WO2020186701A1

WO2020186701A1 - User location lookup method and apparatus, device and medium

Info

Publication number: WO2020186701A1
Application number: PCT/CN2019/103921
Authority: WO
Inventors: 杨尊程
Original assignee: 百度在线网络技术（北京）有限公司
Priority date: 2019-03-20
Filing date: 2019-09-02
Publication date: 2020-09-24
Also published as: CN109819400B; CN109819400A

Abstract

A user location lookup method and apparatus, a device and a medium. The method comprises: updating, according to a scene image captured by a camera in a target area in real time, a user location record table corresponding to the target area in real time, wherein the user location record table comprises user identification information and a user positioning result corresponding to the user identification information; obtaining a user location lookup request corresponding to the target area, and searching in the user location recording table according to lookup user identification information included in the user location lookup request; and generating a lookup feedback result according to the search result for the lookup user identification information. By means of the technical solution above, a user can quickly, efficiently and conveniently find positioning information of other users needing to be found in a fixed area (such as a closed area), and then can directly find other users according to the found positioning information; therefore, the finding efficiency is significantly improved, and the problem of low finding efficiency by human eyes is solved.

Description

Method, device, equipment and medium for searching user location

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office with application number 201910213278.X on March 20, 2019, and the entire content of this application is incorporated into this application by reference.

Technical field

The embodiments of the present application relate to the field of image processing technology, for example, to a method, device, device, and medium for finding the location of a user.

Background technique

Traveling in groups, whether it is to eat in the cafeteria or to visit indoor attractions, is the choice of most people, but when the venue is large and the number of people is large, the people traveling together are easy to be washed away.

For example, when going to a cafeteria with colleagues and friends for dinner, they will usually purchase meals separately. After the meal is selected, I hope to sit at the same table with my friends. If the cafeteria is larger, the number of people is large, and the table is also If there are more, it is not easy to find where other friends are, especially when you can’t communicate with your friends (not carrying a mobile phone or the environment is noisy and the other party does not hear the call, etc.), you can only rely on human eyes to observe and find People. However, the efficiency of human eyes to find people is very low, and there is still the possibility of not being found, which seriously affects the mood of users.

Summary of the invention

The following is an overview of the topics detailed in this article. This summary is not intended to limit the scope of protection of the claims.

The embodiments of the present application provide a method, device, device, and medium for finding a user's location, so as to improve the efficiency of a user in finding other companions in a fixed area, and solve the problem of low efficiency of human eyes in finding a companion.

In the first aspect, an embodiment of the present application provides a method for finding a user location, including:

According to the scene image captured by at least one camera in the target area in real time, the user location record table corresponding to the target area is updated in real time, wherein a record in the user location record table includes: user identification information and user identification information The user positioning result corresponding to the identification information;

Acquiring a user location search request corresponding to the target area, and searching in the user location record table according to the search user identification information included in the user location search request;

According to the search result of the search user identification information, a search feedback result that matches the user search request is generated.

In the second aspect, an embodiment of the present application also provides an apparatus for finding a user location, including:

The user location record table real-time update module is used to update the user location record table corresponding to the target area in real time according to the scene image captured by at least one camera in the target area, wherein one record in the user location record table includes : User identification information, and user positioning results corresponding to the user identification information;

The user location search module is configured to obtain a user location search request corresponding to the target area, and search in the user location record table according to the search user identification information included in the user location search request;

The search feedback result generation module is configured to generate a search feedback result that matches the user search request according to the search result of the search user identification information.

In the third aspect, the embodiments of the present application also provide a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, the implementation is as follows: The method for finding the location of the user described in any embodiment.

In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for searching the user location as described in any embodiment of the present application is implemented.

The method, device, device, and medium for searching the user location provided by the embodiments of the present application update the user location record table corresponding to the target area in real time according to the scene image captured by at least one camera in the target area in real time. The user location record table The location result of the user in the target area in the record. When a user location search request corresponding to the target area is received, the user location record table is searched for the user identification information included in the user location search request, and the search result is generated. The feedback result of the user location search request. Through the above technical solutions, users can quickly, efficiently and conveniently query the location information of other users that need to be found in a fixed area (typically closed area), and then can directly find people based on the queried location information. Significantly improves the efficiency of finding people, and solves the problem of low efficiency in finding people.

