A risk management method and system

Abstract

The present invention provides a risk handling method and system, the method comprising: obtaining an environmental video captured by a target camera in a hospital; comparing the facial image identified by the environmental video with a preset face image in a blacklist database, and analyzing medical behavior based on the facial image; performing risk scoring based on the comparison results and analysis results, and generating a prompt instruction for a risk user based on the risk scoring result; sending the prompt instruction to a target terminal in the hospital to initiate a risk prompt. The present invention accurately identifies risk users to take corresponding measures, maintains the normal medical order of the hospital, improves hospital safety, and protects the right of patients to receive medical treatment in an orderly manner.

Description

Technical Field

[0001] The present invention relates to the technical field of medical registration, and in particular to a risk management method and system. Background Art

[0002] Due to the extremely unbalanced medical demand, some large hospitals and expert appointments are in short supply, creating conditions for the active existence of scalpers.

[0003] If hospitals want to eliminate scalpers, they need to deploy a complete registration system, open online real-name authentication registration, and use multiple channels for appointment registration. However, the deployment cost of a complete registration system is high and the construction cycle is long. For hospitals that do not have online appointment registration, it is difficult to prevent hospital "scalpers" from registering at the window.

[0004] At present, the existing technology cannot accurately identify whether it is the person who registered the appointment, which allows scalpers to take advantage of the situation and causes technical problems that harm the public interest. Summary of the invention

[0005] The purpose of the present invention is to provide a risk management method and system, which can accurately identify risky users so as to take corresponding measures, maintain the normal medical order in the hospital, improve hospital safety, and protect the right of patients to receive medical treatment in an orderly manner.

[0006] The technical solution provided by the present invention is as follows:

[0007] The present invention provides a risk management method, comprising the steps of:

[0008] Obtain the environmental video captured by the target camera within the hospital premises;

[0009] Comparing the facial image identified by the environmental video with the preset facial images in the blacklist database, and performing medical behavior analysis based on the facial image;

[0010] Perform risk scoring based on the comparison and analysis results, and generate prompt instructions for risky users based on the risk scoring results;

[0011] The prompt instruction is sent to a target terminal within the hospital site to initiate a risk prompt.

[0012] Furthermore, the step of obtaining the environment video captured by the target camera in the hospital premises includes the following steps:

[0013] Setting target cameras at a preset area and a site service robot within the hospital site respectively;

[0014] The preset areas include any one or more of a passage area, a registration area, a pharmacy area, an outpatient entrance and exit area, a consulting service area, and a consulting room area.

[0015] Furthermore, the step of comparing the facial image identified by the environmental video with the preset facial image in the blacklist database and analyzing the medical behavior based on the facial image includes the following steps:

[0016] Detecting and identifying facial images appearing in the video image using a face detection algorithm;

[0017] Comparing the facial image with a preset facial image in a blacklist database to obtain the comparison result;

[0018] The number of visits to the hospital and the number of medical treatment behaviors of the corresponding user in the hospital are counted according to the facial image.

[0019] Furthermore, the step of performing risk scoring according to the comparison result and the analysis result, and generating a prompt instruction for the risky user according to the risk scoring result comprises the following steps:

[0020] According to a preset score evaluation strategy, risk scoring is performed on the comparison results and analysis results respectively;

[0021] The risk scoring results are summed up to obtain a total score value, and a prompt instruction of the corresponding facial image is obtained according to the total score value.

[0022] Furthermore, the risk scoring of the comparison result and the analysis result respectively according to the preset score evaluation strategy includes the steps of:

[0023] Determining whether further analysis is needed based on the risk level of the facial image and its history;

[0024] If further analysis is required, a risk score is assigned to the facial image based on the number of medical visits;

[0025] If no further analysis is required, a risk score is assigned to the facial image based on the comparison results and the number of visits to the hospital.

[0026] Furthermore, the risk scoring results are summed up to obtain a total score, and a prompt instruction comparison step of the corresponding facial image is obtained according to the total score:

[0027] If the risk level is the first level when the mapping relationship table is queried according to the total score value, a real-name system prompt instruction is generated;

[0028] If the risk level is the second level when the mapping relationship table is queried according to the total score value, a real-name prompt instruction is generated, and the blacklist database is updated according to the facial image;

[0029] If the risk level is the third level as obtained by querying the mapping relationship table according to the total score value, an alarm prompt instruction is generated.

