CN111666443A

CN111666443A - Service processing method and device, electronic equipment and computer readable storage medium

Info

Publication number: CN111666443A
Application number: CN202010496795.5A
Authority: CN
Inventors: 丁凯; 严石伟; 蒋楠
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-06-03
Filing date: 2020-06-03
Publication date: 2020-09-15

Abstract

The application provides a service processing method, a service processing device, electronic equipment and a computer readable storage medium, and relates to the field of big data. The method comprises the following steps: acquiring a service processing request; the service processing request comprises face data of an object to be detected; when the face data meet preset detection conditions, matching the face data based on a preset temporary database; if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; and if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data. The method and the device greatly improve the efficiency and the accuracy of retrieval, thereby improving the efficiency and the accuracy of business processing.

Description

Service processing method and device, electronic equipment and computer readable storage medium

Technical Field

The present application relates to the field of big data technologies, and in particular, to a service processing method, an apparatus, an electronic device, and a computer-readable storage medium.

Background

Artificial intelligence technology is currently used in a wide range of applications in smart retail, including promotion and landing in smart retail store scenes (such as customer arrival-at-store reminder schemes), enabling offline stores, and creating new retail.

The existing reminding scheme for the arrival of the customer comprises the steps of obtaining face data of the customer and then finishing the arrival reminding service based on a face recognition technology. However, the existing arrival-at-store reminder scheme has the following disadvantages:

(1) the algorithm performance is poor. In the process of face recognition, along with the increase of the number of faces, the accuracy of a face recognition algorithm is obviously reduced;

(2) the retrieval speed is slow: in the process of face recognition, as the number of faces increases, the recognition speed is slow, and it is a great challenge to remind a service with high real-time requirement.

Disclosure of Invention

The application provides a service processing method, a service processing device, an electronic device and a computer-readable storage medium, which can solve the problems. The technical scheme is as follows:

in a first aspect, a method for processing a service is provided, where the method includes:

acquiring a service processing request; the service processing request comprises face data of an object to be detected;

when the face data meet preset detection conditions, matching the face data based on a preset temporary database; the temporary database comprises at least one piece of face data acquired and stored in a preset time period;

if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data;

and if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data.

Preferably, the face data includes at least one acquired face image to be detected of the object to be detected;

the face data meets the preset detection conditions, and the detection conditions comprise:

calculating to obtain quality scores of all the face images to be detected, and comparing all the quality scores with a first quality score threshold value;

when the quality score of at least one face image exceeds the first quality score threshold value, judging that the face data meet a preset detection condition;

and acquiring each face image with the quality score exceeding the first quality score threshold, and taking the face image with the highest quality score as a target face image to be detected.

Preferably, the service processing request further includes a service type; the temporary database comprises at least one temporary sub-library, and each temporary sub-library has a corresponding service type;

the matching of the face data based on the preset temporary database comprises the following steps:

and determining a target temporary sub-library from each temporary sub-library based on the service type, and matching the target face image to be detected in the target temporary sub-library.

Preferably, each temporary sub-library comprises at least one piece of first identification information, each piece of first identification information corresponds to one piece of face data, and each piece of face data comprises at least one piece of first historical face image;

the matching of the target face image to be detected in the target temporary sub-library comprises the following steps:

acquiring the face features to be detected of the target corresponding to the face image to be detected of the target;

determining a first identification face feature corresponding to each piece of first identification information based on each piece of first historical face image corresponding to each piece of first identification information;

matching the target face features to be detected with each first identification face feature, taking the first identification face feature with the highest matching degree as a first target identification face feature, and taking first identification information corresponding to the first target identification face feature as target identification information;

calculating to obtain a feature score of the first target identification face feature;

and when the feature score of the first target identification face feature exceeds a first feature score threshold value, judging that the matching is successful.

Preferably, the method further comprises the following steps:

when the feature score of the first target face recognition feature does not exceed a first feature score threshold value, judging that the matching fails;

and generating new identification information, establishing a corresponding relation between the target human face image to be detected and the new identification information, and taking the new identification information as target identification information.

Preferably, updating the temporary database and the complete database based on the face data includes:

when the quality score of the target face image to be detected exceeds a second quality score threshold value, acquiring the number of first historical face images corresponding to target identification information;

updating the temporary database and the complete database based on the quantity and the face data.

Preferably, the updating the temporary database and the complete database based on the number and the face data includes:

when the number is equal to 1, calculating to obtain a quality score of the first historical face image;

and if the quality score does not exceed a third quality score threshold, replacing the first historical face image in the temporary target sub-library with the target face image to be detected, and storing the target face image to be detected in a complete database.

if the quality score exceeds the third quality score threshold value, or the number is greater than 1, judging whether the score of the target human face image to be detected exceeds a fourth quality score threshold value;

if so, establishing a corresponding relation between the target face image to be detected and the target identification information, storing the target face image to be detected to a target temporary sub-library, and storing the target face image to be detected to the complete database.

and when the number is equal to 0, storing the target face image to be detected to a target temporary sub-library, and storing the target face image to be detected to the complete database.

Preferably, the complete database comprises at least one complete sub-library, each complete sub-library having a corresponding service type;

matching the face data based on a preset complete database to obtain a matching result, wherein the matching result comprises the following steps:

and determining a target complete sub-library from the complete sub-libraries based on the service type, and matching the target face image to be detected in the target complete sub-library to obtain a matching result.

Preferably, each complete sub-library comprises at least one piece of second identification information, and each piece of second identification information corresponds to at least one piece of second historical face image;

matching the face image to be detected of the target in the target complete sub-library, wherein the matching comprises the following steps:

acquiring new identification information and a target to-be-detected face image from a target temporary sub-library;

determining second identification face features corresponding to each piece of second identification information based on each piece of second historical face image corresponding to each piece of second identification information;

matching the target face features to be detected with each second identification face feature, and taking the second identification face feature with the highest matching degree as a second target identification face feature;

calculating to obtain a feature score of the second target identification face feature;

when the feature score of the second target identification face feature exceeds a second feature score threshold value, judging that the matching is successful;

and when the score of the second target human face recognition feature does not exceed a third feature score threshold value, judging that the matching fails.