After reading and understanding the drawings and detailed description, other aspects can be understood.

Description of the drawings

Fig. 1 is a flowchart of a method for finding a user location in Embodiment 1 of the present application;

2 is a flowchart of a method for finding a user location in Embodiment 2 of the present application;

FIG. 3 is a flowchart of a method for finding the location of a user in Embodiment 3 of the present application;

FIG. 4 is a schematic structural diagram of an apparatus for finding a user location in Embodiment 4 of the present application;

FIG. 5 is a schematic structural diagram of a computer device in Embodiment 5 of the present application.

detailed description

The application will be further described in detail below with reference to the drawings and embodiments. It is understandable that the specific embodiments described here are only used to explain the application, but not to limit the application. In addition, it should be noted that, for ease of description, the drawings only show a part of the structure related to the present application instead of all of the structure.

Example one

FIG. 1 is a flowchart of a method for finding a user's location provided by this embodiment, which is applicable to a situation where a user wants to find a companion after leaving a companion at a target location. This method can be determined by the user's location provided by the embodiment of this application. The search device is executed, and the device can be implemented by software and/or hardware. As shown in Fig. 1, the method of this embodiment specifically includes:

S110. According to the scene image captured by at least one camera in the target area in real time, update the user location record table corresponding to the target area in real time, wherein a record in the user location record table includes: user identification information and information related to the user The user positioning result corresponding to the identification information.

The target area refers to the fixed area where the user wants to find companions or other users. It can be an indoor area or an outdoor area. Generally, the fixed area has a large area and is not convenient for tracing people, such as large scenic spots, exhibition halls, restaurants, etc., where at least one camera is installed in the fixed area to take pictures of people in the target area. Scene image. When a person is within the shooting range of the camera, the scene image shot by the camera includes the image of the person. For example, when the target area is a rectangular indoor area such as a canteen, cameras (typically, high-definition cameras) may be installed only at the entrance and exit of the target area and the four corners of the target area to capture scene images in the target area.

The user location record table records the location information of people who are located in the target area and can be captured by the camera, and the location information of the people recorded in the user location record table is updated based on the scene image captured by the camera in real time, that is, As the person moves in the target area, the real-time captured scene image captured by the camera is also different, and the location information of the person determined according to the real-time captured scene image captured by the camera also changes.

It is worth pointing out that since the cameras in the target area are fixedly installed, each area in the scene image captured by each camera corresponds to an actual area in the target area. According to the area of the human image in the scene image The location can determine the actual location of the person in the target area. Specifically, the determined actual area location of the search user in the target area may be area location information of the reference object in the scene image, or related information of the reference object, such as number information.

Among them, each piece of record information in the user location record table includes user identification information and a user positioning result corresponding to the user identification information, that is, the user identification information and the user positioning result appear in pairs.

In one embodiment, the user identification information in the user location record table may be a face image and/or user identification information, wherein the correspondence between the face image and the user identification information is determined by a pre-established standard user library .

User identification information is the unique identification information used to identify the user. User identification information can be user identification information, such as an ID number. Typically, taking the target area as a company’s special place as an example, people who go to this target area If they are all employees of the company, the user identification information can be the employee ID; the user identification information can also be the user’s face image, which can be the standard face image of the user stored in the standard user library, or It is a face image captured in the scene image captured by the camera in real time; the user identification information can also be a combination of user identification information and the corresponding face image.

The camera in the target area captures the scene image in real time. For example, it captures a scene image every 5 seconds. The position of the image of the person in the scene image may or may not change. When the camera captures the image of the person in the scene image in real time When the position of the person changes, for example, the image of a person in the scene image is moving, or an image of a new person enters the scene image, and the person is at the target according to the real-time location of the person’s image in the scene image After the actual area location within the area, the user location result recorded in the target record in the user location record table is updated in real time, so that the user location result recorded in the user location record table is always determined based on the latest captured scene image. When the position of the person's image in the scene image captured by the camera in real time has not changed, the user location record table will be updated in real time based on the scene image, but the corresponding target record in the user location record table has not changed.