[0030] The present invention also provides a risk management system, comprising: setting target cameras at a preset area in the hospital site and at a site service robot respectively;

[0031] An acquisition module is used to acquire the environment video captured by the target camera in the hospital site;

[0032] An analysis module, used to compare the facial image identified by the environmental video with the preset facial images in the blacklist database, and perform medical behavior analysis based on the facial image;

[0033] A processing module, used to perform risk scoring according to the comparison results and the analysis results, and generate a prompt instruction for the risky user according to the risk scoring result;

[0034] A communication module, used for sending the prompt instruction to a target terminal in the hospital to initiate a risk prompt;

[0035] The preset areas include any one or more of a passage area, a registration area, a pharmacy area, an outpatient entrance and exit area, a consulting service area, and a consulting room area.

[0036] Furthermore, the analysis module includes:

[0037] A recognition unit, used to detect and recognize a facial image appearing in the video image by using a face detection algorithm;

[0038] A comparison unit, used for comparing the facial image with a preset facial image in a blacklist database to obtain the comparison result;

[0039] A statistical unit is used to count the number of visits to the hospital and the number of medical treatment behaviors of the corresponding user in the hospital according to the facial image.

[0040] Furthermore, the processing module includes:

[0041] A scoring unit, used to perform risk scoring on the comparison result and the analysis result respectively according to a preset score evaluation strategy;

[0042] The processing unit is used to sum up the risk scoring results to obtain a total score value, and obtain a prompt instruction of the corresponding facial image according to the total score value.

[0043] Furthermore, the scoring unit includes:

[0044] A judgment subunit, used to judge whether further analysis is needed according to the risk level of the facial image and its history;

[0045] An evaluation subunit is used to, if further analysis is required, perform a risk score on the facial image based on the number of medical visits; if no further analysis is required, perform a risk score on the facial image based on the comparison result and the number of visits to the hospital;

[0046] The processing unit comprises:

[0047] A processing subunit is used to generate a real-name prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the first level; generate a real-name prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the second level, and update the blacklist database according to the facial image; and generate an alarm prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the third level.

[0048] Through the risk handling method and system provided by the present invention, risk users can be accurately identified to take corresponding measures, maintain the normal medical order in the hospital, improve hospital safety, and protect the right of patients to receive medical treatment in an orderly manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The following will explain the preferred implementation mode in a clear and understandable manner with reference to the accompanying drawings, and further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of a risk management method and system.

[0050] Figure 1 It is a flow chart of an embodiment of a method for identifying scalpers of the present invention;

[0051] Figure 2 is a flow chart of another embodiment of a method for identifying scalpers of the present invention;

[0052] Figure 3 It is a schematic diagram of the arrangement and installation of a target camera of a scalper identification method of the present invention;

[0053] Figure 4 It is a flow chart of an example of a method for identifying yellow cattle of the present invention. DETAILED DESCRIPTION

[0054] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0055] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections.

[0056] In order to simplify the drawings, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0057] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0058] In addition, in the description of the present application, the terms “first”, “second”, etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0060] One embodiment of the present invention, as Figure 1 As shown, a method for identifying scalpers includes:

[0061] S100 obtains the environmental video captured by the target camera within the hospital premises;

[0062] Specifically, the target camera refers to a camera in the hospital that is used by the hospital and patients. The target camera collects the environment video within its field of view in real time. Then, the server in the hospital receives the environment video sent by each target camera.

[0063] After the server obtains the environmental video from the target camera in the hospital venue, the environmental video includes but is not limited to people, beds, tables, and walls. The server preprocesses the environmental video, and the preprocessing includes video denoising, illumination normalization, posture calibration, and grayscale normalization, which are not limited here. The server preprocesses the environmental video to facilitate the extraction of more discernible facial images. The server extracts facial images based on the environmental video, including: obtaining each frame of video image in the environmental video, detecting whether there is a face area in each frame of video image, and extracting all the video images containing face areas as facial images.

[0064] S200 compares the facial image identified by the environmental video with the preset facial images in the blacklist database, and performs medical behavior analysis based on the facial image;

[0065] Specifically, the server stores and updates a blacklist database in real time, which stores preset facial images of risky users such as "scalpers", "medical troublemakers", "criminal suspects", and "criminals" who may affect the normal diagnosis and treatment order of the hospital.

