;

[0057] Figure 2 This is a flowchart illustrating a data analysis-based missing behavior determination and alarm method in one embodiment.

[0058] Figure 3 This is a structural block diagram of a data analysis-based missing behavior determination and alarm device in one embodiment.

[0059] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] The data analysis-based missing behavior determination and alarm method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located on the cloud or other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0062] The missing person behavior determination and alarm method proposed in this application relies on personnel files containing a large amount of data. These personnel files are databases constructed by extracting features and clustering data from massive amounts of images and videos acquired through the current urban surveillance network. Within the personnel files, images and videos are categorized by the person who filmed them, the filming time, and the filming location, combined with known personal information to generate raw data. The personnel files are built based on multi-dimensional data, commonly including visual biometric information such as faces and bodies, as well as license plate information, non-motorized vehicle information, collection information, and QR code information. To facilitate data categorization within the personnel files, each person who filmed the video is assigned a unique feature value.

[0063] In one embodiment, such as Figure 2 As shown, a method for determining and alarming missing persons based on data analysis is provided. This embodiment uses the application of this method to a terminal as an example for illustration. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be implemented through the interaction between the terminal and the server.

[0064] Specifically, the missing person behavior determination and alarm method proposed in this embodiment includes the following steps:

[0065] Step S20: Filter the original data in the personnel file to obtain the target missing persons.

[0066] This section filters individuals from the original data, identifying those without independent behavioral capacity based on their age and other information. It then combines this with location and time information from captured images and videos to determine the temporal and spatial characteristics of shopping malls, transportation hubs, and medical institutions, which are more likely to lead to people getting lost compared to residential areas. This process identifies target missing persons who are more likely to go missing.

[0067] Step S40: Obtain the companions of the corresponding missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each missing person based on the intimacy data.

[0068] The term "closeness" here is defined as the level of confidence in the guardian of the missing person. For example, if the missing person is an elderly person, their guardian might be their children or a caregiver responsible for their daily care. Unlike existing technologies that often select guardians based on frequency of daily interactions, this method, which limits guardians based on relationships, effectively avoids misjudgments of high-frequency but low-relevance individuals such as neighbors or colleagues.

[0069] The calculation of intimacy data involves information including frequent locations, residences, daily traffic patterns, and daily outing and return times. Based on the classification of this information, different weights are assigned to specific data points, allowing for the calculation of intimacy data for companions appearing alongside the target missing person in the original data. By summarizing all companions corresponding to a single target missing person, an intimacy database for that person can be obtained.

[0070] Step S60: Obtain real-time monitoring data and combine it with the trajectory information in the original data to determine whether there is any missing person behavior.

[0071] The trajectory information here includes data such as the time, location, and duration of the accompanying person's appearance. This data can be obtained from images and videos captured by monitoring equipment in the personnel files. By comparing the trajectory information in the real-time monitoring data with that in the raw data, it is determined whether the real-time monitoring data shows any signs of the target missing person getting lost, being abducted, or engaging in other missing behaviors. Based on the severity of the missing behavior during the comparison process, it is classified into different levels.

[0072] Step S80: When a missing person behavior occurs, the missing person level is determined by combining the intimacy database, and an alarm operation corresponding to the missing person level is performed.

[0073] The missing person alerts here are divided into two levels. The first is to sort them by severity according to the level of missing behavior. The second is to build a contact sequence based on the intimacy data mentioned above. This allows the corresponding contact sequence to be selected for the corresponding level of alert operation based on the severity.

[0074] The data analysis-based missing person detection and alerting method constructed based on the above steps performs multi-dimensional joint and accurate determination of missing person behavior based on factors such as intimacy data and companionship data. Compared with existing technologies that rely solely on single-dimensional determination methods based on trajectory or facial features, this method has higher accuracy in determining missing person behavior. Furthermore, issuing alerts based on the level of missing person behavior allows for more accurate mobilization of social resources, avoiding waste of these resources.

