Information processing method and computer-readable storage medium

Abstract

The present application discloses an information processing method, comprising: determining association information between a candidate object and a target location; wherein the candidate object is an object corresponding to a target object; and the target location is a location where the target object is located; obtaining first attribute information of the target object, determining a first matching degree between the first attribute information and second attribute information of the candidate object, wherein the second attribute information is pre-stored in a data set corresponding to the target location; determining a target biometric matching threshold based on the association information and the first matching degree; and determining a target matching object that matches the target object from the candidate objects according to the target biometric matching threshold. The present application also discloses a computer-readable storage medium.

Description

Technical Field

[0001] The present application relates to information processing technology in the field of information processing, and in particular to an information processing method and a computer-readable storage medium. Background Art

[0002] With the development of computer vision, face recognition has been widely used in fields such as finance and security. When performing face recognition, the face to be recognized is usually matched with faces in a database, and the face with the highest matching degree with the face to be recognized is determined from the database as the target matching face. However, as the number of faces in the database increases, there are alternative faces in the database that are similar to the face to be recognized. When determining the target matching face using the above method, the alternative faces are not taken into account, resulting in inaccurate determination of the target matching face. Summary of the Invention

[0003] In order to solve the above technical problems, the embodiments of the present application hope to provide an information processing method and a computer-readable storage medium, which solves the problem that alternative faces are not taken into consideration when determining the target matching face, resulting in inaccurate determination of the target matching face.

[0004] The technical solution of this application is achieved as follows:

[0005] An information processing method, the method comprising:

[0006] Determine association information between candidate objects and target locations; wherein the candidate objects are objects corresponding to the target objects; and the target locations are locations where the target objects are located;

[0007] Acquiring first attribute information of the target object, and determining a first matching degree between the first attribute information and second attribute information of the candidate object, where the second attribute information is pre-stored in a data set corresponding to the target location;

[0008] determining a target biometric matching threshold based on the association information and the first matching degree;

[0009] According to the target biometric matching threshold, a target matching object that matches the target object is determined from the candidate objects.

[0010] In the above solution, determining the association information between the candidate object and the target location includes:

[0011] determining the target location where the target object is located;

[0012] The riding record information of the candidate object is acquired, and the associated information is determined based on the riding record information.

[0013] In the above solution, the step of obtaining the first attribute information of the target object includes:

[0014] Acquire a first image of the target object by an image acquisition component;

[0015] The first attribute information is determined based on the first image.

[0016] In the above solution, determining a first matching degree between the first attribute information and the second attribute information of the candidate object includes:

[0017] Acquiring the riding record information of the candidate object, and acquiring third attribute information from the second attribute information based on the riding record information;

[0018] The first attribute information is matched with the third attribute information to obtain the first matching degree.

[0019] In the above solution, the step of obtaining the third attribute information from the second attribute information based on the ride record information includes:

[0020] When the target object is located at the exit of the target location, target entry record information is obtained from the boarding record information, and third attribute information is determined from the second attribute information based on the target entry record information; wherein the target entry record information is the entry record information of the most recent time from the current time; or

[0021] When the target object is located at the exit of the target place, the target entry record information and the first target entry and exit record information are obtained from the ride record information, and based on the target entry record information and the first target entry and exit record information, the third attribute information is determined from the second attribute information; wherein, the first target entry and exit record information includes the first exit record information before the current time and the first entry record information corresponding to the first exit record information.

[0022] In the above solution, determining the third attribute information from the second attribute information based on the ride record information includes:

[0023] When the target object is at the entrance of the target location, obtaining second target entry and exit record information from the boarding record information; wherein the second target entry and exit record information includes the second exit record information before the current time and the second entry record information corresponding to the second exit record information;

[0024] The third attribute information is determined from the second attribute information based on the second target entry and exit record information.

[0025] In the above solution, determining the target biometric matching threshold based on the association information and the first matching degree includes:

[0026] determining a second biometric matching threshold based on the association information and the first biometric matching threshold;

[0027] If the first matching degree satisfies a target matching degree condition, determining the target biometric matching threshold as the second biometric matching threshold;

[0028] In a case where the first matching degree does not satisfy the target matching degree condition, the second biometric matching threshold is processed to obtain the target biometric matching threshold.

[0029] In the above solution, determining the second biometric matching threshold based on the association information and the first biometric matching threshold includes:

[0030] If the association information satisfies the target location association condition, determining the second biometric matching threshold to be the first biometric matching threshold;

[0031] In a case where the association information does not satisfy the target location association condition, the first biometric matching threshold is processed to obtain the second biometric matching threshold.

[0032] In the above solution, the step of determining a target matching object that matches the target object from the candidate objects based on the target biometric matching threshold includes:

[0033] determining a plurality of second matching degrees of biometric matching between the target object and the candidate objects based on the first image of the target object and the plurality of second images of the candidate objects;

[0034] In a case where there is a second matching degree that satisfies the target biometric matching threshold, determining the target matching object from the candidate objects based on the second matching degree;

[0035] Accordingly, the method further includes:

[0036] In the case that the second matching degree does not satisfy the target biometric matching threshold, alarm information for prompting that the target object is an abnormal object is generated and output.

[0037] A computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the above-mentioned information processing method.

