WO2019223608A1

WO2019223608A1 - Service providing method and apparatus

Info

Publication number: WO2019223608A1
Application number: PCT/CN2019/087347
Authority: WO
Inventors: 孙楠; 陆阳; 朱志宇
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2018-05-25
Filing date: 2019-05-17
Publication date: 2019-11-28
Also published as: CN110533553B; CN110533553A

Abstract

Provided in the embodiments of the present invention are a service providing method and apparatus. The method comprises: receiving data collected by at least two collection devices; performing, by combining with position attributes respectively associated with the collected data, user position track identification on the collected data; and providing, according to the intention of a user reflected by a user position track, a service corresponding to the intention of the user for the user. According to the present solution, a certain scene may actively sense the intention of a user, namely, sensing which user is going to do what and where the user will be, thereby providing a more intelligent service for the user, and the degree of intelligence of providing the user with a service by the scene is improved.

Description

Service providing method and device

This application claims priority from a Chinese patent application filed on May 25, 2018 with an application number of 201810517433.2 and an invention name of "Service Provision Method and Device", the entire contents of which are incorporated herein by reference.

Technical field

The present invention relates to the field of Internet technologies, and in particular, to a method and device for providing services.

Background technique

At present, various smart electronic products surround people, providing people with a more intelligent living atmosphere. For example, various smart wearable products can be used to detect people's physical conditions, and various smart home products can create smarter homes. surroundings. Therefore, more and more offline physical scenarios, such as hotels and other scenarios, will also deploy certain smart products in order to provide users with personalized and intelligent services.

However, taking the hotel scenario as an example, the smart products currently deployed in hotels can provide limited intelligent services, and often only a few smart elements are deployed in the hotel, such as welcome robots, smart speakers, smart curtains, and smart light control. Therefore, it is an urgent problem to expand the intelligent service model and improve the intelligence of the hotel.

Summary of the Invention

In view of this, embodiments of the present invention provide a service providing method and device, so as to improve the degree of service intelligence in a specific scenario, such as a hotel scenario.

In a first aspect, an embodiment of the present invention provides a service providing method, including:

Receiving acquisition data from at least two acquisition devices;

Combine the position attributes of the collected data with each other to perform user position trajectory recognition on the collected data;

And providing a user with a service corresponding to the user's intention according to the user's intention reflected by the user's position trajectory.

In a second aspect, an embodiment of the present invention provides a service providing apparatus, including:

A data receiving module, configured to receive data collected by at least two acquisition devices;

A data processing module, configured to identify a user's position and trajectory on the collected data by combining position attributes associated with the collected data;

A service scheduling module is configured to provide a user with a service corresponding to the user's intention according to the user's intention reflected by the user's location trajectory.

According to a third aspect, an embodiment of the present invention provides an electronic device including a memory, a processor, and a sound input-output component. The memory is used to store one or more computer instructions, and the one or more computer instructions are stored by all When the processor executes, the method for implementing the service in the first aspect is implemented.

An embodiment of the present invention provides a computer storage medium for storing and storing a computer program, which is executed by a computer to implement the service providing method in the first aspect.

In the service providing method provided by the embodiment of the present invention, a hotel scenario is taken as an example in a certain scenario, and there are a plurality of acquisition devices. The acquisition devices may be different types of devices such as a camera and a user terminal device. Users perform IntelliSense. After each collection device works, the collected data is sent to the server, so that the server can analyze each collection data in combination with the location attributes associated with each collection data, that is, the location information corresponding to the corresponding collection device, to identify any scene in the scene. A user's location trajectory is simply that, when a user is identified from a certain collection of data, the user's current location of the user is determined based on the location attributes corresponding to the collected data at this time, so that through the collection of many The data can be tracked to obtain the user's position trajectory after the same identification processing, and the user's position trajectory can often reflect the user's user intent, such as where the user wants to go, so that it can be reflected according to the user's position trajectory. User intention to provide users with targeted services. Through this solution, a certain scenario can actively sense the user, that is, which user is where to do what, so as to provide a more intelligent service for the user, and improve the intelligence of the service provided to the user in this scenario.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly explain the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a flowchart of Embodiment 1 of a service providing method according to an embodiment of the present invention; FIG.

2 is a flowchart of a second embodiment of a service providing method according to an embodiment of the present invention;

3 is a flowchart of Embodiment 3 of a service providing method according to an embodiment of the present invention;

4 is a flowchart of a fourth embodiment of a service providing method according to an embodiment of the present invention;

5 is a flowchart of Embodiment 5 of a service providing method according to an embodiment of the present invention;

6 is a schematic structural diagram of a service providing apparatus according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of an electronic device corresponding to the service providing apparatus provided by the embodiment shown in FIG. 6.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms "a", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates another meaning, "multiple" Generally, at least two kinds are included, but the case where at least one kind is included is not excluded.