[0066] After the server obtains the facial image in the above manner, it compares the facial image recognized in the ambient video with all the preset face images in the blacklist database that is stored and updated in real time for similarity to obtain a comparison result. The server also performs targeted medical behavior analysis on the user corresponding to the facial image based on the facial image recognized by the ambient video to obtain an analysis result.

[0067] S300 performs risk scoring according to the comparison result and the analysis result, and generates a prompt instruction for the risky user according to the risk scoring result;

[0068] S400 sends the prompt instruction to the target terminal in the hospital to initiate a risk prompt.

[0069] Specifically, the server performs risk scoring on the user corresponding to the identified facial image according to the preset rules based on the comparison results and analysis results obtained in the above manner to obtain the risk scoring result. Then, the server obtains the corresponding prompt instruction based on the risk scoring result query. Since each facial image corresponds to its own risk scoring result, the prompt instruction queried by the server corresponds to the user of the facial image to which the risk scoring result belongs, that is, the user corresponding to the facial image corresponds to their own risk scoring result and its prompt instruction. The server will query the target terminal in the hospital venue for the matched prompt instruction, so that the target terminal can take corresponding measures for risk prompts for users of different facial images according to the prompt instruction. Among them, the target terminal includes but is not limited to the computer of the registration staff, the self-service registration machine, the desktop computer in the clinic, the computer at the outpatient service desk, the computer or speakers at the outpatient entrance and security room, and the speakers in the passage area (such as elevators, corridors, etc.).

[0070] The present invention utilizes a camera to detect facial images of hospital visitors, analyzes the probability of the hospital visitors being suspected risk users such as "scalpers", "medical trouble makers", "criminal suspects", "criminals", etc., initiates risk warnings for users with a high probability of being risk users, and issues background warnings. By utilizing existing surveillance cameras in the hospital or deploying additional surveillance camera equipment, the present invention can not only accurately identify "scalpers" in order to promptly stop behaviors that disrupt the medical resource allocation rules, but also exclude other risk users and maintain the normal medical order in the hospital.

[0071] One embodiment of the present invention, as Figure 2 As shown, a method for identifying scalpers includes:

[0072] S010 respectively set target cameras in the preset area and the site service robot within the hospital site;

[0073] Specifically, the preset area includes any one or more of a passage area, a registration area, a pharmacy area, an outpatient entrance and exit area, a consulting service area, and a consulting room area. Figure 3 As shown, one or more video shooting devices (ie, cameras or still cameras) can be set as target cameras in each preset area.

[0074] S100 obtains the environmental video captured by the target camera within the hospital premises;

[0075] S210 detects and identifies a facial image appearing in the video image by using a face detection algorithm;

[0076] S220 compares the facial image with a preset facial image in a blacklist database to obtain the comparison result;

[0077] Specifically, this embodiment is an optimized embodiment of the above embodiment. The same parts of this embodiment as the above embodiment refer to the above embodiment, and will not be repeated here. The server uses any one of the face detection algorithms such as CNN, OpenCV, Seetaface, etc. to perform face detection.

[0078] Since there are some preset face images in the blacklist database that have been confirmed as risky users or there is a high possibility that they are risky users. Preferably, risky users can be classified into "scalpers", "medical trouble users", "criminal suspects", "criminals", etc. in the blacklist database, that is, the blacklist database includes risky user image sets such as "scalper face image set", "medical trouble face image set", "suspect face image set", and "criminal face image set". Therefore, when the acquired facial image is compared with the preset face images in the blacklist database, it is preferred to compare the facial image with the preset face images corresponding to different risky user image sets in the blacklist database in turn. If the similarity between the facial image and the preset face images in the current risky user image set reaches a preset threshold, then the comparison result of the server is to determine that the user corresponding to the facial image belongs to a risky user and can determine its risky user type. If the similarity between the facial image and the preset face images in all risky user image sets does not reach the preset threshold, then the comparison result of the server is to determine that the user corresponding to the facial image is not a risky user type. Exemplarily, when there is a preset face image in the “scalper face image set” and the similarity between the face images reaches a preset threshold, it can be determined that the user corresponding to the face image is a hospital scalper.