[0075] In one embodiment, the accompanying persons of the corresponding target missing persons are obtained from the raw data, the intimacy data of the accompanying persons is calculated, and an intimacy database for each target missing person is constructed based on the intimacy data, i.e., step S40, which includes:

[0076] Step S42: Obtain people who appeared at the same time as the target missing person as accompanying persons.

[0077] Step S44: Extract the accompanying data of the accompanying person and the target missing person appearing at the same time from the original data, and calculate the intimacy data of the accompanying person based on the accompanying data.

[0078] Step S46: Construct a closeness database for each missing person based on the closeness data of all accompanying persons.

[0079] In practice, based on the aforementioned analysis of step S40, it is known that the intimacy data is calculated based on the tag data to obtain the confidence level of the guardian of the corresponding missing person. The process of calculating the intimacy data relies on preset weight values ​​for different guardians or different scenarios in which the guardians are located.

[0080] The specific process for calculating intimacy data, namely step S44, includes:

[0081] Step S442: Determine the feature vector of the accompanying person, and filter the accompanying data of the corresponding accompanying person from the original data based on the feature vector;

[0082] Step S444: Calculate the intimacy data of the corresponding companion based on the preset intimacy weight value and the accompanying data.

[0083] To obtain specific tag data, it is necessary to filter the raw data in the personnel file based on the preset tag categories. For example, if the raw data contains pictures of accompanying persons, the specific data of the accompanying persons should be found, and the tag data should be composed of the specific content corresponding to the tag categories such as the target missing person's frequented places, residence, daily traffic trajectory, daily outing and return time.

[0084] After obtaining the tag data, the initial intimacy data of each accompanying person who has appeared with the current missing person can be calculated based on Formula 1 using the preset weight values ​​of the corresponding tag data:

[0085] Initial intimacy data = (Tag data 1 × Preset weight value 1 + Tag data 2 × Preset weight value 2 + Tag data 3 × Preset weight value 3 + ... + Tag data N × Preset weight value N) Formula 1

[0086] After obtaining the initial intimacy data of the first accompanying person, the calculation process shown in Formula 1 is performed on all accompanying persons who appeared at the same time as the current missing person to obtain the initial intimacy data of all accompanying persons. Then, target intimacy data that meets the preset intimacy threshold requirements is selected from the initial intimacy data. The target intimacy data and the corresponding accompanying persons are summarized to obtain the intimacy database of each target missing person. At this time, the intimacy database contains the accompanying persons and the intimacy data corresponding to each accompanying person.

[0087] It's important to note that the intimacy data is also regularly updated and maintained. A threshold is set for intimacy levels; those exceeding the threshold are considered guardians. This threshold can be set based on statistical data or preset manually. The statistical data-based approach involves collecting data on the companions and intimacy levels of a large number of children and the elderly, merging and sorting them together. The resulting data distribution will exhibit a bimodal distribution, with lower intimacy levels representing people who chat / play daily, or those living in the same unit / community, while higher intimacy levels represent the true guardian group. When filtering each intimacy data point based on the preset threshold, the following operations are also included:

[0088] When the initial intimacy data shows a bimodal distribution, the preset intimacy threshold is adjusted.

[0089] In practice, the bimodal distribution here refers to a distribution where a large number of occurrences are concentrated around two different scores, resulting in two peaks in the frequency distribution curve. The presence of a bimodal distribution indicates that the current intimacy data has two relatively separate value intervals. Without addressing this, subsequent intimacy data will fail to reflect the true companionship characteristics of the individuals involved. Therefore, to facilitate subsequent operations, the following processing is required:

[0090] Delete data with an affinity level lower than the trough between the two peaks. Set a preset percentage threshold. When the proportion of records with an affinity level higher than a certain threshold exceeds the preset percentage threshold, the affinity threshold will be regarded as the updated preset affinity setting threshold.

[0091] In one embodiment, real-time monitoring data is acquired, and the trajectory information in the original data is combined to determine whether there is any missing behavior corresponding to the target missing person, i.e., step S60, includes:

[0092] Step S62: Construct a feature image of the corresponding missing person based on the original data;

[0093] Step S64: Obtain real-time monitoring data, perform similarity calculation between the real-time monitoring data and the feature image, and obtain the target monitoring image in which the target missing person appears in the real-time monitoring data.