S120: Obtain a user location search request corresponding to the target area, and search in the user location record table according to the search user identification information included in the user location search request.

When the user has a user location search request to find other user location information within the target area, the user location search request including the search user identification information is sent, where the search user identification information may be a user's face image, such as stored in a mobile phone It includes looking up the photo of the user's face image, and it can also be user identification information, such as looking up the user's ID number, or looking up the user's employee ID (for the case where the user is a colleague).

For example, a mobile phone APP (Application, application program) can be developed according to the user location search method provided in this embodiment. When the user has a user location search request to find other user location information within the target area, the user in the mobile phone APP After the location information query portal enters the user location search request, it waits for the search feedback result returned by the mobile APP.

It is worth pointing out that the mobile APP can correspond to only one target area or multiple target areas. When corresponding to multiple target areas, the user needs to select the target area range that needs to be queried before entering the user location search request.

When the system receives a user location search request within the target area initiated by the user, it analyzes the search user identification information included in the user location search request, and then searches in the user location record table, whether the user location record table includes the search user identification The target record of the information. If the search user identification information included in the user location search request is user identification information, search for the user identification information of the user in the user location record table; if the search user identification information included in the user location search request is the user's face image, Then search for the user's face image of the user in the user location record table.

S130. Generate a search feedback result that matches the user's search request according to the search result of searching for user identification information.

If the user identification information is searched in the user location record table, a search feedback result that matches the user search request is generated according to the user location result recorded in the user location record table corresponding to the search user identification information; if the user location record table is If the user identification information is not found in the search, the user location cannot be found as the search feedback result matching the user search request.

When the user identification information can be searched in the user location record table, the target record corresponding to the search user identification information in the user location record table is obtained, and the user location result in the target record is used as the search feedback result for feedback; When the user identification information cannot be searched in the user location record table, the user location result of the search user cannot be returned, and only feedback results such as "user location cannot be found" can be fed back. In this case, it may be the search The user is not in the target area, or each camera failed to successfully capture the image of the searching user, especially the face image.

In the embodiment of the present application, the user location record table corresponding to the target area is updated in real time according to the scene image captured by at least one camera in the target area. The user location record table records the location result of the user in the target area. When the user location search request corresponding to the target area is reached, the user location record table is searched for the user identification information included in the user location search request, and a feedback result of the user location search request is generated according to the search result. Through the above technical solutions, users can quickly, efficiently and conveniently query the location information of other users that they need to find in a fixed area (such as a closed area), and then can directly find people based on the queried location information. Obviously Improve the efficiency of finding people, and solve the problem of low efficiency in finding people.

On the basis of the above technical solution, according to the scene image captured by at least one camera in the target area in real time, when the user location record table corresponding to the target area is updated in real time, the following operations can also be performed: The scene image captured by at least one camera in the target area in real time does not update the target record in the user location record table, then the target record is deleted.

When the target record in the user location record table exceeds the set time period (for example, two hours, which can be specifically set according to the actual situation) and is not updated, the target record is deleted. According to the scene image captured by each camera in real time, within the set time period, the target record in the user location record table was not updated, indicating that each camera in the target area failed to capture within this time period The image of the user corresponding to the target record, especially the face image, can be considered that the user has left the target area, and there is no need to record the user's location information. After reducing the number of records in the user location record table, It can also improve the efficiency of searching for other user identification information and reduce search time. Even if the user does not leave the target area, only the blind spot of each camera cannot be captured by any camera, deleting the target record will not have an impact. First, the positioning information in the target record is not accurate, and secondly, as long as the user Walk around again, the camera will capture the image of the user, update the user location record table, and re-add the location information record corresponding to the user.

In an embodiment, each record in the user location record table not only includes user identification information and user positioning results corresponding to the user identification information, but also includes the update time corresponding to the user positioning results, and further, according to the search for users The search feedback result matching the user search request generated by the search result of the identification information may also include the update time corresponding to the user positioning result.