[0038] The information processing method and computer-readable storage medium provided by the embodiments of the present application determine the association information between the candidate object and the target place; wherein the candidate object is an object corresponding to the target object; the target place is the place where the target object is located; obtain the first attribute information of the target object, determine the first matching degree between the first attribute information and the second attribute information of the candidate object, and the second attribute information is pre-stored in the data set corresponding to the target place; determine the target biometric matching threshold based on the association information and the first matching degree; determine the target matching object that matches the target object from the candidate objects according to the target biometric matching threshold; in this way, the candidate objects similar to the target object are taken into consideration, and based on the target biometric matching threshold corresponding to the determined candidate objects, the candidate objects are screened to obtain the target matching object, thereby improving the accuracy of determining the target matching object and solving the problem that the candidate objects are not taken into consideration when determining the target matching object, resulting in inaccurate determination of the target matching object. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flowchart of an information processing method provided in an embodiment of the present application;

[0040] Figure 2 A flowchart of another information processing method provided in an embodiment of the present application;

[0041] Figure 3 A flowchart of another information processing method provided in an embodiment of the present application;

[0042] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0044] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] The present application provides an information processing method that can be applied to electronic devices. Figure 1 As shown, the method includes the following steps:

[0046] Step 101: Determine the association information between candidate objects and target locations.

[0047] The candidate object is an object corresponding to the target object; the target location is the location where the target object is located; and the association information may be the degree of association between the candidate object and the target location.

[0048] In an embodiment of the present application, historical behavior information of candidate objects in multiple locations can be obtained, and based on the historical behavior information, the association information between the candidate objects and the target location can be determined; wherein the candidate objects can be objects similar to the target object; the electronic device can match the target object with multiple facial objects in a database to obtain an initial matching degree between the target object and each facial object; if there is an initial matching degree within a matching degree threshold range, the facial object corresponding to the initial matching degree within the matching degree threshold range is selected as the candidate object. The matching degree threshold range can be a pre-set initial face recognition threshold range; the number of candidate objects can be at least one.

[0049] It should be noted that the maximum initial matching degree can be obtained from multiple initial matching degrees. When the maximum initial matching degree is greater than the maximum matching degree threshold within the matching degree threshold range, the face object corresponding to the maximum initial matching degree is used as the target matching object that matches the target object, so as to determine the identity information of the target object based on the target matching object; when the maximum initial matching degree is less than the minimum matching degree threshold within the matching degree threshold range, it is determined that there is no target matching object that matches the target object in the database, and an alarm information is generated to prompt that the target object is an abnormal object.

[0050] In one feasible implementation, the object to be processed can be a passenger entering or exiting a subway station, the target location can be the target station where the passenger is located, and the candidate objects can be objects in a database that are similar to the passenger to be identified. The database includes registered images of the passenger before their initial boarding; each registered image corresponds to an identity information; and the historical behavior information can include the passenger's historical travel records.

[0051] Step 102: Acquire first attribute information of the target object, and determine a first matching degree between the first attribute information and second attribute information of the candidate object.

[0052] The second attribute information is pre-stored in a data set corresponding to the target location.

[0053] In this embodiment of the present application, the first attribute information may be acquired when the target object is at the target location; the first attribute information may include at least one of the target object's clothing, gender, age, and gait; and the second attribute information may be historical attribute information of the candidate object. The second attribute information may include at least one of the candidate object's clothing, gender, age, and gait.

[0054] It should be noted that the first matching degree can be the matching degree between the first attribute information and all the information in the second attribute information; of course, the first matching degree can also be the matching degree between the first attribute information and part of the attribute information in the second attribute information; when determining the first matching degree, it can be determined based on the weight corresponding to the attribute type; the attribute types include: gender, age, gait and clothing; different attribute types correspond to different weights.

[0055] In one feasible implementation, the weight corresponding to gender is a first weight, the weight corresponding to age is a second weight, the weight corresponding to gait is a third weight, and the weight corresponding to clothing is a fourth weight. A first sub-matching degree between the gender of the target object and the gender of the candidate object, a second sub-matching degree between the age of the target object and the age of the candidate object, a third sub-matching degree between the gait of the target object and the gait of the candidate object, and a fourth sub-matching degree between the clothing of the target object and the clothing of the candidate object can be calculated. The electronic device can multiply the first sub-matching degree by the first weight to obtain a first value, multiply the second sub-matching degree by the second weight to obtain a second value, multiply the third sub-matching degree by the third weight to obtain a third value, and multiply the fourth sub-matching degree by the fourth weight to obtain a fourth value. The electronic device can then accumulate the first, second, third, and fourth values to obtain a first match.

[0056] Step 103: Determine a target biometric matching threshold based on the association information and the first matching degree.

[0057] In an embodiment of the present application, a first biometric matching threshold can be obtained, and whether to adjust the first biometric matching threshold can be determined based on the associated information and the first matching degree. If it is determined to adjust the first biometric matching threshold, the first biometric matching threshold is adjusted to obtain the target biometric matching threshold; if it is determined not to adjust the first biometric matching threshold, the first biometric matching threshold is determined to be the target biometric matching threshold; wherein the first biometric matching threshold is a preset face recognition threshold corresponding to the alternative object; the target biometric matching threshold can be the target face recognition threshold corresponding to the alternative object.