[0094] Step S66: Compare the shooting location information corresponding to the target monitoring image with the trajectory information in the original data to obtain the missing parameters of the corresponding missing person.

[0095] Step S68: Compare the missing parameters with the preset missing threshold to determine whether there is a missing person behavior corresponding to the target missing person.

[0096] In practice, the primary basis for determining the disappearance of a target missing person is the trajectory information of accompanying persons contained in the raw data. This trajectory information includes GPS information from monitoring equipment and facial or other biometric information of accompanying persons other than the target missing person in the images.

[0097] The main process of determining the missing person's behavior consists of three steps. First, the characteristic image of the missing person is determined. Second, the target monitoring image of the missing person is determined from the real-time monitoring data based on the characteristic image. Finally, the missing behavior is determined based on the information in the target monitoring image and the trajectory information in the original data.

[0098] The operation of determining the characteristic image of the target missing person, namely step S62, includes:

[0099] Step S622: Extract features from the original data to obtain the target feature vector of the corresponding missing person;

[0100] Step S624: Construct a feature image of the corresponding missing person based on the target feature vector.

[0101] It should be noted that steps S622-S624 are performed here because the image data of the corresponding missing persons stored in the personnel files is too large. In order to reduce the amount of data to be processed in the subsequent steps of determining the missing behavior, it is necessary to perform operations such as feature extraction on the image data in the original data to simplify the data volume.

[0102] The simplified data implementation method here is as follows: feature extraction is performed from the original data to obtain the target feature vector of the corresponding missing person, and image reconstruction is performed based on the target feature vector to obtain the feature image that serves as the simplified benchmark for judging the missing behavior of the corresponding missing person.

[0103] The features extracted here can typically include the facial features, clothing features, walking posture features, and surrounding building features of the missing person. The extracted features are stored in vector form. The reconstructed feature image is composed of the target feature vectors that highlight the characteristics of the missing person. Compared with the massive image data in the original data, the reconstructed feature image can retain the characteristics of the missing person as much as possible with a very small number of images, thereby significantly reducing the amount of data to be processed in subsequent missing behavior determination, and also improving the processing efficiency of missing behavior determination as much as possible.

[0104] After executing step S62, step S64 performs a similarity calculation to filter target surveillance images of the missing person from the real-time monitoring data. Since the location and shooting range parameters of each monitoring device are known, information related to the missing person's disappearance can be directly determined based on the target surveillance images. By comparing this information with the trajectory information of the missing person in the original data, the missing person's disappearance parameters in the target surveillance images can be obtained. Comparing these parameters with a preset disappearance threshold determines whether the missing person has deviated from their usual location.

[0105] In one embodiment, when the missing behavior occurs, the missing level of the missing behavior is determined by combining the intimacy database, and an alarm operation corresponding to the missing level is performed, i.e., step S80, including:

[0106] Step S81: When the missing behavior exists, obtain the location parameters of the location where the missing behavior occurred;

[0107] Step S83: Identify the target companion in the real-time monitoring data and obtain the corresponding companion's intimacy data from the intimacy database;

[0108] Step S85: Determine the missing level of the missing behavior based on location parameters and the closeness data of the person accompanying the target;

[0109] Step S87: Construct a contact sequence for the corresponding missing person based on the intimacy database;

[0110] Step S89: Select the contact corresponding to the missing person level from the contact sequence and perform an alarm operation.

[0111] In practice, this step mainly includes two parts: determining the level of missing persons and performing graded alarm operations based on the contact sequence.

[0112] The determination of the level of missing person behavior includes steps S81-S85. The main idea is to determine whether there is a target accompanying person in the real-time monitoring data of the missing person. If so, the closeness of the target accompanying person is determined based on the closeness data, and the missing person level is determined based on the obtained closeness data. If there is no target accompanying person, the missing person behavior is determined based on the missing person's missing parameters.