For example, it is also possible to delete the target record after the update time in the target record in the user location record table differs from the current time by more than a set time period. At this point, it shows that no camera can capture the image of the user corresponding to the target record. It can be considered that the user has left the target area, or that the user has not left the target area, but the position cannot be obtained in the blind corner of each camera information.

Example two

FIG. 2 is a flowchart of a method for finding the location of a user provided in the second embodiment of the present application. This embodiment is embodied on the basis of the above-mentioned embodiment, in which, according to the scene image captured by at least one camera in the target area in real time, Update the user location record table corresponding to the target area in real time, specifically:

Input the scene image captured by at least one camera in the target area in real time into the pre-trained head recognition model, and obtain the head image output by the head recognition model and the user positioning result corresponding to the head image;

According to the image position of the human head image in the scene image, determine the human face image in the scene image, and the human face image is associated with the human head image;

According to the determined face image and the user positioning result corresponding to the face image, the user location record table corresponding to the target area is updated in real time.

As shown in Figure 2, the method of this embodiment may specifically include:

S210. Input the scene image captured by at least one camera in the target area in real time into a pre-trained head recognition model, and obtain a head image output by the head recognition model and a user positioning result corresponding to the head image.

The input of the human head recognition model is the scene image captured by the camera in real time, and the output is each human head image in the scene image, and the user positioning result corresponding to each human head image, where the user positioning result is based on the human head image in the scene image The coordinate position is determined, that is, there is a special correspondence between the user positioning result and the coordinate position of the human head image in the scene image. The coordinate position of the human head image in the scene image is determined, and the user corresponding to the human head image is also determined Positioning results.

In an embodiment, the user positioning result may be regional location information of the reference object in the scene image, or related information of the reference object, such as number information.

Among them, the training method of the head recognition model is as follows:

1) Obtain a sample scene image, each head image in the sample scene image, and a user positioning result corresponding to each head image in the sample scene image.

2) The sample scene image, each human head image in the sample scene image, and the user positioning result corresponding to each human head image in the sample scene image are corresponded as a set of training samples.

3) A large number of training samples are used to train standard recognition models (such as original machine learning models) to generate a head recognition model.

Furthermore, by inputting the scene image captured by the camera in real time into the human head recognition model, each human head image corresponding to the scene image and the user positioning result corresponding to each human head image can be obtained.

S220: Determine a face image in the scene image according to the image position of the head image in the scene image, where the face image is associated with the head image.

The image position of the human head image in the scene image, such as the coordinate position, can also be obtained by the human head recognition model. It is only necessary to add the image position information of the human head image in the scene image to the training sample when training the human head recognition module.

After determining the image position of the human head image in the scene image, the facial image is recognized by face recognition technology at the image position, and the recognized facial image is associated with the human head image at the image position to know Which user the head image is.

In an embodiment, S220 may be specifically: acquiring a human head image sequentially as the first target processing image;

In the scene image corresponding to the first target processed image, determine the candidate face search area according to the image position of the first target processed image;

If it is determined that the face image is recognized in the candidate face search area, then the face image is associated with the first target processed image;

Return to the operation of sequentially acquiring a human head image and processing the image as the first target until the processing of all human head images is completed.

In the scene image captured by the camera in real time, each head image recognized by the head recognition model is analyzed in turn. After obtaining a head image, in the scene image corresponding to the head image, according to the image position of the head image ( For example, the coordinate position) to determine the candidate face search area. If the face image can be recognized in the candidate face search area according to the face recognition technology, then the recognized face image is associated with the head image. That is, the head image is the user corresponding to the face image. If the face image cannot be recognized in the candidate face search area according to the face recognition technology, the next head image is obtained for analysis.

Among them, the candidate face search area is the area next to the image position of the human head image. The specific area size can be set according to actual diligence, for example, the candidate person determined according to the position of the larger human head image in the scene image taken by the camera The range of the face search area is larger, and the range of the candidate face search area determined according to the smaller the position of the head image in the scene image taken by the camera is smaller.