[0079] It is understandable that for certain risky users, if they are not found to have any wrong behavior that would make them risky users within the predetermined time period, indicating that the person is a normal person, the preset face image of the risky user can be deleted from the blacklist database, and the blacklist database can be updated regularly to reduce memory. The predetermined time period is pre-set by the hospital manager or hospital owner, for example, the predetermined time period is 5 years or 10 years.

[0080] S230 counting the number of visits and medical treatment behaviors of the corresponding user in the hospital according to the facial image;

[0081] Specifically, after the server extracts the facial images of the people coming to the hospital through the above-mentioned face detection algorithm, it can count the number of visits and medical treatment behaviors of the user corresponding to the facial image in the hospital within a preset period (for example, one day, one week, or one month, etc.) and obtain analysis results.

[0082] Among them, the number of medical treatment behaviors includes the number of registrations (i.e. the number of times one only registers at the window registration counter or self-service registration terminal within the hospital but does not receive medical treatment), the number of medical treatment visits (the number of times one visits the consulting room within the hospital), the number of medicine pick-ups (the number of times one goes to the pharmacy within the hospital to pick up medicine), and the number of specialist appointments, any one or more of the above.

[0083] S300 performs risk scoring according to the comparison result and the analysis result, and generates a prompt instruction for the risky user according to the risk scoring result;

[0084] S400 sends the prompt instruction to the target terminal in the hospital to initiate a risk prompt.

[0085] The present invention utilizes a camera to detect facial images of hospital visitors, analyzes the probability of the hospital visitors being suspected risk users such as "scalpers", "medical trouble makers", "criminal suspects", "criminals", etc., initiates risk warnings for users with a high probability of being risk users, and issues background warnings. By utilizing existing surveillance cameras in the hospital or deploying additional surveillance camera equipment, the present invention can not only accurately identify "scalpers" in order to promptly stop behaviors that disrupt the medical resource allocation rules, but also exclude other risk users and maintain the normal medical order in the hospital.

[0086] One embodiment of the present invention is a method for identifying scalpers, comprising:

[0087] S010 respectively set target cameras in the preset area and the site service robot within the hospital site;

[0088] S100 obtains the environmental video captured by the target camera within the hospital premises;

[0089] S210 detects and identifies a facial image appearing in the video image by using a face detection algorithm;

[0090] S220 compares the facial image with a preset facial image in a blacklist database to obtain the comparison result;

[0091] S230 counting the number of visits and medical treatment behaviors of the corresponding user in the hospital according to the facial image;

[0092] S310, performing risk scoring on the comparison result and the analysis result respectively according to a preset score evaluation strategy;

[0093] S320: summing up the risk scoring results to obtain a total score, and obtaining a prompt instruction of a corresponding facial image according to the total score;

[0094] Specifically, the server stores a preset score evaluation strategy set by the hospital manager or hospital owner. Then, the server scores different comparison results and analysis results one by one according to the preset score evaluation strategy.

[0095] The preset score evaluation strategy stored in the server corresponds to at least two scoring dimensions, and the at least two scoring dimensions may include: at least two of a qualitative evaluation strategy, a first quantitative evaluation strategy, and a second quantitative evaluation strategy.

[0096] In one embodiment, the factor considered by the qualitative assessment strategy is whether the user belongs to a risk user in the blacklist database. For example, if the user belongs to a risk user in the blacklist database, the risk assessment score is the first score, otherwise the risk assessment score is the second score. The factor considered by the first quantitative assessment strategy is the indicator represented by the number of visits to the hospital, and the factor considered by the second quantitative assessment strategy is the indicator represented by the number of medical treatment behaviors. Among them, the specific indicators considered by each assessment strategy can be set according to actual needs, and the values ​​of the risk assessment scores corresponding to different indicators are different. The present invention does not limit the specific setting method.

[0097] The server obtains at least two risk scores based on the comparison result and the analysis result. The server finally sums or weights all the risk score results, and uses the sum or weighted sum, i.e., the total score, as the evaluation score for the user corresponding to the facial image. The weights used in the weighted summation can be set according to actual needs, and the present invention does not limit this. The server then obtains the prompt instruction for the corresponding facial image based on the total score.

[0098] S400 sends the prompt instruction to the target terminal in the hospital to initiate a risk prompt;

[0099] The preset areas include any one or more of a passage area, a registration area, a pharmacy area, an outpatient entrance and exit area, a consulting service area, and a consulting room area.