[0113] For example:

[0114] (1) No accompanying persons

[0115] The system counts the number of consecutive appearances of a missing person without any accompaniment and checks whether the missing person's current location and trajectory match historical information such as their usual haunts, daily travel routes, and outing and return times. For cases that do not conform to historical information, a travel risk range is preset for risk control; if the number of consecutive unaccompanied appearances exceeds this risk range, it is considered a missing person event.

[0116] For example, if the missing person is an elderly person, such as someone who is out alone at night during their usual rest time at home, an alert should be issued immediately; however, if the person is in a medical institution they frequent, their absence may simply be due to the absence of their guardian, in which case the risk is lower, and a delayed alert should be issued while continuing to monitor them.

[0117] (2) Accompanying persons

[0118] Obtain the characteristic values ​​of the accompanying person to determine the intimacy level of the accompanying person.

[0119] 1) If the intimacy level is lower than the intimacy threshold, obtain the current location, trajectory, etc. to see if they match the person's usual places of activity, daily traffic routes, daily outings and return times, etc. Determine the historical information with the travel risk range. If it exceeds the travel risk range, it is considered a suspected abduction incident and an alarm is issued; if it is within the travel risk range, follow the risk event prompts.

[0120] 2) If the intimacy level is higher than the intimacy threshold, it is necessary to further obtain the current location, trajectory, etc. to see if they match the person's usual places of activity, daily traffic routes, daily outing and return times, etc. The historical information is then compared with the travel risk range. If it exceeds the travel risk range, it is considered a risk event; if it does not exceed the travel risk range, it is considered a safe situation.

[0121] For the aforementioned missing persons incidents, suspected abduction incidents, and risk incidents, different levels of handling are required, typically in three tiers: the first choice is to contact their guardians, the second choice is to contact the staff of their community, and the last choice is the local public security agency.

[0122] Step S87 involves constructing a contact sequence for the target missing person based on the closeness database, including:

[0123] Step S872: Select sample companions who meet the contact threshold requirements from the intimacy database;

[0124] Step S874: Construct a contact sequence for the target missing person based on the closeness value of the accompanying persons in the sample, from high to low.

[0125] For the highest-level accompanying persons, those with a closeness exceeding a threshold are selected and sorted from most recent accompanying time to the oldest, forming a sequence of first, second, and Kth contacts. For community personnel, the grassroots community contact person for the ward is retrieved from the database based on the ward's place of residence. Public security agencies handle this similarly.

[0126] After classifying companions according to their level of intimacy, corresponding tiered alarm processing can be implemented. Different alarm notification methods will be used for different events.

[0127] (1) Suspected abduction incident

[0128] The highest level of danger requires immediately attempting to contact each contact in sequence via instant messaging methods such as phone calls. If unsuccessful, attempt to contact the next contact in the sequence, or the community, police, etc. At least two people must be contacted; otherwise, contacting the community / police will be forcibly triggered. Simultaneously, send images and other information about any accompanying persons triggering the suspected abduction incident, and send the current location information of the person under guardianship in real time. Contacts can be selected on the platform, choosing the option that indicates no actual risk, but at least two contacts must select this option.

[0129] If all options are selected as having no actual risk, then the intimacy level of this companion will be directly increased to above the set threshold, and any additional changes to the intimacy level will be considered as those of a trustworthy person.

[0130] (2) Missing incidents

[0131] The risk level is high. Immediately attempt to notify the contacts in the sequence sequentially via instant messaging methods such as VoIP. If unsuccessful, try contacting the next contact in the sequence, or the community, police, etc. Contacting just one person is sufficient. Simultaneously, send the ward's current location information in real time. Contacts can choose to ignore this risk through the platform.

[0132] (3) Risk events

[0133] At the higher risk level, all contacts will receive SMS notifications informing them of their current location and the accompanying person's image. Any contact can choose to ignore this risk or add the person to real-time surveillance for continuous location updates. If no action is taken within the set time, the community / police will be contacted. If the risk is ignored, the accompanying person's intimacy level will be automatically raised to above the set threshold, classifying them as a trustworthy individual.