It should be understood that the term “and / or” used herein is merely an association relationship describing an associated object, which means that there can be three kinds of relationships, for example, A and / or B can mean: A exists alone, and both A and B, there are three cases of B alone. In addition, the character "/" in this text generally indicates that the related objects are an "or" relationship.

It should be understood that although the terms first, second, third, etc. may be used to describe XXX in the embodiments of the present invention, these XXX should not be limited to these terms. These terms are only used to distinguish XXX. For example, without departing from the scope of the embodiments of the present invention, the first XXX may also be referred to as the second XXX, and similarly, the second XXX may also be referred to as the first XXX.

Depending on the context, the words "if", "if" as used herein can be interpreted as "at" or "when" or "responding to determination" or "responding to detection". Similarly, depending on the context, the phrases "if determined" or "if detected (the stated condition or event)" can be interpreted as "when determined" or "responded to the determination" or "when detected (the stated condition or event) ) "Or" in response to a test (statement or event stated) ".

It should also be noted that the terms "including," "including," or any other variation thereof are intended to encompass non-exclusive inclusions, so that a product or system that includes a series of elements includes not only those elements, but also those that are not explicitly listed Other elements, or elements that are inherent to this commodity or system. Without more restrictions, the elements defined by the sentence "including one ..." do not exclude the existence of other identical elements in the product or system including the elements.

In addition, the sequence of steps in the following method embodiments is only an example, and is not strictly limited.

FIG. 1 is a flowchart of Embodiment 1 of a service providing method according to an embodiment of the present invention. The service providing method provided in this embodiment of the present invention may be applicable to a scenario where a service is provided to a user, such as a hotel scenario. According to the service providing method provided in the embodiment of the present invention, a hotel can provide a more intelligent service to a user, especially a staying customer. This method can be performed by a server deployed on-site at the hotel or deployed in the cloud. As shown in Figure 1, the method includes the following steps:

101. Receive acquisition data from at least two acquisition devices.

102. Combine the position attributes associated with the collected data to identify the user position and trajectory on the collected data.

103. Provide a service corresponding to the user's intention to the user according to the user's intention reflected by the user's position trajectory.

First take a hotel scenario as an example to briefly introduce the hardware deployment in the hotel. In this hotel, in addition to various intelligent hardware products deployed in traditional hotels, such as welcome robots, smart curtains, smart speakers, smart lights and other equipment, in public areas, such as corridors, elevators, lobby front desks, etc. , Hotel entrances, restaurants and gyms and other entertainment venues, the hotel scene can also have at least two collection devices for collecting user information, that is, multiple collection devices, where these collection devices can include pre-deployment Multiple cameras at appropriate locations in the hotel scene. In addition, the user terminal equipment owned by people entering the hotel scene, such as residents and service personnel, can also be considered as a collection device.

In addition, in addition to the above-mentioned acquisition equipment, the hotel scene can also be deployed with other sensing devices to assist user perception, such as different types of devices such as positioning devices, human detection sensors, etc., combined with the intelligence provided by the hotel scene to users Services, these sensing devices can be deployed in advance in suitable locations. In some optional embodiments, the sensing device may be an auxiliary device capable of collecting the foregoing collection data. For the above-mentioned acquisition equipment and sensing equipment, for example, in the corridor of each floor, cameras with different walking directions, such as cameras corresponding to east-west directions, are deployed on the wall at a certain distance. For another example, multiple cameras can be set at the elevator door frame on each floor, such as one camera on the left and right sides of the elevator door frame, or two cameras arranged on the left and right sides of the elevator door frame, respectively, to suit different users. Height difference. For another example, in the entire hotel, several positioning devices are distributed at appropriate distance intervals. The positioning devices may be, for example, wireless access points (AP), iBeacon Bluetooth devices, and so on. As another example, a camera and a human detection sensor connected to the camera can be deployed on the door of each guest room. For another example, more broadly, a user terminal device such as a smart phone and the like carried by each user who enters the scene can also be considered as a component of multiple collection devices.

In addition, the acquisition equipment and sensing equipment fixedly deployed in the hotel scene can be associated with location attributes in advance. For example, for the aforementioned camera, the associated location attributes are, for example, the floor number where it is located and the corresponding position number in the camera sequence corresponding to the floor corridor, or its corresponding room number. It can be understood that the floor number, location number, and room number can be regarded as coarse-grained location information. Based on actual needs, the server can store the correspondence between the coarse-grained location information and the corresponding fine-grained location information in advance. The fine-grained location information refers to location information such as longitude and latitude that accurately identifies a geographic location.

In the embodiment of the present invention, the location attributes associated with each collection device can assist in positioning the user's location. For example, if a camera at a certain position captures the face of a certain user, the user can be considered to be located at this time. The location of the camera.