In an embodiment, S220 may also be specifically: acquiring a human head image sequentially as the first target processing image;

If it is determined that the pre-trained face recognition model is called to recognize the face image in the candidate face search area, then the face image is associated with the first target processed image;

In the above-mentioned embodiment, specifically, the pre-trained face recognition model is called to perform face recognition in the candidate face search area, where the face recognized by the face recognition model can be a positive face or a certain The profile of the deflection angle.

In this step, all the head images recognized by the head recognition model are analyzed to obtain the head image that can be successfully associated with the face image, and then the user positioning result corresponding to the head image is determined to correspond to the associated face image User positioning results.

S230: According to the determined face image and the user positioning result corresponding to the face image, update the user location record table corresponding to the target area in real time.

Wherein, a record in the user location record table includes: user identification information and a user positioning result corresponding to the user identification information.

After identifying a face image, the user identification information corresponding to the face image can be determined according to the correspondence between the face image recorded in the standard user library and the user identification information, and then the user identification information can be obtained. The face image and/or user identification information of the user, and a set of data of the user positioning result, and then the user location record table can be updated in real time based on this set of data.

In an embodiment, S230 may be specifically:

Sequentially acquiring a determined face image as the second target processing image;

Judging whether the user location record table stores a target record including the second target processed image, or user identification information corresponding to the second target processed image;

If yes, update the target record according to the second target processed image and the user positioning result corresponding to the second target processed image;

If not, a new record is created and added to the user location record table according to the second target processed image and the user positioning result corresponding to the second target processed image.

When using the user's face image and/or user identification information, and the user location result to update the user location record table, first determine whether the face image or user identification information exists in the user location record table, and if there is a matching target Record, the user positioning result corresponding to the face image can be used to update the user positioning result in the target record. If there is no matching record, the face image and/or user identification information (specifically based on the user location The form of the user identification information in the record table is specifically set), and the corresponding user location result is added to the user location record as a set of new records.

S240. Obtain a user location search request corresponding to the target area, and search in the user location record table according to the search user identification information included in the user location search request.

S250: Generate a search feedback result that matches the user's search request according to the search result of searching for user identification information.

For the parts that are not explained in detail in this embodiment, please refer to the foregoing embodiment, which will not be repeated here.

In the above technical solution, the human head image in the scene image captured by the camera in real time is first recognized, then the face recognition is performed near the position of the human head image, and the recognized face image is bound with the human head image, and then according to the face The image recognizes which user the corresponding head image is, and then the user location record table can be updated in real time according to the recognized user identification information and the user positioning information corresponding to the head image, so that when the user has a user search request, Search in the user location record table that is updated in real time, and quickly and accurately generate feedback results, so that when users receive feedback results that contain user location information, they can quickly, conveniently and accurately find the corresponding user. At the same time, compared to the data processing speed of face image recognition directly in the scene image, the data processing speed of the face image recognition first in the scene image and then the face image recognition near the head image is obviously faster. , Further improve the real-time update speed of the user location record table.

Example three

FIG. 3 is a flowchart of a method for finding the location of a user according to Embodiment 3 of the present application. This embodiment provides a specific implementation manner, where the target area is a dining hall, and the user positioning result is the number of the user's nearest neighbor table information.

As shown in FIG. 3, the method of this embodiment may specifically include:

S310. Input the scene image captured by at least one camera in the canteen in real time into the pre-trained head recognition model, and obtain the head image output by the head recognition model and the image position of the head image in the scene image.

For example, cameras can be installed only at the entrance and exit of the canteen and on the four corners of the canteen to capture images of all users in the canteen, thereby reducing the hardware cost of this embodiment.

S320: Determine the number information of the nearest dining table corresponding to the human head image according to the image position of the human head image in the scene image.

After determining the image position of the human head image in the scene image, for example, the coordinate information of the human head image is determined, the table recognition is performed near the image position, and the position information of the recognized multiple dining tables is compared with the position information of the human head image. Further determine the table image closest to the head image, and then perform character recognition on the number information included in the table image. As a result, this is the closest neighbor to the head image, which is the number of the table closest to the user The information is used as the user positioning result corresponding to the head image.