[0058] It should be noted that when there are multiple candidate objects, each candidate object corresponds to a first biometric matching threshold, and each candidate object corresponds to a target biometric matching threshold. The first biometric matching threshold can be determined based on the initial matching degree between the candidate object and the target object. The first biometric matching threshold corresponding to each candidate object can be the same. Of course, the first biometric matching threshold corresponding to each candidate object can also be different.

[0059] Step 104: Determine a target matching object that matches the target object from the candidate objects according to the target biometric matching threshold.

[0060] In an embodiment of the present application, a second matching degree of biometric matching between the candidate object and the target object can be determined, and a target matching object that matches the target object can be determined from the candidate objects based on the target biometric matching threshold and the second matching degree.

[0061] Specifically, when there is one candidate object, a determination is made as to whether the second matching degree satisfies the target biometric matching threshold. If the second matching degree satisfies the target biometric matching threshold, the candidate object is determined to be the target matching object. When there are multiple candidate objects, for the nth candidate object, a determination is made as to whether the second matching degree corresponding to the nth candidate object satisfies the target biometric matching threshold corresponding to the nth candidate object. If the second matching degree corresponding to the nth candidate object satisfies the target biometric matching threshold corresponding to the nth candidate object, the nth candidate object is retained. If the second matching degree corresponding to the nth candidate object does not satisfies the target biometric matching threshold corresponding to the nth candidate object, the nth candidate object is eliminated. The electronic device may then count the number of retained candidate objects. If the number of retained candidate objects is one, the retained candidate object is selected as the target matching object. If the number of retained candidate objects is multiple, the candidate object corresponding to the maximum second matching degree is determined from the multiple retained candidate objects as the target matching object. Where n is a positive integer.

[0062] The information processing method provided by the embodiments of the present application determines the association information between the candidate object and the target place; wherein the candidate object is an object corresponding to the target object; the target place is the place where the target object is located; obtains the first attribute information of the target object, determines the first matching degree between the first attribute information and the second attribute information of the candidate object, and the second attribute information is pre-stored in the data set corresponding to the target place; determines the target biometric matching threshold based on the association information and the first matching degree; determines the target matching object that matches the target object from the candidate objects according to the target biometric matching threshold; in this way, the candidate objects similar to the target object are taken into account, and based on the target biometric matching threshold corresponding to the determined candidate objects, the candidate objects are screened to obtain the target matching object, thereby improving the accuracy of determining the target matching object and solving the problem that the alternative objects are not taken into account when determining the target matching object, resulting in inaccurate determined target matching objects.

[0063] Based on the above embodiments, the embodiments of the present application provide an information processing method, referring to Figure 2 As shown, the method includes the following steps:

[0064] Step 201: The electronic device determines a target location where a target object is located.

[0065] In an embodiment of the present application, a first image of the target object can be obtained, and the target position of the image acquisition component that acquires the first image can be determined based on the first image, and the target place can be determined based on the target position; the background image of the target object can also be extracted from the first image, and the target place of the target object can be determined based on the background image.

[0066] In one feasible implementation, the target object is a passenger to be identified. A camera at a subway station entrance or exit can capture a first image of the passenger to be identified and send the first image to an electronic device. The electronic device can then determine the target boarding station where the passenger to be identified is located based on the camera's position. The electronic device can be a backend server at the subway station, and the target location includes the target boarding station.

[0067] Step 202: The electronic device obtains the riding record information of the candidate object and determines the associated information based on the riding record information.

[0068] In an embodiment of the present application, the ride record information is the record information of the candidate object during its historical rides; the electronic device can obtain the candidate object's ride record information from the ride record database based on the candidate object's identification; the electronic device can determine the number of times the target place appears in the places corresponding to the candidate object's historical rides based on the candidate object's ride record information, and determine the association information based on the target number and the total number of rides of the candidate object. The association information is the degree of association between the candidate object and the target place. The places corresponding to the candidate object's historical rides include historical entry places and historical exit places.

[0069] In a feasible implementation, the ratio of the target number of times to the total number of rides of the candidate objects is calculated, and the ratio is used as the target association information.

[0070] In a feasible implementation, the association information may also be the association between the candidate's user identity and the target location. For example, the candidate has a doctor's identity ID, and the target location is a hospital. The identity information is recorded in the hospital's access control database.

[0071] Step 203: The electronic device acquires a first image of the target object through an image acquisition component.

[0072] In the embodiment of the present application, when the target object is within the camera range of the image acquisition component, the image acquisition component can acquire a first image of the target object.

[0073] In a feasible implementation, the target object may be a passenger to be identified in a subway station, and the image acquisition component may be a camera installed at an entrance or exit of the subway station.

[0074] Step 204: The electronic device determines first attribute information based on the first image.

[0075] In an embodiment of the present application, a face area image can be extracted from the first image, and the face area image can be input into a human attribute recognition model to obtain first attribute information of the target object output by the human attribute recognition model.

[0076] In a feasible implementation, the target object is a passenger to be identified, and the first attribute information is the gender, age, clothing, and gait of the passenger to be identified; the first attribute information may also include the glasses of the passenger to be identified.

[0077] Step 205: The electronic device obtains the riding record information of the candidate object, and obtains the third attribute information from the second attribute information based on the riding record information.