Preferably, generating a first processing result of the service processing request includes:

and generating a processing result that the object to be detected is a known object.

Preferably, generating a second processing result corresponding to the service processing request based on the matching result includes:

if the matching is judged to be successful, generating a processing result that the object to be detected is a known object;

and if the matching is judged to be failed, generating a processing result that the object to be detected is a new object.

Preferably, each face data has time information;

the method further comprises the following steps:

determining face data to be deleted from the temporary database based on the time information of each face data;

and deleting the face data to be deleted from the temporary database.

Preferably, the determining the face data to be deleted from the temporary database based on the time information of each face data includes:

determining the stored time of each face data in the temporary database based on the time information of each face data;

and determining at least one piece of face data to be deleted, the stored time of which exceeds a time threshold.

randomly acquiring a preset number of face data from the temporary database at preset time intervals;

determining the stored time of each acquired face data based on the time information of each face data;

In a second aspect, a service processing apparatus is provided, the apparatus including:

the acquisition module is used for acquiring a service processing request; the service processing request comprises face data of an object to be detected;

the matching module is used for matching the face data based on a preset temporary database when the face data meet preset detection conditions; the temporary database comprises at least one piece of face data acquired and stored in a preset time period;

the first processing module is used for generating a first processing result of the service processing request if the matching is successful, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data;

and the second processing module is used for matching the face data based on the complete database to obtain a matching result if the matching fails, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data.

the device further comprises a detection module, which is specifically configured to:

calculating to obtain quality scores of all the face images to be detected, and comparing all the quality scores with a first quality score threshold value; when the quality score of at least one face image exceeds the first quality score threshold value, judging that the face data meet a preset detection condition; and acquiring each face image with the quality score exceeding the first quality score threshold, and taking the face image with the highest quality score as a target face image to be detected.

the matching module is specifically configured to:

the matching module comprises:

the first acquisition submodule is used for acquiring the face features to be detected of the target corresponding to the face image to be detected of the target;

the first determining submodule is used for determining first identification face features corresponding to each piece of first identification information based on each piece of first historical face image corresponding to each piece of first identification information;

the first matching submodule is used for matching the target to-be-detected face features with each first identification face feature, taking the first identification face feature with the highest matching degree as a first target identification face feature, and taking first identification information corresponding to the first target identification face feature as target identification information;

the first calculation submodule is used for calculating and obtaining the feature score of the first target identification face feature;

and the first judgment submodule is used for judging that the matching is successful when the feature score of the first target identification face feature exceeds a first feature score threshold value.

Preferably, the matching module further comprises:

the first judging submodule is further used for judging that matching fails when the feature score of the first target face identification feature does not exceed a first feature score threshold;

and the generation submodule is used for generating new identification information, establishing a corresponding relation between the target to-be-detected face image and the new identification information, and taking the new identification information as target identification information.

Preferably, the first processing module comprises:

the second obtaining submodule is used for obtaining the number of the first historical face images corresponding to the target identification information when the quality score of the target face image to be detected exceeds a second quality score threshold value;

and the updating submodule is used for updating the temporary database and the complete database based on the number and the face data.

Preferably, the update submodule is specifically configured to:

when the number is equal to 1, calculating to obtain a quality score of the first historical face image; and if the quality score does not exceed a third quality score threshold, replacing the first historical face image in the temporary target sub-library with the target face image to be detected, and storing the target face image to be detected in a complete database.

Preferably, the update submodule is specifically configured to:

if the quality score exceeds the third quality score threshold value, or the number is greater than 1, judging whether the score of the target human face image to be detected exceeds a fourth quality score threshold value; if so, establishing a corresponding relation between the target face image to be detected and the target identification information, storing the target face image to be detected to a target temporary sub-library, and storing the target face image to be detected to the complete database.

Preferably, the update submodule is specifically configured to:

the second processing module is specifically configured to:

the second processing module comprises:

the second acquisition submodule is used for acquiring new identification information and a target face image to be detected from the target temporary sub-library;

the second determining submodule is used for determining second identification face features corresponding to each piece of second identification information based on each piece of second historical face image corresponding to each piece of second identification information;

the second matching submodule is used for matching the target to-be-detected face features with each second identification face feature and taking the second identification face feature with the highest matching degree as a second target identification face feature;

the second calculation submodule is used for calculating and obtaining the feature score of the second target identification face feature;

the second judging sub-module is used for judging that the matching is successful when the feature score of the second target identification face feature exceeds a second feature score threshold value; and when the score of the second target human face recognition feature does not exceed a third feature score threshold value, judging that the matching fails.

Preferably, the first processing module is specifically configured to:

Preferably, the second processing module is specifically configured to:

Preferably, each face data has time information;

the device further comprises:

the determining module is used for determining the face data to be deleted from the temporary database based on the time information of each face data;

and the deleting module is used for deleting the face data to be deleted from the temporary database.

Preferably, the determining module comprises:

the third calculation sub-module is used for determining the stored time of each face data in the temporary database based on the time information of each face data;

and the third determining submodule is used for determining at least one piece of face data to be deleted, the stored time of which exceeds the time threshold.

Preferably, the determining module comprises:

the third acquisition submodule is used for randomly acquiring a preset number of face data from the temporary database at preset time intervals;

the fourth calculation submodule is used for determining the stored time of each acquired face data based on the time information of each face data;

and the fourth determining submodule is used for determining at least one piece of face data to be deleted, the stored time of which exceeds the time threshold.

In a third aspect, an electronic device is provided, which includes:

a processor, a memory, and a bus;

the bus is used for connecting the processor and the memory;

the memory is used for storing operation instructions;

the processor is configured to invoke the operation instruction, and the executable instruction enables the processor to execute an operation corresponding to the service processing method shown in the first aspect of the application.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the program, when executed by a processor, implements the service processing method shown in the first aspect of the present application.