Therefore, based on the collection equipment provided in the hotel scene, such as the above example, it is equivalent to making the hotel constitute a smart induction field, which can sense the user's position trajectory in the scene, and the user's position trajectory often reflects the user's An intent that makes it easier to provide users with targeted, more intelligent services.

Specifically, when each acquisition device works, it will continuously collect data in real time or with a set acquisition strategy, and send the collected data to the server, such as the camera to collect video data, and the user terminal device to collect the positioning signals broadcasted by the positioning device. ,and many more.

For the collected data uploaded by each collection device, combined with the location attributes associated with each collected data, the server performs user location trajectory identification on each collected data to identify the user location trajectory of one or some users, so as to know its corresponding user intention To provide targeted services to users based on their intent. Among them, for any collected data, the associated location attribute may be the location information associated with the corresponding collection device, such as the floor number and location number corresponding to the camera fixed in advance, or the real-time location of the user terminal device. location information.

In actual applications, corresponding to different acquisition devices, it may be necessary to combine the acquisition data collected by multiple acquisition devices to identify the user location trajectory of the same user, such as combining the video data captured by multiple cameras to identify the user of a user Location trajectory, or it may be necessary to combine different collection data uploaded by the same collection device to identify the user's location trajectory, such as combining multiple positioning data sequentially uploaded by a user terminal device (the positioning mentioned below) The signal strength vector) identifies the user position trajectory of the corresponding user.

For example, if at some time it is found that a certain camera collects the collection data corresponding to user A, and at a similar time, several other cameras adjacent to the collection device also sequentially collect the collection corresponding to the user A Therefore, the server can obtain the location track of the user A based on the collected data of the cameras and combine the position attributes associated with the cameras, that is, the position attributes associated with the collected data, to determine the user A. User intent, that is to know who the user is, where it is, what it is going to do, such as where to go.

Therefore, based on the recognition result of the current user intention of the user A, the server can intelligently provide the corresponding required service to the user A. For example, if the user A is found to come out of the room he is staying in and walk towards the elevator, he can schedule Elevator to the floor where user A is located.

In order to identify the user intention (such as the user intention of user A), optionally, the actual processing process of the server may be:

The server will receive the collected data from multiple collection devices. For each received data, the server can first identify the user with the collected data, so as to determine the same user in turn from the many collected data. Collected data of identity information. These multiple collected data corresponding to the same user's identity information are called target collected data. Furthermore, for the determined target acquisition data, according to the position attributes corresponding to the target acquisition data, the user position trajectory of the user corresponding to the same user identity information is determined.

The user identity information may be carried in the collected data, or sent to the server independently of the collected data but together with the collected data. For example, the user identity information may be a user face image in video data captured by a camera, or may be a user terminal device identifier sent by the user terminal device at the same time as sending a positioning signal strength vector to the server. The user terminal device Identification as user identity information.

For an optional implementation process of user identification and user location trajectory determination, refer to the detailed description in the subsequent embodiments.

Based on this, through this solution, a scenario can actively sense the user's intention, that is, which user is where to do what, so as to provide users with more intelligent services, and improve the intelligence of the service provided to users in this scenario.

The following describes the service providing method provided by the embodiment of the present invention with several specific examples in a hotel scenario.

FIG. 2 is a flowchart of Embodiment 2 of a service providing method according to an embodiment of the present invention. As shown in FIG. 2, the method may include the following steps:

201. Receive video data collected by N first cameras located on a floor walkway.

202. Perform face recognition on the video data collected by each of the N first cameras to determine M target video data that sequentially capture the same target face image, 1 <M ≦ N.

203. If the target face image exists in a preset legal user database, determine the user position of the user corresponding to the target face image according to the floor number and location number associated with the respective M first cameras corresponding to the M target video data. Track.

204. Provide a service corresponding to the user's intention to the user according to the user's intention reflected by the user's position trajectory.

This embodiment illustrates the recognition of the user intention of a certain user based on face recognition. In this embodiment, the user's intention may be embodied as the user's intention to board an elevator, or the user's intention to return to the room.

In order to realize the identification of the user's intention of boarding the elevator, the deployment of the above N cameras may be: In an optional embodiment, one or more cameras may also be provided at the elevator door frame on each floor to assist in identifying the proximity to the elevator. The user ’s intention to take the elevator; in another optional embodiment, multiple cameras may be arranged at intervals in the corridor of each floor to assist in identifying the user ’s intention to take the elevator in the direction of the elevator; in another optional In the embodiment, in order to more accurately identify the user's intention to take the elevator, multiple cameras may be deployed in the corridors of each floor at intervals, and one or more cameras may also be provided at the elevator door frames of each floor.

Because in actual application, the elevator of any floor may be located in the central location area of the floor, or it may be located in the edge location area on one side of the floor. When the elevator is located in the central location area, the residents located on both sides of the elevator There is a need to take an elevator, so it is necessary to identify users who are going to the elevator from both sides. To this end, at the corresponding floor corridor, a camera capable of collecting video data of users who are going to the elevator from different directions is required. For example, a row of cameras facing the east can be set on one wall of the corridor, and a row of cameras facing the west can be set on the other wall of the corridor.