[0078] It should be noted that the process of obtaining the passenger record information of the candidate object in step 205 can refer to the process of obtaining the passenger record information of the candidate object in step 202, and the embodiment of the present application will not be repeated here.

[0079] In an embodiment of the present application, the target ride record information can be obtained from the ride record information based on the location of the target object at the target place, and then the third attribute information corresponding to the target ride record information can be obtained from the second attribute information based on the target ride record information.

[0080] It should be noted that step 205 can be implemented through step a1 or a2; step 205 can also be implemented through steps a3-a4:

[0081] Step a1: When the target object is located at the exit of the target location, the electronic device obtains the target entry record information from the boarding record information, and determines the third attribute information from the second attribute information based on the target entry record information.

[0082] The target entry record information is the entry record information with the most recent time from the current time.

[0083] In an embodiment of the present application, it is possible to determine whether the target object is located at the exit of the target location based on the target position of the image acquisition component that captures the first image. If it is determined that the target object is located at the exit of the target location, the electronic device can obtain the target entry record information from the candidate object's boarding record information based on the current time, and obtain third attribute information corresponding to the target entry record information from the second attribute information. The third attribute information is attribute information of the candidate object when it boarded the vehicle and entered the station at the time closest to the current time.

[0084] It should be noted that the second attribute information may include the candidate's baseline attribute information and historical attribute information corresponding to each entry and exit of the candidate during their historical rides. The baseline attribute information is determined based on the candidate's registered image prior to their initial ride; the historical attribute information is determined based on captured images of the candidate entering and exiting the station during their historical rides. The candidate's entry record information corresponds to the candidate's entry attribute information, and the candidate's exit record information corresponds to the candidate's exit attribute information.

[0085] Step a2. When the target object is located at the exit of the target place, the electronic device obtains the target entry record information and the first target entry and exit record information from the riding record information, and determines the third attribute information from the second attribute information based on the target entry record information and the first target entry and exit record information.

[0086] The first target entry and exit record information includes the first exit record information before the current time and the first entry record information corresponding to the first exit record information.

[0087] In an embodiment of the present application, based on the target position of the image acquisition component, it is determined whether the target object is located at the exit of the target place. When it is determined that the target object is located at the exit of the target place, the electronic device obtains the target entry record information and the first target entry and exit record information from the riding record information; wherein, the process of obtaining the target entry record information in step a2 is the same as the process of obtaining the target entry record information in step a1, and the embodiment of the present application will not be repeated here.

[0088] The electronic device can obtain the first target entry and exit record information before the current time from the riding record information based on the current time; wherein the first target entry and exit record information can be a single entry and exit record information or multiple entry and exit record information; when the first target entry and exit record information is a single entry and exit record information, the first target entry and exit record information includes the exit record information at the time closest to the current time and the entry record information corresponding to the exit record information; when the first target entry and exit record information is multiple entry and exit record information, the first target entry and exit record information includes the multiple exit record information before the current time and the entry record information corresponding to each exit record information.

[0089] In an embodiment of the present application, based on the target entry record information and the first target entry and exit record information, the attribute information corresponding to the target entry record information and the attribute information corresponding to the first target entry and exit record information can be determined from the second attribute information to obtain the third attribute information.

[0090] Step a3: When the target object is at the entrance of the target location, the electronic device obtains the second target entry and exit record information from the riding record information.

[0091] The second target entry and exit record information includes the second exit record information before the current time and the second entry record information corresponding to the second exit record information.

[0092] In an embodiment of the present application, when it is determined that the target object is at the entrance of the target place based on the target position of the image acquisition component, the second target entry and exit record information is obtained from the riding record information of the alternative object based on the current time; wherein, the second target entry and exit record information can be the same as the first target entry and exit record information, or different from the first target entry record information.

[0093] Among them, the second target entry and exit record information can be a single entry and exit record information or multiple entry and exit record information; when the second target entry and exit record information is a single entry and exit record information, the second target entry and exit record information includes the exit record information at the time closest to the current time and the entry record information corresponding to the exit record information; when the second target entry and exit record information is multiple entry and exit record information, the second target entry and exit record information includes multiple exit record information before the current time and the entry record information corresponding to each exit record information.

[0094] Step a4: Based on the second target entry and exit record information, the electronic device determines the third attribute information from the second attribute information.

[0095] In an embodiment of the present application, based on the second target entry and exit record information, attribute information corresponding to the second entry and exit record information can be determined from the second attribute information to obtain third attribute information; wherein the third attribute information includes attribute information corresponding to the second exit record information and attribute information corresponding to the second entry record information.

[0096] Step 206: The electronic device matches the first attribute information with the third attribute information to obtain a first matching degree.

[0097] In an embodiment of the present application, the first attribute information and the third attribute information can be matched based on the attribute type; wherein the attribute type includes: gender, age, gait and clothing; different attribute types correspond to different weights.

[0098] Specifically, the gender of the target object in the first attribute information is matched with the gender of the alternative object in the third attribute information, the age of the target object in the first attribute information is matched with the age of the alternative object in the third attribute information, the gait of the target object in the first attribute information is matched with the gait of the alternative object in the third attribute information, and the clothing of the target object in the first attribute information is matched with the clothing of the alternative object in the third attribute information to obtain the matching degree corresponding to each attribute type, and the matching degree corresponding to each attribute type and the weight corresponding to each attribute type are weighted to obtain the first matching degree.