The beneficial effect that technical scheme that this application provided brought is:

acquiring a service processing request; the service processing request comprises face data of an object to be detected; when the face data meet preset detection conditions, matching the face data based on a preset temporary database; the temporary database comprises at least one piece of face data acquired and stored in a preset time period; if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data; and if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data. Therefore, the face retrieval is carried out based on the temporary database updated in real time, and when the retrieval fails, the face retrieval is carried out based on the complete data including all the face data, so that the final retrieval result is obtained. Compared with the mode of directly searching based on the permanent archive library in the prior art, the scale of the temporary database in the application can be greatly reduced, so that the searching efficiency and accuracy can be greatly improved, and the service processing efficiency and accuracy can be improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.

FIG. 1 is a system architecture diagram of the business process of the present application;

fig. 2 is a schematic flowchart of a service processing method according to an embodiment of the present application;

fig. 3 is a schematic flowchart of a service processing method according to another embodiment of the present application;

FIG. 4 is a schematic flow chart of the present application for searching a temporary database;

FIG. 5 is a schematic flow chart of the present application for retrieving a complete database;

FIG. 6 is a schematic view of the management process of the temporary database in the present application;

FIG. 7 is a graph of statistical effects applied to the new and old customer reminders of the present application;

fig. 8-1 is a schematic structural diagram of a service processing apparatus according to another embodiment of the present application;

fig. 8-2 is a schematic structural diagram of a service processing apparatus according to another embodiment of the present application;

fig. 9 is a schematic structural diagram of an electronic device for service processing according to yet another embodiment of the present application.

Detailed Description

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present invention.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

The terms referred to in this application will first be introduced and explained:

computer Vision technology (CV) Computer Vision is a science for researching how to make a machine "see", and further refers to that a camera and a Computer are used to replace human eyes to perform machine Vision such as identification, tracking and measurement on a target, and further image processing is performed, so that the Computer processing becomes an image more suitable for human eyes to observe or transmitted to an instrument to detect. As a scientific discipline, computer vision research-related theories and techniques attempt to build artificial intelligence systems that can capture information from images or multidimensional data. Computer vision technologies generally include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D technologies, virtual reality, augmented reality, synchronous positioning, map construction, and other technologies, and also include common biometric technologies such as face recognition and fingerprint recognition.

Based on the technology, the application can realize a business processing method which can be particularly used for business processing of face retrieval.

The face recognition refers to a process of extracting face features and comparing similarity. According to different application scenes, face recognition is mainly divided into 1: 1 Face Verification (Face Verification), 1: n Face Recognition (Face Recognition) and Face Retrieval (Face Retrieval). Wherein, 1: n-face retrieval refers to finding one or more faces with the highest similarity to the face to be retrieved in a large-scale face database. The retrieval performance is related to the size of the database.

Referring to fig. 1, a system architecture diagram of the present application is shown. The image acquisition equipment acquires face data through algorithm service, then inputs the face data into a message queue, face data is consumed from the message queue by face data preprocessing service, CV processing is carried out on the face data through CV micro service, including the steps of extracting face features of the face image in the face data, calculating quality scores of the face image, extracting user attributes, then caching the face data and the CV processed data into a Redis (remote dictionary service) cluster (namely a temporary database), and persisting the face data and the CV processed data into a Mysql cluster (namely a complete database).

The business processing service firstly filters the quality score of the face data based on the face image, then searches based on the temporary database, if the search is successful, generates a corresponding business processing result and feeds the business processing result back to the business requiring party, and updates the temporary database and the complete database based on the collected face data; if the retrieval is failed, the retrieval is carried out based on the complete database to obtain a corresponding retrieval result, different service processing results are generated based on different retrieval results and fed back to a service demand party, and then the temporary database and the complete database are updated based on the collected face data.

Furthermore, a temporary database management strategy is also arranged in the business processing service and used for updating the temporary database in real time, so that the scale and the size of the temporary database can be controlled and the timeliness of the data can be guaranteed.

The application can be applied to servers, the servers can be independent physical servers, server clusters or distributed systems formed by a plurality of physical servers, and cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (content delivery network), big data platforms, artificial intelligence platforms and the like. The server may perform data interaction with a terminal, and the terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

The application provides a service processing method, a service processing device, an electronic device and a computer-readable storage medium, which aim to solve the above technical problems in the prior art.

The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

In one embodiment, a service processing method is provided, as shown in fig. 2, the method includes:

step S201, acquiring a service processing request; the service processing request comprises face data of an object to be detected;

the service processing may be to remind the result of face retrieval. Such as personnel presence alerts, security alerts, sound bank detection, and the like. The person arrival reminding specifically includes that the shopping mall or the shop needs to remind the user entering the shopping mall or the shop, and may remind the user of being a new or old user or a VIP user, or remind the user of being a blacklist user (such as a thief), and the like. In practical application, the setting may be performed according to practical requirements, and the embodiment of the present invention is not limited to this.

Specifically, the business processing request may include face data of the object to be detected, that is, face data of the user entering the mall or the store. The face data of the user includes, but is not limited to, a running track of the user, a track ID, at least one level of face image of the user collected, a collection time of each face image, area information of the user, and the like.

The movement track may be a movement track of the user in each image capturing device. The track ID is an identifier of each motion track and is used for distinguishing different motion tracks, in practical application, the form of the track ID may be set according to actual requirements, and the track ID is applicable to the embodiment of the present invention as long as different motion tracks can be distinguished, and the embodiment of the present invention is not limited to this.

The area information of the user is used to characterize the user's location in the mall or store. Because more than one image acquisition device is arranged in a market or a shop, each image acquisition device is responsible for one area, so that the different image acquisition devices acquire the face data of the user, and the area information of the user can be determined.

Step S202, when the face data meet the preset detection conditions, matching the face data based on a preset temporary database; the temporary database comprises at least one face data acquired and stored in a preset time period;

before retrieval is carried out based on face data, whether the face data meet preset detection conditions or not can be judged, and whether the quality score of a face image in the face data exceeds a quality score threshold value or not is mainly judged, wherein the quality score of the face image can be calculated based on factors such as light, distance and definition; if not, the face image can be abandoned to be retrieved; if the number of face images exceeds the preset number of face images, the face images in the face data can be matched based on a preset temporary database. The temporary database stores face data of at least one user acquired by the image acquisition equipment, and the storage time of each face data in the temporary database cannot exceed a preset time threshold, namely, the face data are temporarily stored in the temporary database, so that the face data in the temporary database are updated in real time.