[0134] The above-mentioned real-time transmission of the current location information of the ward can be implemented by referring to the method in Patent 1 / 2. However, in this design, the centroid of the most recent face, body and other data can be added to the control database directly based on the personnel file. The centroid has a more comprehensive expressive ability than specific image features, and at the same time ensures that the clothing and style of the recent data are similar, thereby improving the hit rate.

[0135] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0136] Based on the same inventive concept, this application also provides a data analysis-based missing behavior determination and alarm device for implementing the data analysis-based missing behavior determination and alarm method described above. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more data analysis-based missing behavior determination and alarm device embodiments provided below can be found in the limitations of the data analysis-based missing behavior determination and alarm method described above, and will not be repeated here.

[0137] In one embodiment, such as Figure 3 As shown, a data analysis-based missing person behavior determination and alarm device 90 is provided, comprising:

[0138] The personnel identification module 92 is used to filter the raw data in the personnel files to obtain the target missing persons;

[0139] The intimacy determination module 94 is used to select the tag data of the corresponding target missing persons from the raw data, and determine the intimacy database for each target missing person based on the tag data;

[0140] The missing person behavior level determination module 96 is used to extract the accompanying data of the target missing person based on the trajectory information in the original data, and combine it with the closeness database to determine the missing person behavior level.

[0141] Alarm module 98 is used to process different levels of missing person alarms based on the missing behavior level and intimacy database.

[0142] In practice, the missing person detection and alarm device based on the aforementioned modules performs multi-dimensional and precise detection of missing person behavior based on factors such as intimacy data and companionship data. Compared to existing technologies that rely solely on single-dimensional detection methods based on trajectory or facial features, it has higher accuracy in detecting missing person behavior. Furthermore, by issuing alarms according to the severity of the missing person behavior, it can more accurately mobilize social resources and avoid wasting them.

[0143] The modules in the aforementioned data analysis-based missing person behavior determination and alarm device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0144] In one embodiment, a computer device, which may be a server, is provided, and its internal structure can be as shown in Figure Y. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores relevant data related to a data analysis-based missing behavior determination and alarm method. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a data analysis-based missing behavior determination and alarm method.

[0145] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0146] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0147] Step 20: Filter the raw data in the personnel files to obtain the target missing persons;

[0148] Step 40: Obtain the companions of the target missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each target missing person based on the intimacy data;

[0149] Step 60: Obtain real-time monitoring data and combine it with the trajectory information in the original data to determine whether there is any missing behavior corresponding to the target missing person;

[0150] Step 80: When the missing behavior exists, determine the missing level of the missing behavior by combining the intimacy database, and perform an alarm operation corresponding to the missing level.

[0151] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0152] Step 20: Filter the raw data in the personnel files to obtain the target missing persons;

[0153] Step 40: Obtain the companions of the target missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each target missing person based on the intimacy data;

[0154] Step 60: Obtain real-time monitoring data and combine it with the trajectory information in the original data to determine whether there is any missing behavior corresponding to the target missing person;

[0155] Step 80: When the missing behavior exists, determine the missing level of the missing behavior by combining the intimacy database, and perform an alarm operation corresponding to the missing level.

[0156] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0157] Step 20: Filter the raw data in the personnel files to obtain the target missing persons;

[0158] Step 40: Obtain the companions of the target missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each target missing person based on the intimacy data;

[0159] Step 60: Obtain real-time monitoring data and combine it with the trajectory information in the original data to determine whether there is any missing behavior corresponding to the target missing person;

[0160] Step 80: When the missing behavior exists, determine the missing level of the missing behavior by combining the intimacy database, and perform an alarm operation corresponding to the missing level.