[0100] The present invention makes full use of the collected facial images, and divides the risk level of the user corresponding to the facial image according to actual needs, and then automatically generates corresponding discrimination conditions for constructing a discrimination rule for risky users. In this way, the generation and tuning of rules can be largely freed from the dependence on manual labor, and the generated rules have high usability and can fully meet the needs of practical applications.

[0101] One embodiment of the present invention is a method for identifying scalpers, comprising:

[0102] S100 obtains the environmental video captured by the target camera within the hospital premises;

[0103] S200 compares the facial image identified by the environmental video with the preset facial images in the blacklist database, and performs medical behavior analysis based on the facial image;

[0104] S311 determines whether further analysis is needed based on the risk level of the facial image and its history;

[0105] S312 If further analysis is required, a risk score is assigned to the facial image based on the number of times the medical treatment is sought;

[0106] S313 if no further analysis is needed, performing a risk score on the facial image based on the comparison result and the number of visits to the hospital;

[0107] S321: if the risk level is the first level when the mapping relationship table is queried according to the total score, a real-name system prompt instruction is generated;

[0108] S322: if the risk level is the second level when the mapping relationship table is queried according to the total score, a real-name system prompt instruction is generated, and the blacklist database is updated according to the facial image;

[0109] S323: if the risk level is the third level when the mapping relationship table is queried according to the total score value, an alarm prompt instruction is generated;

[0110] Specifically, the server determines the risk level for the user corresponding to the facial image according to the total score, and the risk level is used to characterize the risk level of the user corresponding to the facial image. The server obtains the final total risk value by calculating the weighted sum or sum of the risk assessment scores, and then queries the mapping relationship table according to the total risk value, and determines the risk level corresponding to the final total risk value as the risk level for the user corresponding to the facial image according to the correspondence between the total risk value and the risk level predetermined in the mapping relationship table. The higher the risk level, the lower the risk level of the user corresponding to the facial image, and the lower the risk level, the higher the risk level of the user corresponding to the facial image. Then, the server queries the mapping relationship table according to the risk level, and according to the correspondence between the risk level and the instruction predetermined in the mapping relationship table, the instruction found is the prompt instruction corresponding to the risk level of the user corresponding to the facial image.

[0111] S400 sends the prompt instruction to the target terminal in the hospital to initiate a risk prompt.

[0112] Exemplary method for judging "scalpers": judging based on risk assessment scores, saving historical information for each visitor identified by facial image, each visitor has their own total risk value, and warnings are issued based on the total risk value corresponding to the accumulated risk assessment score, and the historical information is cleared after being saved for one week. The corresponding relationship between the total risk value and the risk level is defined as follows:

[0113] 0 points: No risk or initial value is re-identified and scored.

[0114] 1-2 points: Further analysis is required.

[0115] 3 points: Low risk, real-name registration and real-name treatment are required for further analysis.

[0116] 4 points: Medium risk, real-name registration and treatment required, and blacklisted.

[0117] 5 points: High risk, report to the police and recommend human intervention and staff to understand the situation in detail. After investigation and proof, the blacklist can be removed.

[0118] Here, the definition of the corresponding relationship between the total risk value and the risk level is as follows: Figure 4 The different judgment logics shown (i.e., the comparison results and analysis results of the present invention) and the settings of the bonus values ​​in the bonus operations corresponding to different judgment logics (i.e., the risk assessment scores of the present invention) can be set according to business needs, and the present invention does not limit them.

[0119] Reminder and warning method: After the notification message of "real-name registration and real-name medical treatment" is issued, when the suspicious person registers or sees a doctor, a reminder of "real-name registration" will appear on the computer of the registration staff, the self-service registration machine, and the desktop computer in the clinic, and the hospital staff and doctors will conduct real-name authentication on the suspicious person. After real-name registration, the person must be in person to see a doctor. When a high-risk alarm is triggered, the computer at the outpatient service desk and the alarm in the security room will sound, the camera will report the location of the suspicious person, and the outpatient service desk staff and security guards will look for the suspicious person. If the person is not a criminal, the security guard can also order the suspicious person to stand still through the microphone and the hospital speakers; if the person is a criminal, it is appropriate to approach quietly.