Step S203, if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data;

when the face data are successfully matched based on the temporary database, namely, the face image to be detected of the target is successfully matched with the target temporary sub-database, the fact that the user appears within a time period of a time threshold value is shown, the face data of the user are collected and stored in the temporary database, a first processing result of a service request can be generated at the moment, and the temporary database and a preset complete database are updated based on the currently collected face data; the complete database includes all the acquired and stored face data, that is, the face data in the temporary database is partial data in the complete database.

And step S204, if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data.

When the matching of the collected face data and the temporary database fails, specifically, the matching of the target face image to be detected in the face data and the target temporary sub-database fails, the face data can be matched based on the complete database to obtain a matching result of successful matching or failed matching, different second processing results corresponding to the service processing request are generated based on different matching results, and then the complete database is updated by adopting the face data.

In the embodiment of the invention, a service processing request is obtained; the service processing request comprises face data of an object to be detected; when the face data meet the preset detection conditions, matching the face data based on a preset temporary database; the temporary database comprises at least one face data acquired and stored in a preset time period; if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data; and if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data. Therefore, the face retrieval is carried out based on the temporary database updated in real time, and when the retrieval fails, the face retrieval is carried out based on the complete data including all the face data, so that the final retrieval result is obtained. Compared with the mode of directly searching based on the permanent archive library in the prior art, the scale of the temporary database in the application can be greatly reduced, so that the searching efficiency and accuracy can be greatly improved, and the service processing efficiency and accuracy can be improved.

In another embodiment, a service processing method is provided, as shown in fig. 3, the method includes:

step S301, acquiring a service processing request; the service processing request comprises face data of an object to be detected;

the service processing may be to remind the result of face retrieval. Such as personnel presence alerts, security alerts, sound bank detection, and the like. The person arrival reminding specifically includes that the shopping mall or the shop needs to remind the user entering the shopping mall or the shop, and may remind the user of being a new or old user or a VIP user, or remind the user of being a blacklist user (such as a thief), and the like. In practical application, the setting may be performed according to practical requirements, and the embodiment of the present invention is not limited to this. For convenience of description, the embodiment of the present invention will be described in detail by taking an example of reminding a user of a new user or an old user.

The movement track may be a movement track of the user in each image capturing device. For example, when a user appears in an image acquisition area of an image acquisition device at 20:08:35 and leaves the image acquisition area at 20:09:12, the image acquisition device can acquire the motion track of the user during 20:08:35 to 20:09:12 and generate a corresponding track ID. The track ID is an identifier of each motion track and is used for distinguishing different motion tracks, in practical application, the form of the track ID may be set according to actual requirements, and the track ID is applicable to the embodiment of the present invention as long as different motion tracks can be distinguished, and the embodiment of the present invention is not limited to this.

In practical applications, if there is a longer dwell trajectory in the motion trajectory, the dwell trajectory may be deleted from the motion trajectory. For example, when a user appears in an image acquisition area of an image acquisition device at 20:08:35, 20:08:50 is fixed in the image acquisition area, the user does not start to move until 20:15:47, and the user leaves the image acquisition area at 20:16:03, the time interval of the acquired motion trajectory is 20:08: 35-20: 16:03, the motion trajectory in the period of 20:08: 50-20: 15:47 can be deleted because the user is in a still state all the time, so that the time interval of the motion trajectory of the user is 20:08: 35-20: 08:50, 20:15: 47-20: 16:03, and then the corresponding trajectory ID is generated.

Step S302, when the face data meet the preset detection conditions, matching the face data based on a preset temporary database; the temporary database comprises at least one face data acquired and stored in a preset time period;

before retrieval is carried out based on the face data, whether the face data meet preset detection conditions or not can be judged, whether the quality score of a face image in the face data exceeds a quality score threshold value or not is mainly judged, and if the quality score does not exceed the quality score threshold value, the face image can be abandoned to be retrieved; if the number of face images exceeds the preset number of face images, the face images in the face data can be matched based on a preset temporary database. The temporary database stores face data of at least one user acquired by the image acquisition equipment, and the storage time of each face data in the temporary database cannot exceed a preset time threshold, namely, the face data are temporarily stored in the temporary database, so that the face data in the temporary database are updated in real time.

In a preferred embodiment of the present invention, the face data includes at least one acquired face image to be detected of the object to be detected;

the face data meets the preset detection conditions, including:

when the quality score of at least one face image exceeds a first quality score threshold value, judging that the face data meet a preset detection condition;

and acquiring each face image with the quality score exceeding a first quality score threshold, and taking the face image with the highest quality score as a target face image to be detected.

In practical application, CV processing may be performed on a face image in the acquired face data, including but not limited to extracting face features of the face image, calculating a quality score of the face image, extracting user attributes, and the like. The face features can be extracted based on face recognition, the quality score of the face image can be calculated based on factors such as light, distance and definition, and the user attributes include but are not limited to the age, sex, height and body type of the user. Then, the face data and the CV processed data are cached in a memory, for example, a Redis cluster may be set in the memory to store the face data and the processed data, and each data is sorted based on a trajectory ID and an acquisition time, for example: "trace 1-time 1", "trace 2-time 2", and so on.

Further, the service processing system can continuously read data from the Redis cluster and perform service processing. Specifically, since more than one image may be acquired by any image acquisition device when acquiring the face image of the user, it is necessary to calculate the quality score of each acquired face image, then compare the quality score of each face image with a first quality score threshold, and if the quality score of at least one face image exceeds the first quality score threshold, it may be determined that the face data meets a preset detection condition, and at the same time, all face images whose quality scores exceed the first quality score threshold are acquired, and then the face image with the highest quality score is determined from all face images as the target face image to be detected.

Certainly, in practical application, a face image with the highest quality score may be determined, the quality score of the face image is compared with a first quality score threshold, if the quality score of the face image exceeds the first quality score threshold, the face data is determined to meet a preset detection condition, and the face image is used as a target face image to be detected; if not, the flow ends. In practical applications, the setting may be performed according to practical requirements, and the embodiment of the present invention is not limited thereto.