[0099] Step 207: The electronic device determines a second biometric matching threshold based on the associated information and the first biometric matching threshold.

[0100] The first biometric matching threshold is pre-set, and each candidate object corresponds to a first biometric matching threshold.

[0101] In an embodiment of the present application, it is possible to determine whether to adjust the first biometric matching threshold based on the association information to obtain a determination result, and determine a second biometric matching threshold based on the determination result and the first biometric matching threshold.

[0102] It should be noted that step 207 can be implemented through steps b1-b2:

[0103] Step b1: When the association information satisfies the target location association condition, the electronic device determines that the second biometric matching threshold is the first biometric matching threshold.

[0104] In an embodiment of the present application, when the association information meets the target place association conditions, the target place can be determined as a commonly used place of the candidate object. At this time, there is no need to adjust the first biometric matching threshold, and the first biometric matching threshold can be used as the second biometric matching threshold.

[0105] In a feasible implementation, the association information is the association degree between the target object and the target place; and the target place association condition is that the association degree is greater than the target association degree.

[0106] Step b2: When the association information does not meet the target location association condition, the electronic device processes the first biometric matching threshold to obtain a second biometric matching threshold.

[0107] In an embodiment of the present application, when the association information does not meet the target place association condition, the target place can be determined to be an uncommon place of an alternative object, and the first biometric matching threshold can be increased to obtain a second biometric matching threshold.

[0108] In a feasible implementation, the first biometric matching threshold may be increased according to the difference between the association degree and the target association degree to obtain the second biometric matching threshold.

[0109] Step 208: When the first matching degree satisfies the target matching degree condition, the electronic device determines the target biometric matching threshold as the second biometric matching threshold.

[0110] The target matching condition is that the first matching degree is greater than the first target matching degree.

[0111] In an embodiment of the present application, when the first matching degree is greater than the first target matching degree, it is determined that the first attribute information of the target object matches the second attribute information of the candidate object. At this time, the second biometric matching threshold may not be adjusted, and the second biometric matching threshold may be used as the target biometric matching threshold.

[0112] Step 209: When the first matching degree does not meet the target matching degree condition, the electronic device processes the second biometric matching threshold to obtain a target biometric matching threshold.

[0113] In an embodiment of the present application, when the first matching degree does not meet the target matching condition, the second biometric matching threshold can be increased to obtain the target biometric matching threshold.

[0114] It should be noted that the second biometric matching threshold may be increased according to the difference between the first matching degree and the first target matching degree to obtain the target biometric matching threshold.

[0115] Step 210: The electronic device determines a plurality of second matching degrees of biometric matching between the target object and the candidate objects based on the first image of the target object and the plurality of second images of the candidate objects.

[0116] Among them, the multiple second images include the registered image of the candidate object before the initial boarding, and the images of the candidate object when entering and exiting the station during the target time period before the current time; the number of candidate objects can be at least one; the biometric matching is facial feature matching, referred to as face matching.

[0117] In an embodiment of the present application, for each alternative object, a first face area image of the target object is extracted from the first image, and a second face area image of the alternative object is extracted from each second image. Based on the first face area image and multiple second face area images, multiple second matching degrees between the face of the target object and the face of the alternative object are determined.

[0118] It should be noted that when determining the alternative objects, the first image of the target object is matched with the registered images of multiple passengers in the database. When determining the target matching object from the alternative objects, the images of the alternative objects when entering and exiting the station during the target time period before the current time are also added. This takes into account the changes in the faces of the alternative objects during historical rides, thereby improving the accuracy of determining the target matching object from the alternative objects.

[0119] Step 211: When there is a second matching degree that satisfies the target biometric matching threshold, the electronic device determines a target matching object from the candidate objects based on the second matching degree.

[0120] In an embodiment of the present application, when the number of alternative objects is one, if there is a second matching degree among multiple second matching degrees that is greater than the target biometric matching threshold, the alternative object is used as the target matching object; when the number of alternative objects is multiple, for the nth alternative object, if there is a second matching degree greater than the target biometric matching threshold corresponding to the nth alternative object among the multiple second matching degrees corresponding to the nth alternative object, the alternative object is retained; if there is no second matching degree greater than the target biometric matching threshold corresponding to the nth alternative object among the multiple second matching degrees corresponding to the nth alternative object, the alternative object is deleted; the electronic device can count the number of retained alternative objects, and when the number of retained alternative objects is one, the retained alternative object is used as the target matching object; when the number of retained alternative objects is multiple, the alternative object corresponding to the maximum second matching degree can be determined from the retained alternative objects as the target matching object.

[0121] Based on the foregoing embodiment, in other embodiments of the present application, the information processing method may further include the following steps:

[0122] Step 212: If there is no second matching degree that satisfies the target biometric matching threshold, the electronic device generates and outputs an alarm message for indicating that the target object is an abnormal object.

[0123] In an embodiment of the present application, for each candidate object, if there is no second matching degree greater than the target biometric threshold, it means that there is no target matching object that matches the target object among the candidate objects, and an alarm information can be generated and output.

[0124] In a feasible implementation, the abnormal object may be an object that has not been registered on the ride platform before the initial ride; wherein the database does not have a registered image of the abnormal object.