[0120] The present invention utilizes a camera to detect facial images of hospital visitors, analyzes the probability that the hospital visitors are suspected to be risky users such as "scalpers", "medical troublemakers", "criminal suspects", and "criminals", and initiates risk warnings for users with a high probability of being risky users as background warnings. By utilizing existing surveillance cameras in the hospital or by deploying additional surveillance camera equipment, the present invention can not only accurately identify "scalpers" in order to promptly stop behaviors that disrupt the medical resource allocation rules, but also exclude other risky users, maintain the normal medical order in the hospital, improve hospital safety, and protect the rights of patients.

[0121] In addition, the present invention uses an automatic method to evaluate whether the hospital visitor is a risk user, with a fast evaluation speed, short cycle, and strong objectivity. The present invention adopts a statistical analysis method to provide a unified standard for the evaluation of the risk level of the hospital visitor corresponding to the facial image, improves the objectivity and accuracy of the risk level evaluation of the hospital visitor corresponding to the facial image, reduces a lot of labor costs, reduces the subjectivity and accidental errors of manual evaluation of whether the hospital visitor is a risk user, and enhances the accuracy and reliability of the evaluation.

[0122] One embodiment of the present invention is a risk management system, comprising: setting target cameras at a preset area and a site service robot in the hospital site;

[0123] An acquisition module is used to acquire the environment video captured by the target camera in the hospital site;

[0124] An analysis module, used to compare the facial image identified by the environmental video with the preset facial images in the blacklist database, and perform medical behavior analysis based on the facial image;

[0125] A processing module, used to perform risk scoring according to the comparison results and the analysis results, and generate a prompt instruction for the risky user according to the risk scoring result;

[0126] A communication module, used for sending the prompt instruction to a target terminal in the hospital to initiate a risk prompt;

[0127] The preset areas include any one or more of a passage area, a registration area, a pharmacy area, an outpatient entrance and exit area, a consulting service area, and a consulting room area.

[0128] Specifically, this embodiment is a system embodiment corresponding to the above method embodiment. For specific effects, please refer to the above method embodiment, which will not be described in detail here.

[0129] Based on the above embodiment, the analysis module includes:

[0130] A recognition unit, used to detect and recognize a facial image appearing in the video image by using a face detection algorithm;

[0131] A comparison unit, used for comparing the facial image with a preset facial image in a blacklist database to obtain the comparison result;

[0132] A statistical unit is used to count the number of visits to the hospital and the number of medical treatment behaviors of the corresponding user in the hospital according to the facial image.

[0133] Specifically, this embodiment is a system embodiment corresponding to the above method embodiment. For specific effects, please refer to the above method embodiment, which will not be described in detail here.

[0134] Based on the above embodiment, the processing module includes:

[0135] A scoring unit, used to perform risk scoring on the comparison result and the analysis result respectively according to a preset score evaluation strategy;

[0136] The processing unit is used to sum up the risk scoring results to obtain a total score value, and obtain a prompt instruction of the corresponding facial image according to the total score value.

[0137] Specifically, this embodiment is a system embodiment corresponding to the above method embodiment. For specific effects, please refer to the above method embodiment, which will not be described in detail here.

[0138] Based on the above embodiment, the scoring unit includes:

[0139] A judgment subunit, used to judge whether further analysis is needed according to the risk level of the facial image and its history;

[0140] An evaluation subunit is used to, if further analysis is required, perform a risk score on the facial image based on the number of medical visits; if no further analysis is required, perform a risk score on the facial image based on the comparison result and the number of visits to the hospital;

[0141] The processing unit comprises:

[0142] A processing subunit is used to generate a real-name prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the first level; generate a real-name prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the second level, and update the blacklist database according to the facial image; and generate an alarm prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the third level.

[0143] Specifically, this embodiment is a system embodiment corresponding to the above method embodiment. For specific effects, please refer to the above method embodiment, which will not be described in detail here.

[0144] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned program modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program units or modules to complete all or part of the functions described above. The program modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into a processing unit, and the above-mentioned integrated unit can be implemented in the form of hardware or in the form of software program units. In addition, the specific names of the program modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0145] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed with hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0147] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0148] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0149] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0150] It should be noted that the above embodiments can be freely combined as needed. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A risk management method, characterized in that: Includes steps: Obtain the environmental video captured by the target camera within the hospital premises; The facial image identified by the environmental video is compared with the preset facial images in the blacklist database based on a qualitative evaluation strategy, and a medical behavior analysis is performed based on the facial image based on a quantitative evaluation strategy, wherein the medical behavior analysis includes counting the number of visits to the hospital and the number of medical behaviors of the corresponding user in the hospital premises based on the facial image; Determine whether further analysis is needed based on the risk level of the facial image and its history: If further analysis is required, a risk score is assigned to the facial image based on the number of medical visits; If no further analysis is required, a risk score is assigned to the facial image based on the comparison result and the number of visits to the hospital; Generate prompt instructions for risky users based on risk scoring results; The prompt instruction is sent to a target terminal within the hospital site to initiate a risk prompt.