S330: Determine a face image in the scene image according to the image position of the head image in the scene image, where the face image is associated with the head image.

S340. According to the determined face image and the number information of the nearest neighbor dining table corresponding to the face image, update the user location record table corresponding to the canteen in real time.

A record in the user location record table includes: user identification information and the number information of the nearest neighbor dining table corresponding to the user identification information.

Since the face image and the head image are related, the number information of the nearest neighbor dining table corresponding to the face image is the number information of the nearest neighbor dining table corresponding to the face image.

Determine whether the face image or the user identification information corresponding to the face image exists in the user location record table. If there is a matching target record, you can use the number information of the nearest neighbor dining table corresponding to the face image to the target record The number information of the nearest neighbor dining table is updated. If there is no matching record, the face image and/or user identification information (specifically can be set according to the form of user identification information in the user location record table), and The number information of the corresponding nearest neighbor dining table is added to the user location record as a set of new records.

S350. Obtain a user location search request corresponding to the canteen, and search in the user location record table according to the search user identification information included in the user location search request.

S360. Generate a search feedback result that matches the user's search request according to the search result of searching for user identification information.

If the user identification information is found in the user location record table, a search feedback result that matches the user's search request is generated according to the number information of the nearest neighbor dining table recorded in the user location record table corresponding to the search user identification information, for example The XX user is located near the xx table.

If the user identification information is not found in the user location record table, the user location cannot be found as a search feedback result matching the user search request, for example, the location information of the XX user is not found.

The above technical solution enables users to find people in the canteen quickly, efficiently and conveniently, and solves the problem of wasting time in finding people. Even if the canteen is large, people can be found quickly. Moreover, only cameras need to be installed at the entrance and exit of the canteen and at the four corners, which reduces the cost.

Example four

Figure 4 is a schematic structural diagram of a user location search device provided by this embodiment, which can be applied to a situation where a user wants to find a companion after leaving a companion at a target place. The device can be implemented by software and/or hardware. , And generally can be integrated in a computer device, such as a computer device that establishes a communication connection with multiple cameras in the target location. As shown in Figure 4, the device specifically includes:

The user location record table real-time update module 410 is configured to update the user location record table corresponding to the target area in real time according to the scene image captured by at least one camera in the target area in real time, wherein one record in the user location record table Including: user identification information and user positioning results corresponding to the user identification information;

The user location search module 420 is configured to obtain a user location search request corresponding to the target area, and search in the user location record table according to the search user identification information included in the user location search request;

The search feedback result generation module 430 is configured to generate a search feedback result matching the user search request according to the search result of the search user identification information.

In the embodiment of the present application, the user location record table corresponding to the target area is updated in real time according to the scene image captured by at least one camera in the target area. The user location record table records the location result of the user in the target area. When the user location search request corresponding to the target area is reached, the user location record table is searched for the user identification information included in the user location search request, and a feedback result of the user location search request is generated according to the search result. Through the above technical solutions, users can quickly, efficiently and conveniently query the location information of other users that need to be found in a fixed area (typically closed area), and then can directly find people based on the queried location information. Significantly improves the efficiency of finding people, and solves the problem of low efficiency in finding people.

In an embodiment, the user location record table real-time update module 410 includes: a head recognition unit, a head and face association unit, and a user location record table update unit, where

A human head recognition unit configured to input scene images captured by at least one camera in the target area in real time into a pre-trained human head recognition model, and obtain a human head image output by the human head recognition model and a user corresponding to the human head image Positioning result

A human head and human face associating unit configured to determine a human face image in the scene image according to the image position of the human head image in the scene image, and the human face image is associated with the human head image;

The user location record table update unit is configured to update the user location record table corresponding to the target area in real time according to the determined face image and the user positioning result corresponding to the face image.