Wherein, such a camera deployment that can collect video data of different orientations can also satisfy the identification of the user's intention to return to the room as shown in this embodiment. Because in a practical situation, if it is assumed that a user in a room walks out of the room and goes west to go to the elevator, walking out of the elevator and goes to the east is going to the room.

In addition, in order to better support the identification of the user's intention of returning to the room, the multiple cameras deployed in the corridor of any floor can include cameras that are close to each room on the floor, in order to accurately identify whether a user stops at the place where he is staying Near the door of the room.

Based on the deployment of the above N cameras, when these cameras start to work, the collected video data can be sent to the server. For the video data collected by each camera, the server can perform face recognition processing on the video data.

Specifically, taking the video data a collected by any camera as an example, in order to increase the speed of face recognition processing, the server may first perform down-sampling processing on the video data a, and then image the down-sampled video data a. Frame segmentation processing, and then face recognition processing may be performed on the current image frame every few frames, such as 5 frames, to identify whether the current image frame contains a face image. When it is recognized that the video data a includes a certain face image as a target face image, the target face image may be labeled, such as extracting the target face image and marking the target face image in Acquisition time in the video data a.

Optionally, in order to ensure the reliability of the target face image recognition result, it can be considered that if the target face image is recognized in several frames of continuous recognition, the recognition result of the target face image is considered valid.

The above-mentioned face recognition processing is performed on the video data collected by each camera. In this way, for the identified target face image, multiple other video data, such as video data, of the target face image can be obtained. b. Video data c, and corresponding acquisition times of the target face image in video data b and video data c, respectively. Therefore, according to the sequence of the corresponding acquisition times of the target face image in the video data a, video data b, and video data c, the video data a, video data b, and video data c can be sorted to obtain sequential acquisition. To three (at this time, M = 3) target video data of the target face image.

Further, optionally, the user position track of the user corresponding to the target face image may be determined according to the floor number and the position number associated with the three first cameras corresponding to the three target video data respectively.

Optionally, before determining the location track of the user, the user corresponding to the target face image may be further identified, and the location track of the user may be determined only when the identity of the user is legal, so as to provide the user with the Provide a service corresponding to the user's intention reflected by the user's position trajectory.

In an optional embodiment, after obtaining the M target video data, user identification may be performed for the user corresponding to the target face image. In another optional embodiment, user identification may also be performed when the target face image is recognized for the first time. At this time, if it is determined that the user identity corresponding to the target face image is illegal, the target face is ignored. Image, so if the target face image is also recognized in other video data subsequently, it is also ignored.

It can be understood that the server stores a database containing reference face images of all users in the hotel scene in advance, which is called a preset legal user database. The user in this embodiment may include all occupants and service staff. Among them, the reference face image of the guest was obtained when the guest checked in: Specifically, when checking in, the relevant person will enter the guest's identity information and the guest's check-in information into the server. The identity information includes, for example, the resident's ID number, ID photo or images collected on site (as the reference face image of the resident), mobile phone number, mobile phone MAC address, etc .; check-in information, such as the room number and room price , Length of stay, services booked such as gym, catering, etc. Similarly, user information such as the reference face image, mobile phone number, and mobile phone MAC address of the service personnel is also stored in the preset legal user database in advance.

Therefore, the server can compare the identified target face image with a reference face image contained in a preset legal user database to determine who the user corresponding to the target face image is, for example, a person staying in a room Guest, or a service staff. If there is no reference face image matching the target face image in the preset legitimate user database, the user corresponding to the target face image is considered to be an illegal user.

When M target video data of a target face image are sequentially acquired from the video data collected by the N first cameras, and the identity of the user corresponding to the target face image is determined to be legal, the M The floor numbers and location numbers associated with the respective M first cameras corresponding to the target video data determine the user location trajectory of the user corresponding to the target face image, and then provide the user with the user ’s intention based on the user ’s intention reflected in the user ’s location trajectory. The service the user intended. The M first cameras are cameras that respectively collect the M target video data.

In an optional embodiment, if the M first cameras correspond to the same floor number and the position numbers of the M first cameras reflect that the walking direction of the user corresponds to the elevator direction, then determine the user's position track of the user Is walking towards the elevator, so that the user ’s position trajectory reflects the user ’s intention to board the elevator. At this time, the server controls the elevator to run to the floor corresponding to the floor number according to the user ’s intention to board the elevator. .

For example, for example, camera 1 captures Zhang San's face image at time T1, camera 2 also captures Zhang San's face image at time T2, and camera 3 also captures Zhang San's face image at time T3, of which , T1, T2, and T3 are similar and increase in order, and camera 1, camera 2, and camera 3 are all arranged from west to east in the corridor on the third floor, and the elevator is located on the east side of camera 3, it is determined that the user wants to take the elevator.