[0125] The following is a detailed explanation of the information processing method provided in the embodiment of the present application in combination with the application scenario.

[0126] In the problem of massive face search, as the number of faces in the face database continues to increase, the accuracy of determining the target matching face that matches the face to be identified from N faces gradually decreases. The information processing method provided in the embodiment of the present application can be applied to the ride billing scenario, which improves the accuracy of determining the target object that matches the ride object to be identified.

[0127] Taking the subway fare billing scenario as an example, each exit and entrance of the subway station is equipped with a camera. When the passenger to be identified is at the entrance or exit of the subway station, the camera can capture a first image of the passenger to be identified and extract the first face area image from the first image, such as Figure 3 As shown, an initial face matching is performed on the first facial region image with N facial images in a database to obtain multiple initial similarities. An image corresponding to an initial matching degree within a matching degree threshold range is determined from the multiple facial images, and the object corresponding to the image is selected as a candidate object similar to the face of the passenger to be identified. The matching degree threshold range is a pre-set initial face recognition threshold range, which includes a minimum matching degree threshold and a maximum matching degree threshold. N is a positive integer. If none of the multiple initial matching degrees are within the matching degree threshold range, a final result is directly output. The maximum initial matching degree is determined from the multiple initial matching degrees. If the maximum initial matching degree is determined to be greater than the maximum matching degree threshold within the matching degree threshold range, the object corresponding to the maximum initial matching degree is selected as the target matching object for the passenger to be identified. If the maximum initial matching degree is determined to be less than or equal to the minimum matching degree threshold within the matching degree threshold range, an alarm is generated to indicate that the passenger to be identified is an abnormal object.

[0128] For each candidate, such as Figure 3As shown, the boarding record information of the candidate object is obtained, and based on the boarding record information of the candidate object, it is determined whether the target station where the passenger object to be identified is located is the candidate object's frequently used boarding station. If it is the candidate object's frequently used boarding place, the first face recognition threshold is used as the second face recognition threshold; if it is not the candidate object's frequently used boarding place, the first face recognition threshold is increased to obtain the second face recognition threshold; wherein, each candidate object corresponds to a first face recognition threshold, and then it is determined whether the passenger object to be identified is at the entrance of the target station. After determining that the passenger object to be identified is at the entrance of the target station, based on the information from the candidate object The third attribute information of the candidate object is determined by obtaining the most recent exit record information before the current time and the entry record information corresponding to the exit record information from the passenger record information of the object, and matching the first attribute information of the passenger to be identified with the third attribute information of the candidate object (i.e., attribute matching 1) to obtain a first matching degree. If the first matching degree is greater than the first target matching degree, it indicates that the first attribute information matches the third attribute information, and the target face recognition threshold is determined to be the second face recognition threshold; if the first matching degree is less than or equal to the second target matching degree, the second face recognition threshold is increased to obtain the target face recognition threshold. Of course, when determining that the passenger to be identified is at the entry point of the target station, the third attribute information of the candidate object can also be determined based on the multiple exit record information obtained before the current time and the entry record information corresponding to each exit record information.

[0129] When it is determined that the passenger to be identified is at the exit of the target station, the electronic device can determine the third attribute information of the candidate object based on the obtained entry record information closest to the current time, match the third attribute information with the first attribute information (i.e., attribute 2 matching) to obtain a first matching degree. When the first matching degree is greater than the first target matching degree, it is determined that the first attribute information of the passenger to be identified matches the third attribute information, and then the target face recognition threshold is determined to be the second face recognition threshold; when it is determined that the first attribute information of the passenger to be identified does not match the third attribute information, the second face recognition threshold is increased to obtain the target face recognition threshold. Of course, when it is determined that the passenger to be identified is at the exit of the target station, the third attribute information of the candidate object can also be determined based on the obtained entry record information closest to the current time, as well as multiple exit record information before the current time and entry record information corresponding to each exit record information.

[0130] After determining that the passenger to be identified is at the entrance of the target station, you can also first obtain the exit record information most recent from the current time and the entrance record information corresponding to the exit record information. Based on the obtained exit record information most recent from the current time and the entrance record information corresponding to the exit record information, obtain the first sub-attribute information of the candidate object from the second attribute information, and match the first sub-attribute information with the first attribute information of the passenger to be identified. When it is determined that the first sub-attribute information matches the first attribute information of the passenger to be identified, the second face recognition threshold is determined to be the target face recognition threshold corresponding to the candidate object; when it is determined that the first sub-attribute information matches the first attribute information of the passenger to be identified, When the first attribute information of the vehicle object does not match, the multiple exit record information before the current time and the entry record information corresponding to each exit record information are obtained, and based on the multiple exit record information before the current time and the entry record information corresponding to each exit record information, the second sub-attribute information of the alternative object is obtained from the second attribute information. When it is determined that the second sub-attribute information does not match the first attribute information of the passenger object to be identified, the second face recognition threshold is increased to obtain the target face recognition threshold; when it is determined that the second sub-attribute information matches the first attribute information of the passenger object to be identified, the second face recognition threshold is determined to be the target face recognition threshold corresponding to the alternative object.