In a preferred embodiment of the present invention, the service processing request further includes a service type; the temporary database comprises at least one temporary sub-library, and each temporary sub-library has a corresponding service type;

matching the face data based on a preset temporary database, comprising:

Because the embodiment of the invention can carry out face retrieval on the user entering a market or a store, and then determines that the user is a new user, an old user and the like, the service request processing also needs to include the service type besides the face data of the user, namely, a prompt corresponding to the service type is generated according to the retrieval result.

Therefore, in order to improve the retrieval efficiency, the embodiment of the present invention may set a plurality of temporary sub-libraries in the temporary database, where each temporary sub-library corresponds to one service type. For example, the reminders of the old and new customers correspond to the temporary sub-library of the old and new customers, the reminders of the blacklist customers correspond to the temporary sub-library of the blacklist, the reminders of the VIP customers correspond to the temporary sub-library of the VIP, and the like. Therefore, when face data are retrieved, a target temporary sub-library required to be used can be determined from each temporary sub-library based on the service type, then the target face image to be detected is matched in the target complete sub-library to obtain a matching result, and therefore retrieval efficiency is improved.

In a preferred embodiment of the present invention, each temporary sub-library includes at least one piece of first identification information, each piece of first identification information corresponds to one piece of face data, and each piece of face data includes at least one piece of first historical face image;

matching the face image to be detected in the target temporary sub-library, comprising:

matching the face features to be detected with each first identification face feature, taking the first identification face feature with the highest matching degree as a first target identification face feature, and taking first identification information corresponding to the first target identification face feature as target identification information;

The temporary databases are updated by the face data acquired by the image acquisition device and the data after CV processing on the face image, so that the first identification information in each temporary sub-database may also be a track ID, each track ID corresponds to one face data, each face data includes at least one historical face image, and the historical face image is a face image stored in the temporary sub-database after business processing on the face data acquired before. Of course, each track ID in the temporary sub-library corresponds to one face data, and also corresponds to data obtained by performing CV processing on the face image in the face data.

After the target temporary sub-library is determined, the target face image to be detected can be matched based on the target temporary sub-library.

Specifically, the face features of the target to be detected corresponding to the face image of the target to be detected are firstly obtained, and the acquired face image is subjected to CV processing before, so that the face features of the target to be detected can be directly obtained from the cache.

Then, the first identification face features corresponding to the first identification information are determined based on the first historical face images corresponding to the first identification information. Specifically, for any first identification information, historical face features corresponding to each historical face image are calculated, then historical face average features are calculated based on each historical face feature, and the historical face average features are used as first identification face features corresponding to the first identification information. For example, if a certain track ID in the target temporary sub-library includes 100 historical face images, then historical face features corresponding to the 100 historical face images are respectively calculated, then a historical face average feature is calculated based on the 100 historical face features, and the historical face average feature is used as an identification face feature corresponding to the track ID. And so on, thereby obtaining the first identification face features corresponding to each first identification information in the target temporary sub-library. Of course, in practical application, if the number of the historical face images is large, the average characteristic of the historical face may also be determined by a certain number of the historical face images, and the average characteristic may be set according to practical requirements in practical application, which is not limited in the embodiment of the present invention.

And matching the face features to be detected of the target with each first identification face feature, taking the first identification face feature with the highest matching degree as a first target identification face feature, and taking first identification information corresponding to the first target identification face feature as target identification information. For example, after the face features a to be detected by the target are matched with the first identification face features, the first identification face feature a with the highest matching degree is determined, then a is used as the first target identification face feature, and the track ID corresponding to a is used as the target identification information.

And then calculating to obtain the feature score of the first target identification face feature, and judging that the matching is successful when the feature score of the first target identification face feature exceeds a first feature score threshold value. That is to say, if the calculated feature score of the first target identification face feature exceeds the first feature score threshold, it can be determined that the matching is successful, that is, the target to-be-detected face feature and the first target identification face feature belong to the same identification information, and the object to be detected is a known object.

Further, when the feature score of the first target face recognition feature does not exceed a first feature score threshold value, judging that the matching fails;

and generating new identification information, establishing a corresponding relation between the target face image to be detected and the new identification information, and taking the new identification information as the target identification information.

And if the calculated feature score of the first target identification face feature does not exceed the first feature score threshold, judging that the matching fails, namely that the target to-be-detected face feature and the first target identification face feature temporarily do not belong to the same identification information. This is because the data in the temporary database is updated in real time, and the time for each face data to be stored in the temporary database cannot exceed the preset time threshold, so that the matched first target identification face features may be deleted from the temporary database.

For example, the time threshold set in the temporary database is 1 hour, the face data of a certain user 20:00:00 enters a mall is collected and stored in the temporary database, the user 20:50:00 leaves the mall, the face data of the user 21:00:00 is deleted from the temporary database, the face data of the user 21:01:00 enters the mall again, and the matching of the face data by the temporary database fails.

When the matching is judged to be failed, new identification information can be generated, the corresponding relation between the target face image to be detected and the new identification information is established, and the new identification information is used as the target identification information.

Step S303, if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data;

The generating of the first processing result of the service processing request includes:

Specifically, the generated first processing result may be whether the object to be detected belongs to the service type in the service request. For example, if the service request is a reminder for a senior client, the first processing result may be to generate a reminder that the user is a senior client and send the reminder to a requester of the service processing, such as a terminal in a shop.

Further, after the object to be detected is determined to be a known object, the temporary database and the complete database can be updated based on a preset strategy because the face data of the user is collected again currently.

In a preferred embodiment of the present invention, updating the temporary database and the complete database based on the face data includes:

the temporary database and the complete database are updated based on the quantity and the face data.

Specifically, whether the quality score of the target face image to be detected exceeds a second quality score threshold value is judged, if yes, target identification information corresponding to the target face image to be detected is determined, the number of all first historical face images corresponding to the target identification information is obtained, and different numbers correspond to different updating strategies; if not, the flow ends.