It is worth noting that in order to more accurately determine whether the user wants to take the elevator, the camera closest to the elevator door among the M cameras should not be too far away from the elevator door. Therefore, optionally, it is possible to identify whether the user intends to take the elevator. The elevator determination conditions may further include: if the M first cameras correspond to the same floor number and the position numbers of the M first cameras reflect that the user ’s walking direction corresponds to the elevator direction, and the M cameras are on the floor The distance between the elevator doors corresponding to the number satisfies the requirements, it is determined that the user's position trajectory of the user is walking toward the elevator. Accordingly, the user's intention reflected by the user's position trajectory is the user's intention to ride the elevator.

The distance between the M cameras and the elevator door corresponding to the floor number meets the requirement refers to the distance between the camera closest to the elevator door and the elevator door among the M cameras. The server may maintain in advance the relative positional relationship between the positions of the cameras on the same floor and the position of the elevator door on the floor, such as maintaining the position numbers of the cameras on any floor that are gradually approaching the elevator door in a certain direction.

In addition, it is worth noting that, in an extreme case, for example, the room where a user is staying is very close to the elevator door on the floor. At this time, the user's intention to take the elevator can be based on the camera deployed at the door frame of the elevator. That is, when the server recognizes a user's face image based on the video data collected by the camera deployed at the door frame of the elevator, the server determines that the user wants to take the elevator based on the position attribute associated with the video data, that is, the position attribute associated with the camera. The position attribute reflects the position of the camera at the elevator door of a certain floor, for example, the position of the elevator at a certain floor is the value of the position attribute.

In addition, in some embodiments, in addition to providing targeted services to users based on the obtained user intentions, it may further combine user characteristic information of users to push service information for users.

For example, when it is found that the user intends to take the elevator, at this time, in addition to scheduling the elevator to the user's current floor based on the user's intention, it can also combine the current time, the user's previous behavior information record, and the user's check-in purpose. The user characteristic information pushes the corresponding service information for the user. For example, if you find that the user goes to the gym around the current time every day to exercise, you can push the information about the number of people in the gym and the use of equipment, so that the user can know the situation of the gym in advance. For another example, if it is found that the user currently wants to take the elevator, and it is determined that it is currently at a meal time according to the current time, and the user has the right to dine in the hotel restaurant, the user can push the meal information provided by the current restaurant to the user. For another example, if it is found that the user currently wants to take the elevator, and it is determined that the user is currently out of time according to the current time, and the user's check-in purpose is to travel, the user can push the attraction information to the user.

In another optional embodiment, if the M first cameras correspond to the same floor number and the position numbers of the M first cameras reflect that the user walked near his room, it is determined that the user's position trajectory of the user is toward The user walks in the direction of the room, so that the user's position trajectory reflects the user's intention to return to the room. At this time, the server presets the smart device in the user's corresponding room according to the user's intention to return to the room reflected in the user's position trajectory. Control, for example, can control the unlocking of the door of the room corresponding to the user. For example, it can also control the air conditioner and light in the room in a specific mode. Among them, the M cameras are often composed of multiple cameras from near the elevator position on the floor to near the user's room location, and the shooting direction of the multiple cameras corresponds to the user's direction from the elevator to the room. Moreover, it can be understood that the floor numbers corresponding to the M cameras are consistent with the floor numbers of the user's rooms.

In summary, taking the hotel scene as an example, by deploying several cameras for collecting video data at appropriate positions in the hotel scene, and based on the server-side face recognition and video data processing logic that reflects the user ’s position trajectory recognition reflecting user intentions, The hotel scene can automatically realize the user's intention, so as to provide users with more intelligent services.

FIG. 3 is a flowchart of Embodiment 3 of a service providing method according to an embodiment of the present invention. As shown in FIG. 3, the method may include the following steps:

301. Receive video data collected by N first cameras located on a floor walkway, and video data collected by second cameras located at each room door.

302: Perform user profile feature recognition on the video data collected by each of the N first cameras to determine K target video data that sequentially capture the same target user profile feature, 1 <K ≦ N.

303. If the K first cameras corresponding to the K target video data correspond to the same floor number, and the position numbers of the K first cameras reflect the user with the contour characteristics of the target user walking to the target room, determine the user The user position trajectory is walking towards the target room.

304: Control the second camera corresponding to the target room to collect video data according to the intention of entering the target room reflected by the user's position trajectory, and identify the face image in the video data collected by the second camera. If the identified face image and the When the reference face image corresponding to the target room matches, the smart device in the target room is preset to control.