[0161] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0162] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0163] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0164] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining and alerting missing persons based on data analysis, characterized in that, The method for determining and alarming missing persons includes: By filtering the raw data in the personnel files, the target missing persons were identified; Obtain the companions of the target missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each target missing person based on the intimacy data; Based on the original data, construct a feature image corresponding to the target missing person; Acquire real-time monitoring data, perform similarity calculation between the real-time monitoring data and the feature image, and obtain the target monitoring image in the real-time monitoring data in which the target missing person appears; By comparing the shooting location information corresponding to the target monitoring image with the trajectory information in the original data, the missing parameters of the target missing person are obtained; The missing parameters are compared with a preset missing threshold to determine whether there is any missing behavior corresponding to the target missing person; When the aforementioned missing behavior exists, obtain the location parameters of the location where the missing behavior occurred; Identify the target companion appearing in the real-time monitoring data, and retrieve the corresponding intimacy data of the target companion from the intimacy database; The degree of disappearance is determined based on the location parameters and the intimacy data of the person accompanying the target; Based on the intimacy database, a contact sequence corresponding to the target missing person is constructed; Select the contact corresponding to the missing person level from the contact sequence and perform an alarm operation.

2. The method for determining and alarming missing persons based on data analysis according to claim 1, characterized in that, The step of obtaining the companions of the target missing persons from the original data, calculating the intimacy data of the companions, and constructing an intimacy database for each target missing person based on the intimacy data includes: Identify individuals who appeared at the same time as the missing person as accompanying persons; The accompanying data of the accompanying person and the target missing person appearing at the same time is extracted from the original data, and the intimacy data of the accompanying person is calculated based on the accompanying data; A closeness database for each of the missing persons is constructed based on the closeness data of all the accompanying persons.

3. The method for determining and alarming missing persons based on data analysis according to claim 2, characterized in that, The step of extracting companion data from the original data, showing the simultaneous presence of the companion and the missing person, and calculating the intimacy data of the companion based on the companion data, includes: Determine the feature vector of the accompanying person, and based on the feature vector, filter out the accompanying data corresponding to the accompanying person from the original data; The intimacy data of the corresponding companion is calculated based on the preset intimacy weight value and the accompanying data.

4. The method for determining and alarming missing persons based on data analysis according to claim 1, characterized in that, The construction of a feature image corresponding to the target missing person based on the original data includes: Feature extraction is performed on the original data to obtain the target feature vector corresponding to the target missing person; Based on the target feature vector, a feature image corresponding to the target missing person is constructed.

5. The method for determining and alarming missing persons based on data analysis according to claim 1, characterized in that, The step of constructing a contact sequence corresponding to the target missing person based on the intimacy database includes: Select accompanying persons who meet the contact threshold requirements from the intimacy database; The accompanying persons of the sample are arranged in descending order of their intimacy scores to construct a contact sequence corresponding to the target missing person.

6. A data analysis-based missing person behavior determination and alarm device, characterized in that, The missing behavior determination and alarm device includes: The personnel identification module is used to filter the raw data in personnel files to identify the target missing persons; The database construction module is used to obtain the companions of the target missing persons from the original data, calculate the intimacy data of the companions, and construct an intimacy database for each target missing person based on the intimacy data. The behavior determination module is used to construct a feature image corresponding to the target missing person based on the original data; Acquire real-time monitoring data, perform similarity calculation between the real-time monitoring data and the feature image, and obtain the target monitoring image in the real-time monitoring data in which the target missing person appears; By comparing the shooting location information corresponding to the target monitoring image with the trajectory information in the original data, the missing parameters of the target missing person are obtained; The missing parameters are compared with a preset missing threshold to determine whether there is any missing behavior corresponding to the target missing person; The alarm module is used to obtain the location parameters of the location where the missing behavior occurred when the missing behavior exists; Identify the target companion appearing in the real-time monitoring data, and retrieve the corresponding intimacy data of the target companion from the intimacy database; The degree of disappearance is determined based on the location parameters and the intimacy data of the person accompanying the target; Based on the intimacy database, a contact sequence corresponding to the target missing person is constructed; Select the contact corresponding to the missing person level from the contact sequence and perform an alarm operation.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the data analysis-based missing behavior determination and alarm method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the data analysis-based missing behavior determination and alarm method according to any one of claims 1 to 5.

Images