In a preferred embodiment of the present invention, updating the temporary database and the complete database based on the quantity and the face data comprises:

when the number is equal to 1, calculating to obtain the quality score of the first historical face image;

and if the quality score does not exceed the third quality score threshold, replacing the first historical face image in the temporary target sub-library with the target face image to be detected, and storing the target face image to be detected in the complete database.

Specifically, when the number of all first historical face images corresponding to the target identification information is equal to 1, calculating the quality score of the first historical face image, and if the quality score of the first historical face image does not exceed a third quality score threshold, replacing the first historical face image in the target temporary sub-library with the target face image to be detected, and storing the target face image to be detected in the complete database. That is, if there is only one historical face image of the user in the temporary target sub-library, and the quality score of the historical face image does not exceed the third score threshold, the currently acquired target face image to be detected is replaced by the historical face image in the temporary target sub-library, and the target face image to be detected is stored in the complete database.

if the quality scores exceed a third quality score threshold value, or the number of the quality scores is larger than 1, judging whether the scores of the target human face images to be detected exceed a fourth quality score threshold value;

Specifically, when the quality score of the historical face image in the target temporary sub-library exceeds a third score threshold, or the number of all first historical face images corresponding to the target identification information is greater than 1, whether the score of the target face image to be detected exceeds a fourth quality score threshold is further judged, if any one of the two conditions is met, the corresponding relation between the target face image to be detected and the target identification information is established, the currently acquired target face image to be detected is stored in the target temporary sub-library, and meanwhile, the target face image to be detected is stored in the complete database. That is, when only one historical face image of the user exists in the target temporary sub-library, and the quality score of the historical face image exceeds the third score threshold, or at least two historical face images of the user exist in the target temporary sub-library, whether the score of the currently acquired target image to be detected exceeds the fourth quality score threshold is further judged, if yes, the target image to be detected is stored in the target temporary sub-library to serve as the historical face image of the user, and meanwhile, the target detection image is stored in the complete database.

and when the number is equal to 0, storing the target face images to be detected to a target temporary sub-library, and storing the target face images to be detected to the complete database.

Specifically, new identification information is generated when matching fails, so that the new identification information is that no historical face image exists, that is, when the number of the first historical face images in the target temporary sub-library is equal to 0, the target face image to be detected is stored in the temporary database, so that the target face image to be detected is further retrieved through the complete database, and then the target face image to be detected is stored in the complete database according to a retrieval result.

Further, referring to fig. 4, a search process based on the temporary database in the present application is shown. For the specific searching step, reference may be made to step S303, which is not repeated herein.

Step S304, if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data;

Generating a second processing result corresponding to the service processing request based on the matching result, wherein the generating of the second processing result comprises:

Specifically, the generated second processing result may be whether the object to be detected belongs to the service type in the service request, and if the target face image to be detected is successfully matched with the complete database, the second processing result generates a processing result that the object to be detected is a known object in the service type; and if the matching of the target face image to be detected and the complete database fails, generating a processing result that the object to be detected is a new object in the service type. For example, if the service request is a reminder for an old or new customer, the second processing result may be to generate a reminder that the user is an old or new customer and send the reminder to the requester of the service processing, such as a terminal in a shop.

In a preferred embodiment of the present invention, the complete database comprises at least one complete sub-library, each complete sub-library having a corresponding service type;

and determining a target complete sub-library from each complete sub-library based on the service type, and matching the target face image to be detected in the target complete sub-library to obtain a matching result.

In order to improve the retrieval efficiency, the embodiment of the invention can set a plurality of complete sub-libraries in the complete database, and each complete sub-library corresponds to one service type. For example, the reminders of the old and new customers correspond to the complete sub-library of the old and new customers, the reminders of the blacklist customers correspond to the complete sub-library of the blacklist, the reminders of the VIP customers correspond to the complete sub-library of the VIP, and the like. Therefore, when face data are retrieved, a target complete sub-library required to be used can be determined from each complete sub-library based on the service type, then the target face image to be detected is matched in the target complete sub-library to obtain a matching result, and therefore retrieval efficiency is improved.

In a preferred embodiment of the present invention, each complete sub-library includes at least one piece of second identification information, and each piece of second identification information corresponds to at least one piece of second historical face image;

matching the face image to be detected of the target in the complete target sub-library, comprising the following steps:

and when the score of the second target human face recognition feature does not exceed the third feature score threshold value, judging that the matching fails.

In the embodiment of the present invention, the data stored in the temporary database is a part of the data stored in the complete database, so that the temporary database and the data stored in the complete database are in the same form, that is, the second identification information in each complete sub-database may also be a track ID, each track ID corresponds to one piece of face data, each piece of face data includes at least one historical face image, where the historical face image is a face image stored in the complete sub-database after performing service processing on the previously acquired face data. Certainly, each track ID in the complete sub-library corresponds to one piece of face data, and also corresponds to data obtained by performing CV processing on the face image in the face data.

After the target complete sub-library is determined, the target face image to be detected can be matched based on the target complete sub-library.

Specifically, new identification information and a target face image to be detected corresponding to the new identification information are obtained from a target temporary sub-library, and then second identification face features corresponding to each piece of second identification information are determined based on each second historical face image corresponding to each piece of second identification information in a target complete sub-library. Specifically, for any second identification information, the historical face features corresponding to each historical face image corresponding to the second identification information are calculated, then the historical face average features are calculated based on the historical face features, and the historical face average features are used as the second identification face features corresponding to the second identification information. And so on, thus obtaining the second identification face features corresponding to each second identification information in the target complete sub-library. Of course, in practical application, if the number of the historical face images is large, the average characteristic of the historical face may also be determined by a certain number of the historical face images, and the average characteristic may be set according to practical requirements in practical application, which is not limited in the embodiment of the present invention.