This embodiment illustrates recognition of a user's intention to return to a room based on face recognition. The implementation process of identifying the user's intention to return to the room in this embodiment is different from the implementation process of identifying the user's intention to return to the room as shown in FIG. 2. The embodiment shown in FIG. 2 is mainly based on the way in which the user walks to the room door. The multiple cameras of the camera have successively collected the face images of the user, and the user walked near the room where he stayed. These characteristics identify the user's intention to return to the room, that is, to open the room door to enter the room. This recognition method can be considered as an indirect recognition mode. . In contrast, the method for identifying the user's intention to return to the room in this embodiment is a direct recognition mode. In simple terms, the user is required to cooperate with image acquisition and face recognition to determine whether the user has the right to enter a room.

To support the direct recognition mode, a camera may be deployed on each room door in the hotel as a second camera. Optionally, a human detection sensor connected to the second camera may also be deployed. The human detection sensor is, for example, an ultrasonic sensor, Infrared sensors can detect humans within a certain distance. In order to improve the service life and energy saving of the second camera on the room door, after the human detection sensor on the door of a room is activated, when a human body is detected to be approaching, a trigger signal is sent to the corresponding second camera to trigger the second camera. The camera works, and the second camera further collects video data and sends the collected video data to the server. It can be understood that the second camera on the door of the room is also associated with a position attribute, which can be carried in the video data collected by the second camera, and the position attribute is reflected in the corresponding room number, so that the server knows that Which room door sends video data to the second camera.

In this embodiment, the condition for triggering the second camera on the door of a room to collect video data can be simply said: if a user is found walking to the door of the room, but the face image of the user is not recognized, it is not found. Video data collected by a plurality of first cameras including a face image of the user. Because at this time, it is impossible to determine whether the user has the right to enter the room through face recognition.

At this time, optionally, for the video data collected by each of the N first cameras, the server may first perform user profile feature recognition to determine K target video data that sequentially captures the same target user profile feature, and then if K The K first cameras corresponding to the target video data correspond to the same floor number, and the position numbers of the K first cameras reflect that the user with the outline characteristics of the target user walks to the target room, and it is determined that the user's position trajectory of the user is Walk to the target room, thereby determining that the user of the user intends to enter the target room. The above-mentioned user contour features may include hairstyle, body shape, dress, and the like.

At this time, the above-mentioned user profile feature can be regarded as a kind of weak user identity information, which is not enough to accurately determine whether the user has the right to enter the target room, that is, insufficient to accurately identify the user's user identity. Therefore, in When it is determined that the user intends to enter the target room, the server may further control the second camera of the target room to be turned on, collect video data, and perform face recognition on the video data to determine whether the identified face image is consistent with a preset The reference face image corresponding to the target room in the legal user database matches. If they match, it means that the user has the right to enter the target room, that is, the user's identity is legal. Therefore, the server can control the door lock of the target room to open, for example. It is possible to control smart devices such as air conditioners and electric lights in the target room to be in a preset working mode.

The server can directly control the second camera corresponding to the target room to be turned on to collect video data. Alternatively, the server can also be turned on by controlling the human detection sensor connected to the second camera to control the corresponding first camera through the human detection sensor. The two cameras are turned on, that is, the second camera is controlled to be turned on when it detects a human body. By controlling the human detection sensor to be turned on, it is possible to avoid a control error caused by the server directly controlling the opening of the second camera corresponding to the target room if the target room is mistakenly identified, because it is only detected when the human detection sensor detects a human being approaching Trigger the second camera to work. The second camera can be automatically turned off after sending the collected video data to the server.

Based on the recognition of the user's intention to enter the room in this embodiment, the user no longer needs to swipe the card to unlock the door as traditionally when entering the room, providing convenience to the user.

FIG. 4 is a flowchart of Embodiment 4 of a service providing method according to an embodiment of the present invention. As shown in FIG. 4, the method may include the following steps:

401. Receive positioning signal strength vectors and user terminal equipment identifiers collected by multiple user terminal devices at different moments, where the positioning signal strength vectors correspond to multiple pre-deployed positioning devices.

402. Determine a target positioning signal strength vector sequence corresponding to the same target user terminal equipment identifier.

403. Determine a user position trajectory of a user corresponding to a target user terminal device identifier according to a target positioning signal strength vector sequence.

404: Provide a service corresponding to the user's intention to the user corresponding to the target user terminal device identifier according to the user's intention reflected by the user's location track.

This embodiment is intended to recognize the user intention of a certain user based on the positioning algorithm. In this embodiment, the user's intention may be embodied as the user's intention to board the elevator, or the user's intention to return to the room, or the user's intention to use the navigation application, and so on.

In order to realize the identification of a user's intention based on a positioning algorithm, taking a hotel scenario as an example, several positioning devices are pre-deployed in the hotel, and the coverage of the positioning broadcast signals transmitted by each positioning device can be set according to actual needs Specifically, the transmission power of the positioning device can be adjusted to achieve the setting of the coverage range. Each positioning device has unique identification information, which is used to distinguish different positioning devices.