[0131] After determining that the passenger to be identified is at the exit of the target station, the entry record information closest to the current time can be obtained first, and the third sub-attribute information of the candidate object can be determined from the second attribute information based on the entry record information, and the third sub-attribute information can be matched with the first attribute information. When the third sub-attribute information matches the first attribute information, the second face recognition threshold is determined to be the target face recognition threshold corresponding to the candidate object; when the third sub-attribute information does not match the first attribute information, the exit record information before the current time and the entry record information corresponding to the exit record information are obtained, and based on the exit record information before the current time and the entry record information corresponding to the exit record information, the fourth sub-attribute information of the candidate object is obtained. When the fourth sub-attribute information matches the first attribute information, the second face recognition threshold is determined to be the target face recognition threshold corresponding to the candidate object; when the fourth sub-attribute information does not match the first attribute information, the second face recognition threshold is increased to obtain the target face recognition threshold.

[0132] For each candidate object, based on the second matching degree between the face of the passenger to be identified and the face of the candidate object and the target face recognition threshold of the candidate object, a target matching object that matches the passenger to be identified is determined from the candidate objects, so as to determine the identity information of the target object, and then automatically bill the target object for this ride; if there is no second matching degree that meets the target face recognition threshold, an alarm message is generated and output to prompt that the target object is an abnormal object.

[0133] In a feasible implementation, the alarm information may be sent to a user terminal corresponding to the candidate object, and may also be sent to a terminal of an administrator of the boarding point.

[0134] It should be noted that, for the description of the same steps and contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0135] The information processing method provided in the embodiments of the present application takes into account alternative objects that are similar to the target object, and based on the target biometric matching threshold corresponding to the determined alternative objects, screens the alternative objects to obtain the target matching object, thereby improving the accuracy of determining the target matching object and solving the problem that the alternative objects are not taken into account when determining the target matching object, resulting in inaccurate determination of the target matching object.

[0136] Based on the above embodiments, the embodiment of the present application provides an electronic device, which can be applied to Figures 1-2 In the information processing method provided in the corresponding embodiment, refer to Figure 4 As shown, the electronic device 3 may include: a processor 31, a memory 32 and a communication bus 33;

[0137] The communication bus 33 is used to realize the communication connection between the processor 31 and the memory 32;

[0138] The processor 31 is used to execute the information processing program in the memory 32 to implement the following steps:

[0139] Determine association information between candidate objects and target locations; wherein the candidate objects are objects corresponding to the target objects; and the target location is the location where the target objects are located;

[0140] Acquiring first attribute information of the target object, and determining a first matching degree between the first attribute information and second attribute information of the candidate object, the second attribute information being pre-stored in a data set corresponding to the target location;

[0141] determining a target biometric matching threshold based on the association information and the first matching degree;

[0142] According to the target biometric matching threshold, a target matching object that matches the target object is determined from the candidate objects.

[0143] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine the association information between the candidate object and the target location, so as to implement the following steps:

[0144] Determine the target location where the target object is located;

[0145] The riding record information of the candidate object is obtained, and related information is determined based on the riding record information.

[0146] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to obtain the first attribute information of the target object, so as to implement the following steps:

[0147] Acquire a first image of the target object by an image acquisition component;

[0148] First attribute information is determined based on the first image.

[0149] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine a first matching degree between the first attribute information and the second attribute information of the candidate object, so as to implement the following steps:

[0150] Acquire the riding record information of the candidate object, and acquire the third attribute information from the second attribute information based on the riding record information;

[0151] The first attribute information is matched with the third attribute information to obtain a first matching degree.

[0152] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to obtain the third attribute information from the second attribute information based on the ride record information, so as to implement the following steps:

[0153] When the target object is located at the exit of the target location, the target entry record information is obtained from the boarding record information, and the third attribute information is determined from the second attribute information based on the target entry record information; wherein the target entry record information is the entry record information of the most recent time from the current time; or,

[0154] When the target object is located at the exit of the target place, the target entry record information and the first target entry and exit record information are obtained from the riding record information, and based on the target entry record information and the first target entry and exit record information, the third attribute information is determined from the second attribute information; wherein, the first target entry and exit record information includes the first exit record information before the current time and the first entry record information corresponding to the first exit record information.

[0155] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine the third attribute information from the second attribute information based on the ride record information, so as to implement the following steps:

[0156] When the target object is at the entrance of the target location, obtain second target entry and exit record information from the boarding record information; wherein the second target entry and exit record information includes the second exit record information before the current time and the second entry record information corresponding to the second exit record information;

[0157] Based on the second target entry and exit record information, third attribute information is determined from the second attribute information.

[0158] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine the target biometric matching threshold based on the association information and the first matching degree, so as to implement the following steps:

[0159] determining a second biometric matching threshold based on the association information and the first biometric matching threshold;

[0160] When the first matching degree satisfies the target matching degree condition, determining the target biometric matching threshold as the second biometric matching threshold;

[0161] When the first matching degree does not satisfy the target matching degree condition, the second biometric matching threshold is processed to obtain the target biometric matching threshold.

[0162] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine the second biometric matching threshold based on the associated information and the first biometric matching threshold, so as to implement the following steps:

[0163] If the association information satisfies the target location association condition, determining the second biometric matching threshold to be the first biometric matching threshold;

[0164] When the association information does not satisfy the target location association condition, the first biometric matching threshold is processed to obtain a second biometric matching threshold.