2. The risk management method according to claim 1, characterized in that: The step of obtaining the environment video collected by the target camera in the hospital premises includes: Setting target cameras at a preset area and a site service robot within the hospital site respectively; The preset areas include any one or more of a passage area, a registration area, a pharmacy area, an outpatient entrance and exit area, a consulting service area, and a consulting room area.

3. The risk management method according to claim 1, characterized in that: The step of comparing the facial image identified by the environmental video with the preset facial image in the blacklist database and analyzing the medical behavior based on the facial image comprises the following steps: Detect and identify facial images appearing in video images through a face detection algorithm; The facial image is compared with preset facial images in a blacklist database to obtain the comparison result.

4. The risk management method according to claim 3, characterized in that: The step of generating a prompt instruction for a risky user according to the risk scoring result comprises the following steps: The risk scoring results are summed up to obtain a total score value, and a prompt instruction of the corresponding facial image is obtained according to the total score value.

5. The risk management method according to claim 4, characterized in that: The step of summing up the risk scoring results to obtain a total score and obtaining a corresponding facial image prompt instruction according to the total score includes the following steps: If the risk level is the first level when the mapping relationship table is queried according to the total score value, a real-name system prompt instruction is generated; If the risk level is the second level when the mapping relationship table is queried according to the total score value, a real-name prompt instruction is generated, and the blacklist database is updated according to the facial image; If the risk level is the third level as obtained by querying the mapping relationship table according to the total score value, an alarm prompt instruction is generated.

6. A risk management system, characterized in that: include: Target cameras are respectively set up at preset areas within the hospital premises and at the site service robot; An acquisition module is used to acquire the environment video captured by the target camera in the hospital site; An analysis module, for comparing the facial image identified by the environmental video with the preset facial images in the blacklist database based on a qualitative evaluation strategy, and performing a medical behavior analysis based on the facial image based on a quantitative evaluation strategy, wherein the medical behavior analysis includes counting the number of visits to the hospital and the number of medical behaviors of the corresponding user appearing in the hospital premises based on the facial image; A processing module, used to perform risk scoring according to the comparison results and the analysis results, and generate a prompt instruction for the risky user according to the risk scoring result; A communication module, used for sending the prompt instruction to a target terminal in the hospital site to initiate a risk prompt; The preset area includes any one or more of a passage area, a registration area, a pharmacy area, an outpatient entrance and exit area, a consulting service area, and a consulting room area; Wherein, the processing module includes a scoring unit, which is used to perform risk scoring on the comparison result and the analysis result respectively according to a preset score evaluation strategy; The scoring unit comprises: A judgment subunit, used to judge whether further analysis is needed according to the risk level of the facial image and its history; The evaluation subunit is used to perform risk scoring on the facial image according to the number of medical visits if further analysis is required; and to perform risk scoring on the facial image according to the comparison result and the number of visits if no further analysis is required.

7. The risk management system according to claim 6, characterized in that: The analysis module comprises: A recognition unit, used for detecting and recognizing facial images appearing in video images through a face detection algorithm; A comparison unit, used for comparing the facial image with a preset facial image in a blacklist database to obtain the comparison result; A statistical unit is used to count the number of visits to the hospital and the number of medical treatment behaviors of the corresponding user in the hospital according to the facial image.

8. The risk management system according to claim 7, characterized in that: The processing module comprises: The processing unit is used to sum up the risk scoring results to obtain a total score value, and obtain a prompt instruction of the corresponding facial image according to the total score value.

9. The risk management system according to claim 8, characterized in that: The processing unit comprises: A processing subunit is used to generate a real-name prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the first level; generate a real-name prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the second level, and update the blacklist database according to the facial image; and generate an alarm prompt instruction if the risk level obtained by querying the mapping relationship table according to the total score is the third level.

Images