Calculating to obtain the feature score of the second target identification face feature, and judging that the matching is successful when the feature score of the second target identification face feature exceeds a second feature score threshold value; when the feature score of the second target identification face feature does not exceed a third feature score threshold value, judging that the matching fails; and when the feature score of the second target identification face feature is between the second feature score threshold and the third feature score threshold, ending the process. That is to say, if the calculated feature score of the second target identification face feature exceeds the second feature score threshold, it can be determined that the matching is successful, that is, the target to-be-detected face feature and the second target identification face feature belong to the same identification information, and the object to be detected is a known object; and if the calculated feature score of the second target identification face feature does not exceed a third feature score threshold value, judging that the matching fails, namely that the target to-be-detected face feature and the second target identification face feature do not belong to the same identification information, and the object to be detected is a new object.

Further, if the object to be detected is a known object, the face data of the object to be detected and the data after CV processing can be stored in a complete database, and a corresponding relationship between the face data and the identification information corresponding to the second target identification face feature is established; if the object to be detected is a new object, the new identification information, the corresponding face data and the data after CV processing can be stored in a complete database.

Further, referring to fig. 5, a complete database based search process is illustrated in the present application. For a specific search step, refer to step S304, which is not described herein.

Step S305, determining face data to be deleted from a temporary database based on the time information of each face data;

because the data in the temporary database needs to be updated continuously in real time, the face data to be deleted in the temporary database can be determined based on the time information of the face data. The time information of the face data may be the time of acquiring a face image in the face data or the generation time of the identification information.

Further, the face data to be deleted may be all face data corresponding to the identification information and CV-processed data, and the time information of the face data at this time may be the generation time of the identification information corresponding to the face data in the temporary database; or historical face images in the face data and CV processed data corresponding to the historical face images, and the time information of the face data at this time may be the acquisition time of each historical face image in the face data. In practical application, the setting may be performed according to practical requirements, and the embodiment of the present invention is not limited to this.

In a preferred embodiment of the present invention, determining the face data to be deleted from the temporary database based on the time information of each face data includes:

Specifically, when a temporary database is adopted for face retrieval triggered by a service processing request each time, after the face retrieval is completed, the stored time of each face data in the temporary database is determined based on the time information of each face data, and then at least one face data with the stored time exceeding a time threshold is used as data to be deleted.

Specifically, a certain amount of face data are randomly acquired from the temporary database at preset time intervals, the stored time of each face data in the temporary database is determined based on the acquired time information of each face data, and at least one face data with the stored time exceeding a time threshold is used as data to be deleted. For example, 100 pieces of face data are randomly acquired from the temporary database every hour, then the stored time of the 100 pieces of face data is determined, and the stored time of 52 pieces of face data is determined by comparison to exceed the time threshold, so that the 52 pieces of face data are to-be-deleted data.

It should be noted that before determining the face data to be deleted, if there are other service processing requests, then it is preferable to process other service processing requests, and after all the service processing requests are completely processed, the face data to be deleted can be determined.

And step S306, deleting the face data to be deleted from the temporary database.

After the face data to be deleted is determined, the face data to be deleted can be deleted from the temporary database.

Further, referring to fig. 6, an update process of the temporary database in the present application is shown. For the specific updating step, reference may be made to steps S305 to S306, which are not described herein again.

Further, when the embodiment of the present invention is applied to the reminding of the new and old customers, the daily statistical chart of the new and old customers can be as shown in fig. 7.

Furthermore, the temporary database is updated in real time through a preset updating strategy, so that the scale of the temporary database can be controlled, the data can be updated latest, the retrieval is carried out based on the latest data when the retrieval is carried out based on the temporary database, and the latest retrieval result is ensured; meanwhile, the scale of the temporary database is controllable, so that the temporary database does not occupy excessive hardware resources, and the consumption of the hardware resources is reduced.

Fig. 8-1 is a schematic structural diagram of a service processing apparatus according to another embodiment of the present application, and as shown in fig. 8-1, the apparatus of this embodiment may include:

an obtaining module 801, configured to obtain a service processing request; the service processing request comprises face data of an object to be detected;

the matching module 802 is configured to match the face data based on a preset temporary database when the face data meets a preset detection condition; the temporary database comprises at least one face data acquired and stored in a preset time period;

a first processing module 803, configured to generate a first processing result of the service processing request if matching is successful, and update the temporary database and the preset complete database based on the face data; the complete database comprises all acquired and stored face data;

the second processing module 804 is configured to, if the matching fails, match the face data based on the complete database to obtain a matching result, generate a second processing result corresponding to the service processing request based on the matching result, and update the complete database based on the face data.

the device further comprises a detection module, which is specifically used for:

calculating to obtain quality scores of all the face images to be detected, and comparing all the quality scores with a first quality score threshold value; when the quality score of at least one face image exceeds a first quality score threshold value, judging that the face data meet a preset detection condition; and acquiring each face image with the quality score exceeding a first quality score threshold, and taking the face image with the highest quality score as a target face image to be detected.

the matching module is specifically configured to:

a matching module comprising:

the first matching submodule is used for matching the target face features to be detected with each first identification face feature, taking the first identification face feature with the highest matching degree as a first target identification face feature, and taking first identification information corresponding to the first target identification face feature as target identification information;

the first calculation submodule is used for calculating and obtaining a feature score of the first target identification face feature;

In a preferred embodiment of the present invention, the matching module further comprises:

the first judgment sub-module is further used for judging that the matching fails when the feature score of the first target face identification feature does not exceed a first feature score threshold value;

and the generation submodule is used for generating new identification information, establishing a corresponding relation between the target to-be-detected face image and the new identification information, and taking the new identification information as the target identification information.

In a preferred embodiment of the present invention, the first processing module includes:

and the updating submodule is used for updating the temporary database and the complete database based on the quantity and the face data.

In a preferred embodiment of the present invention, the update submodule is specifically configured to:

when the number is equal to 1, calculating to obtain the quality score of the first historical face image; and if the quality score does not exceed the third quality score threshold, replacing the first historical face image in the temporary target sub-library with the target face image to be detected, and storing the target face image to be detected in the complete database.

if the quality scores exceed a third quality score threshold value, or the number of the quality scores is larger than 1, judging whether the scores of the target human face images to be detected exceed a fourth quality score threshold value; if so, establishing a corresponding relation between the target face image to be detected and the target identification information, storing the target face image to be detected to a target temporary sub-library, and storing the target face image to be detected to the complete database.

the second processing module is specifically configured to:

the second processing module comprises:

the second matching submodule is used for matching the target face features to be detected with each second identification face feature and taking the second identification face feature with the highest matching degree as a second target identification face feature;

the second judging submodule is used for judging that the matching is successful when the feature score of the second target identification face feature exceeds a second feature score threshold value; and when the score of the second target human face recognition feature does not exceed the third feature score threshold value, judging that the matching fails.