In addition, in order to support the positioning algorithm provided in this embodiment, after the positioning devices are deployed, the positioning signal strength test can be performed at several locations in the hotel, for example, assuming that it is generated every 2 meters in a hotel space of 30,000 square meters One test position can generate a total of 15,000 test positions. In this embodiment, each test position has two dimensions of information, one of which is specific spatial coordinates, such as (x, y, floor number), where x, y refers to latitude and longitude coordinates; the other is at The positioning signal strength vector of each positioning device measured at the test position.

Specifically, the tester may carry, for example, a smart phone standing at different test positions to measure the positioning signal strength vector of each positioning device, where the smart phone obtains the positioning according to the strength of the positioning signal received by each positioning device. Signal strength vector. It can be understood that if a positioning signal of one or some positioning devices is not received at a test position, the corresponding positioning signal strength of the positioning devices at the test position is considered to be 0, and the The positioning signal may carry the identification of the positioning device so as to distinguish the positioning signal strength of each positioning device.

For example, suppose the positioning device includes AP1, AP2, AP3, AP4, and AP5, the test position includes f1, f2, f3, and assume that the positioning signal strength vector measured at f1 is [-50, -60, -70, 0, -70], the positioning signal strength vector measured at f2 is [-65, -42,0,0, -80], and the positioning signal strength vector measured at f3 is [-60, -63, 0,0, -50], where the units of the above-mentioned positioning signal strength vectors are in decibels, and the order of the elements in the above-mentioned positioning signal strength vectors corresponds to AP1, AP2, AP3, AP4, and AP5 in order, that is:

AP1 AP2 AP3 AP4 AP5

f1 = [-50, -60, -70,0, -70]

f2 = [-65, -42,0, -50, -80]

f3 = [-60, -63, -45,0, -50].

Furthermore, based on the positioning signal strength vector of each positioning device measured at each test position, the mapping relationship between the positioning device and the test position can be converted. Specifically, for any positioning device, test positions whose measured positioning signal strength is greater than a preset threshold can be filtered out of all test positions to form a test position set corresponding to the positioning device. For example, suppose the preset threshold is -60. For the above AP1, since the positioning signal strength measured at f1 and f3 is greater than or equal to -60, and the positioning signal strength measured at f2 is less than -60, then AP1 corresponds to The set of test locations consists of f1 and f3, and is expressed as AP1-> (f1, f3). Similarly, AP2-> (f1, f2), AP3-> (f3), AP4-> (f2), AP5-> (f3). It can be understood that only non-zero elements in each positioning signal strength vector are compared with a preset threshold of -60.

Based on this, the server can store the positioning signal strength vector measured at each test position, the test position set corresponding to each positioning device, and the specific position information corresponding to each test position into the positioning database.

Therefore, in a practical application, when a user carrying a user terminal device such as a mobile phone is in a certain position in a hotel, the user terminal device may receive positioning signals transmitted by multiple positioning devices, and thus the user terminal device may The positioning signal strength vector formed by the received positioning signal strength and the user terminal device identifier are sent to the server, so that the server receives the positioning signal strength vectors and user terminal device identifiers sent by multiple user terminal devices at different times.

Wherein, as described in the foregoing embodiment, the user terminal device identifier, such as a mobile phone MAC address, can be used as a user identity identifier, so that the server can identify the user identity based on the user terminal device identifier.

In practical applications, for any user terminal device, it is assumed to be called a target user terminal device. The target user terminal device can send each detected target positioning signal strength vector and target user terminal device identifier to the server. On the one hand, the server can The target user terminal device identifier and the receiving time determine the target positioning signal strength vector sequence corresponding to the target user terminal device identifier, that is, because all target positioning signal strength vectors corresponding to the target user terminal device identifier are in the order of receiving time. It also determines whether the target user terminal device identifier is included in the preset legal user database. On the other hand, after receiving a target positioning signal strength vector, the user position where the corresponding user is currently located can be determined. The user position of the user at different times constitutes the user position track of the user.

Specifically, for any positioning signal strength vector in the target positioning signal strength vector sequence, the server may determine the location of the corresponding user at this time by the following process:

Determining a target positioning device corresponding to a signal strength greater than or equal to a preset threshold in any positioning signal strength vector from the plurality of deployed positioning devices;

Acquiring a set of test positions corresponding to the target positioning device, wherein the signal strength of the target positioning device measured in advance at each test position in the test position set is greater than or equal to a preset threshold;

Determining the user position of the user corresponding to the target user terminal device identifier at this time according to the distance between any one of the positioning signal strength vectors and the reference positioning signal strength vector corresponding to each test position, wherein the reference positioning signal strength vector is a The signal strengths of the plurality of positioning devices measured at the corresponding test positions.