In an embodiment, the head and face association unit specifically includes: a head image acquisition subunit, a candidate face search area determination subunit, a head and face association subunit, and a first loop processing subunit, wherein,

The human head image acquisition sub-unit is set to acquire one human head image in turn, and process the image as the first target;

A candidate face search area determination subunit, configured to determine the candidate face search area in the scene image corresponding to the first target processed image according to the image position of the first target processed image;

The human head and human face association subunit is configured to associate the human face image with the first target processed image if it is determined that a human face image is recognized in the candidate face search area;

The first loop processing sub-unit is set to return to perform the operation of sequentially acquiring a human head image and processing the image as the first target until the processing of all human head images is completed.

In an embodiment, the head and face association subunit is configured to: if a pre-trained face recognition model is called to recognize a face image in the candidate face search area, then the face image will be combined with the first face image. A target handles image association.

In an embodiment, the user identification information in the user location record table includes: a face image, and/or user identification information; wherein the correspondence between the face image and the user identification information is pre-established The standard user library is determined.

In an embodiment, the user location record table update unit specifically includes:

The face image acquisition subunit is set to sequentially acquire a determined face image as the second target processed image;

The user location record table update subunit is configured to determine whether the user location record table stores a target record including the second target processed image, or user identification information corresponding to the second target processed image; if so, Update the target record according to the second target processed image and the user positioning result corresponding to the second target processed image; if not, update the target record according to the second target processed image and the second target processed image The corresponding user location result creates a new record and adds it to the user location record table.

In an embodiment, the user location record table real-time update module 410 further includes: a record deletion unit configured to: if the user location record table is not recorded according to the scene image captured in real time by at least one camera in the target area within a set time period If the target record in is updated, the target record is deleted.

In an embodiment, the search feedback result generation module 430 specifically includes: a first feedback generation unit and a second feedback generation unit, wherein:

The first feedback generating unit is configured to, if the search user identification information is searched in the user location record table, generate according to the user positioning result recorded in the user location record table corresponding to the search user identification information A search feedback result that matches the user search request;

The second feedback generating unit is configured to, if the search user identification information is not searched in the user location record table, the user location cannot be found as a search feedback result that matches the user search request.

In an embodiment, the target area includes: a canteen; and the user positioning result includes: the number information of the table closest to the user.

The above-mentioned user location searching device can execute the user location searching method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the user location searching method.

Example five

Figure 5 shows a block diagram of an exemplary computer device 12 suitable for implementing embodiments of the present application. The computer device 12 shown in FIG. 5 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present application.

As shown in FIG. 5, the computer device 12 takes the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

The bus 18 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus structure among multiple bus structures. For example, these architectures include but are not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and peripheral component interconnection ( PCI) bus.

The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. For example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 5, and generally referred to as a "hard drive"). Although not shown in FIG. 5, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk") and a removable non-volatile disk (such as CD-ROM, DVD-ROM) can be provided. Or other optical media) read and write optical disc drives. In these cases, each drive can be connected to the bus 18 through one or more data media interfaces. The memory 28 may include at least one program product, the program product having a set (for example, at least one) program modules, and these program modules are configured to perform the functions of the embodiments of the present application.

A program/utility tool 40 having a set of (at least one) program module 42 may be stored in, for example, the memory 28. Such program module 42 includes but is not limited to an operating system, one or more application programs, other program modules, and program data Each of these examples or some combination may include the implementation of a network environment. The program module 42 usually executes the functions and/or methods in the embodiments described in this application.

The computer device 12 can also communicate with one or more external devices 14 (such as keyboards, pointing devices, displays 24, etc.), and can also communicate with one or more devices that enable users to interact with the computer device 12, and/or communicate with Any device (such as a network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. This communication can be performed through an input/output (I/O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 20. As shown in FIG. 5, the network adapter 20 communicates with other modules of the computer device 12 through the bus 18. It should be understood that although not shown in FIG. 5, other hardware and/or software modules can be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tapes Drives and data backup storage systems, etc.

The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the user location search method provided in the embodiments of the present application. That is, when the processing unit executes the program:

Example Six

This embodiment provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for searching the user location as provided in all embodiments of the present application is implemented. That is, when the program is executed by the processor:

Any combination of one or more computer-readable media may be used. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .

The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

The computer program code used to perform the operations of the present application can be written in one or more programming languages or a combination thereof. The programming languages include object-oriented programming languages-such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "like" language or similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN) domain, or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).

Claims

A method for finding the location of a user, the method comprising:

According to the scene image captured by at least one camera in the target area in real time, the user location record table corresponding to the target area is updated in real time, wherein a record in the user location record table includes: user identification information and user identification information The user positioning result corresponding to the identification information;

Acquiring a user location search request corresponding to the target area, and searching in the user location record table according to the search user identification information included in the user location search request;

According to the search result of the search user identification information, a search feedback result that matches the user search request is generated.
The method according to claim 1, wherein the real-time updating of the user location record table corresponding to the target area according to the scene image captured by at least one camera in the target area in real time comprises:

Inputting real-time scene images captured by at least one camera in the target area into a pre-trained human head recognition model, and acquiring a human head image output by the human head recognition model and a user positioning result corresponding to the human head image;

Determining a face image in the scene image according to the image position of the head image in the scene image, and the face image is associated with the head image;

According to the determined face image and the user positioning result corresponding to the face image, the user location record table corresponding to the target area is updated in real time.
The method according to claim 2, wherein determining the face image in the scene image according to the image position of the head image in the scene image comprises:

Acquire an image of a human head in turn, and process the image as the first target;

In the scene image corresponding to the first target processed image, determine the candidate face search area according to the image position of the first target processed image;

If it is determined that a face image is recognized in the candidate face search area, associating the face image with the first target processed image;

Return to the operation of sequentially acquiring a human head image and processing the image as the first target until the processing of all human head images is completed.
The method according to claim 3, wherein identifying a face image in the candidate face search area comprises:

The pre-trained face recognition model is invoked, and the face image is recognized in the candidate face search area.
The method according to claim 2, wherein the user identification information in the user location record table includes: at least one of a face image and user identification information;

Wherein, the correspondence between the face image and the user identification information is determined by a pre-established standard user library.
The method according to claim 5, wherein, according to the determined face image and the user positioning result corresponding to the face image, updating the user location record table corresponding to the target area in real time, comprising:

Sequentially acquiring a determined face image as the second target processing image;

Determining whether the user location record table stores a target record including the second target processed image or user identification information corresponding to the second target processed image;

If yes, update the target record according to the second target processed image and the user positioning result corresponding to the second target processed image;

If not, a new record is created and added to the user location record table according to the second target processed image and the user positioning result corresponding to the second target processed image.
The method according to claim 1, wherein, according to the scene image captured by at least one camera in the target area in real time, updating the user location record table corresponding to the target area in real time, further comprising:

If the target record in the user location record table is not updated according to the scene image captured by at least one camera in the target area in real time within the set time period, the target record is deleted.
The method according to claim 1, wherein generating a search feedback result matching the user search request according to a search result of the search user identification information comprises:

If the search user identification information is searched in the user location record table, based on the user positioning result corresponding to the search user identification information recorded in the user location record table, generate a match with the user search request Search feedback results;

If the search user identification information is not found in the user location record table, the user location cannot be found as a search feedback result that matches the user search request.
The method according to any one of claims 1-8, wherein:

The target area includes: a canteen; and the user positioning result includes: the number information of the table closest to the user.
A device for finding the location of a user, the device comprising:

The user location record table real-time update module is configured to update the user location record table corresponding to the target area in real time according to the scene image captured by at least one camera in the target area, wherein one record in the user location record table includes : User identification information, and user positioning results corresponding to the user identification information;

The user location search module is configured to obtain a user location search request corresponding to the target area, and search in the user location record table according to the search user identification information included in the user location search request;

The search feedback result generation module is configured to generate a search feedback result that matches the user search request according to the search result of the search user identification information.
A computer device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, wherein the processor executes the program as described in any one of claims 1-10 Find the location of the user described above.
A computer-readable storage medium with a computer program stored thereon, wherein the program is executed by a processor to realize the user location search method according to any one of claims 1-10.