[0165] In other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to determine a target matching object that matches the target object from the candidate objects based on the target biometric matching threshold, so as to implement the following steps:

[0166] determining a plurality of second matching degrees of biometric matching between the target object and the candidate objects based on the first image of the target object and the plurality of second images of the candidate objects;

[0167] In the case where there is a second matching degree that satisfies the target biometric matching threshold, determining a target matching object from the candidate objects based on the second matching degree;

[0168] Accordingly, in other embodiments of the present application, the processor 31 is configured to execute the information processing program in the memory 32 to implement the following steps:

[0169] In the case that there is no second matching degree that satisfies the target biometric matching threshold, alarm information for prompting that the target object is an abnormal object is generated and output.

[0170] It should be noted that the specific implementation process of the steps executed by the processor in this embodiment can be referred to Figures 1-2 The implementation process of the information processing method provided in the corresponding embodiment will not be repeated here.

[0171] The communication electronic device provided in the embodiments of the present application takes into account alternative objects that are similar to the target object, and screens the alternative objects based on the target biometric matching threshold corresponding to the determined alternative objects to obtain the target matching object, thereby improving the accuracy of determining the target matching object and solving the problem that the alternative objects are not taken into account when determining the target matching object, resulting in inaccurate determination of the target matching object.

[0172] Based on the above embodiments, the embodiments of the present application provide a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement Figures 1-2 The corresponding embodiments provide steps of the information processing method.

[0173] It should be noted that the above-mentioned computer-readable storage medium can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface storage, an optical disc, or a compact disc read-only memory (CD-ROM); it can also be various electronic devices that include one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0174] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0175] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0176] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0177] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0180] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An information processing method, comprising: Determine association information between candidate objects and target locations; wherein the candidate objects are objects corresponding to the target objects; and the target location is the location where the target objects are located; Acquiring first attribute information of the target object, and determining a first matching degree between the first attribute information and second attribute information of the candidate object, where the second attribute information is pre-stored in a data set corresponding to the target location; determining a target biometric matching threshold based on the association information and the first matching degree; According to the target biometric matching threshold, a target matching object that matches the target object is determined from the candidate objects.

2. The method according to claim 1, wherein determining the association information between the candidate object and the target location comprises: determining the target location where the target object is located; The riding record information of the candidate object is acquired, and the associated information is determined based on the riding record information.

3. The method according to claim 1, wherein obtaining the first attribute information of the target object comprises: Acquire a first image of the target object by an image acquisition component; The first attribute information is determined based on the first image.

4. The method according to claim 1, wherein determining a first matching degree between the first attribute information and the second attribute information of the candidate object comprises: Acquiring the riding record information of the candidate object, and acquiring third attribute information from the second attribute information based on the riding record information; The first attribute information is matched with the third attribute information to obtain the first matching degree.

5. The method according to claim 4, wherein the acquiring of the third attribute information from the second attribute information based on the riding record information comprises: When the target object is located at the exit of the target location, the target entry record information is obtained from the boarding record information, and the third attribute information is determined from the second attribute information based on the target entry record information; wherein, The target entry record information is the entry record information of the most recent time. or, When the target object is located at the exit of the target place, the target entry record information and the first target entry and exit record information are obtained from the ride record information, and based on the target entry record information and the first target entry and exit record information, the third attribute information is determined from the second attribute information; wherein, the first target entry and exit record information includes the first exit record information before the current time and the first entry record information corresponding to the first exit record information.

6. The method according to claim 4, wherein determining the third attribute information from the second attribute information based on the ride record information comprises: When the target object is at the entrance of the target location, second target entry and exit record information is obtained from the boarding record information; wherein, The second target entry and exit record information includes the second exit record information before the current time and the second entry record information corresponding to the second exit record information; The third attribute information is determined from the second attribute information based on the second target entry and exit record information.

7. The method according to claim 1, wherein determining a target biometric matching threshold based on the association information and the first matching degree comprises: determining a second biometric matching threshold based on the association information and the first biometric matching threshold; If the first matching degree satisfies a target matching degree condition, determining the target biometric matching threshold as the second biometric matching threshold; In a case where the first matching degree does not satisfy the target matching degree condition, the second biometric matching threshold is processed to obtain the target biometric matching threshold.

8. The method according to claim 7, wherein determining the second biometric matching threshold based on the association information and the first biometric matching threshold comprises: If the association information satisfies the target location association condition, determining the second biometric matching threshold to be the first biometric matching threshold; In a case where the association information does not satisfy the target location association condition, the first biometric matching threshold is processed to obtain the second biometric matching threshold.

9. The method according to claim 1, wherein determining a target matching object that matches the target object from the candidate objects based on the target biometric matching threshold comprises: determining a plurality of second matching degrees of biometric matching between the target object and the candidate objects based on the first image of the target object and the plurality of second images of the candidate objects; In a case where there is a second matching degree that satisfies the target biometric matching threshold, determining the target matching object from the candidate objects based on the second matching degree; Accordingly, the method further includes: In the case that the second matching degree does not satisfy the target biometric matching threshold, alarm information for prompting that the target object is an abnormal object is generated and output.

10. A computer-readable storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the steps of the information processing method according to any one of claims 1 to 9.

Images