In a preferred embodiment of the present invention, the first processing module is specifically configured to:

In a preferred embodiment of the present invention, the second processing module is specifically configured to:

In a preferred embodiment of the present invention, each face data has time information;

as shown in fig. 8-2, the apparatus further comprises:

a determining module 805, configured to determine face data to be deleted from the temporary database based on time information of each piece of face data;

and a deleting module 806, configured to delete the face data to be deleted from the temporary database.

In a preferred embodiment of the present invention, the determining module includes:

The service processing apparatus of this embodiment can execute the service processing methods shown in the first embodiment and the second embodiment of this application, and the implementation principles thereof are similar, and are not described herein again.

In another embodiment of the present application, there is provided an electronic device including: a memory and a processor; at least one program, stored in the memory, for being executed by the processor, which is capable of implementing obtaining a service processing request compared to the prior art; the service processing request comprises face data of an object to be detected; when the face data meet the preset detection conditions, matching the face data based on a preset temporary database; the temporary database comprises at least one face data acquired and stored in a preset time period; if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data; and if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data. Therefore, the face retrieval is carried out based on the temporary database updated in real time, and when the retrieval fails, the face retrieval is carried out based on the complete data including all the face data, so that the final retrieval result is obtained. Compared with the mode of directly searching based on the permanent archive library in the prior art, the scale of the temporary database in the application can be greatly reduced, so that the searching efficiency and accuracy can be greatly improved, and the service processing efficiency and accuracy can be improved.

In an alternative embodiment, an electronic device is provided, as shown in fig. 9, an electronic device 9000 shown in fig. 9 comprising: a processor 9001 and a memory 9003. Among other things, the processor 9001 and memory 9003 are coupled, such as via a bus 9002. Optionally, the electronic device 9000 can also include a transceiver 9004. Note that the transceiver 9004 is not limited to one in practical use, and the structure of the electronic device 9000 is not limited to the embodiment of the present application.

The processor 9001 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 9001 may also be a combination of computing functions, e.g., comprising one or more microprocessors, a combination of DSPs and microprocessors, or the like.

The bus 9002 may include a pathway to transfer information between the aforementioned components. The bus 9002 may be a PCI bus or an EISA bus, etc. The bus 9002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 9, but this does not indicate only one bus or one type of bus.

The memory 9003 may be a ROM or other type of static storage device that may store static information and instructions, a RAM or other type of dynamic storage device that may store information and instructions, an EEPROM, a CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to.

The memory 9003 is used to store application code for performing aspects of the present application and is controlled by the processor 9001 for execution. The processor 9001 is configured to execute application program code stored in the memory 9003 to implement any of the method embodiments shown above.

Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like.

Yet another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when run on a computer, enables the computer to perform the corresponding content in the aforementioned method embodiments. Compared with the prior art, the method comprises the steps of obtaining a service processing request; the service processing request comprises face data of an object to be detected; when the face data meet the preset detection conditions, matching the face data based on a preset temporary database; the temporary database comprises at least one face data acquired and stored in a preset time period; if the matching is successful, generating a first processing result of the service processing request, and updating the temporary database and a preset complete database based on the face data; the complete database comprises all acquired and stored face data; and if the matching fails, matching the face data based on the complete database to obtain a matching result, generating a second processing result corresponding to the service processing request based on the matching result, and updating the complete database based on the face data. Therefore, the face retrieval is carried out based on the temporary database updated in real time, and when the retrieval fails, the face retrieval is carried out based on the complete data including all the face data, so that the final retrieval result is obtained. Compared with the mode of directly searching based on the permanent archive library in the prior art, the scale of the temporary database in the application can be greatly reduced, so that the searching efficiency and accuracy can be greatly improved, and the service processing efficiency and accuracy can be improved.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A method for processing a service, comprising:

2. The business processing method according to claim 1, wherein the face data includes at least one acquired face image to be detected of the object to be detected;

3. The traffic processing method according to claim 1 or 2, wherein the traffic processing request further includes a traffic type; the temporary database comprises at least one temporary sub-library, and each temporary sub-library has a corresponding service type;

4. The business processing method of claim 3, wherein each temporary sub-repository comprises at least one piece of first identification information, each piece of first identification information corresponds to one piece of face data, and each piece of face data comprises at least one piece of first historical face image;

5. The traffic processing method according to claim 4, further comprising:

6. The business processing method of claim 1 or 5, wherein updating the temporary database and the complete database based on the face data comprises:

7. The business processing method of claim 6, wherein said updating the temporary database and the complete database based on the quantity and the face data comprises:

8. The business processing method of claim 6, wherein said updating the temporary database and the complete database based on the quantity and the face data comprises:

9. The business processing method of claim 6, wherein said updating the temporary database and the complete database based on the quantity and the face data comprises:

10. The transaction processing method of claim 1, wherein the complete database comprises at least one complete sub-repository, each complete sub-repository having a corresponding transaction type;

11. The business processing method of any one of claims 6 to 10, wherein each complete sub-library comprises at least one piece of second identification information, each piece of second identification information corresponding to at least one piece of second historical face image;

12. The business processing method of claim 1, wherein each face data has time information;

the method further comprises the following steps:

and deleting the face data to be deleted from the temporary database.

13. A traffic processing apparatus, comprising:

14. An electronic device, comprising:

a processor, a memory, and a bus;

the bus is used for connecting the processor and the memory;

the memory is used for storing operation instructions;

the processor is configured to execute the service processing method according to any one of claims 1 to 12 by calling the operation instruction.

15. A computer-readable storage medium for storing computer instructions which, when executed on a computer, cause the computer to perform the business process method of any one of claims 1-12.