For example, suppose the target positioning signal strength vector measured by the target user terminal device at the current position is: X1 = [-80, -50, 0, -90, -60], and it is assumed that the target positioning signal strength vector The order of the elements corresponds to AP1, AP2, AP3, AP4, and AP5. Assuming the preset threshold is -60, the target positioning devices corresponding to signal strengths in the target positioning signal strength vector that are greater than or equal to the preset threshold, that is, -50 and -60 are AP2 and AP5. Furthermore, based on the correspondence between the positioning devices and the test position set stored in the positioning database, it can be known that the test position set corresponding to AP2 is (f1, f2), and the test position set corresponding to AP5 is (f3). Furthermore, based on the positioning signal strength vector measured at each test position stored in the positioning database, it is known as the reference positioning signal strength vector: f1 = [-50, -60, -70,0, -70], f2 = [- 65, -42,0, -50, -80], f3 = [-60, -63, -45,0, -50]. Therefore, the target user terminal device is determined based on the distance between the target positioning signal strength vector X1 = [-80, -50, 0, -90, -60] measured by the target user terminal device and the three reference positioning signal strength vectors, respectively. The corresponding user's current location.

In the process of calculating the distance between the target positioning signal strength vector measured by the target user terminal device and the three reference positioning signal strength vectors, respectively, optionally, the target positioning signal strength vector measured by the target user terminal device may be directly calculated X1 = [-80, -50, 0, -90, -60] and the Euclidean distance between the three reference positioning signal strength vectors respectively; or alternatively, the target positioning measured by the target user terminal device may also be performed first Signal strength vector X1 = [-80, -50, 0, -90, -60] and the three reference positioning signal strength vectors for element filtering, and then calculating the distance between the filtered positioning signal strength vectors; or optionally , You can also only perform element filtering on the target positioning signal strength vector X1 = [-80, -50, 0, -90, -60] measured by the target user terminal device, and then calculate the filtered target positioning signal strength vector respectively The distance from the three reference positioning signal strength vectors.

Among them, element filtering refers to filtering out elements in the above vector that are smaller than a preset threshold value such as -60, that is, elements that are smaller than -60 are set to 0, so the target positioning signal strength vector X1 = [-80, -50, 0,- 90, -60] after filtering, X2 = [0, -50,0,0, -60]. Assuming that element filtering is also performed on the reference positioning signal strength vector, the reference positioning signal strength vector f1 = [-50, -60, -70,0, -70] after filtering is f11 = [-50, -60,0,0 , 0]; reference positioning signal strength vector f2 = [-65, -42,0, -50, -80] after filtering is f21 = [0, -42,0, -50,0]; reference positioning signal strength vector f3 = [-60, -63, -45,0, -50] After filtering, it is f31 = [-60,0, -45,0, -50].

After the above distances are calculated, a certain number of test positions can be selected from the multiple test positions f1, f2, and f3 in the order of the distance from small to large. For example, two test positions are selected, assuming f1 and f3. Therefore, the current position of the user corresponding to the target user terminal device is determined in combination with the selected test position. When the selected number is set to 1, that is, the test position corresponding to the minimum distance among the distances is used as the position of the user, the position of the user is determined to be the specific position of the test position in the hotel.

Optionally, assuming that the selected test positions are f1 and f3, and assuming that the distance between the vectors corresponding to f1 is less than the distance corresponding to f3, the user position L (x ', y') may be determined according to the following method:

L (x ', y') = a (x1, y1) + b (x3, y3), where (x1, y1) is the coordinate position corresponding to f1, (x3, y3) is the coordinate position corresponding to f3, a And b are preset weighting coefficients, a> b.

After the user position track of the user corresponding to the target user terminal device is determined based on the above process, a corresponding server may be provided to the user based on the user intention reflected in the user position track.

In an optional embodiment, if the user position trajectory reflects that the user intends to walk toward the elevator of the target floor, the elevator is controlled to run to the target floor.

Among them, the server side can also maintain a digital map of the hotel scene, so that the user's location trajectory can be located in the digital map. If the user's location trajectory is found to reflect that the user is walking towards the elevator on that floor in a certain floor, the elevator is dispatched Run to this floor.

In another optional embodiment, if the position track of the user reflects that the user intends to walk toward the user's room, preset control is performed on the smart device in the room corresponding to the user.

Similarly, when the server locates the user's location trajectory in the digital map and finds that the user's location trajectory reflects that the user is walking in the direction of the room where he lives, and resides at the door of the room, the smart device in the corresponding room of the user is pre- Set control, such as controlling the door lock of the room to open, and controlling smart devices such as electric lights and air conditioners in the room to be in the preset working mode.

It can be understood that the server maintains the correspondence between the identification of the user terminal device and the room number, so as to determine whether the room in which the user corresponding to the user terminal device resides is the room in which the user resides.

In another optional embodiment, in order to facilitate understanding, the following scenario is assumed: For reasons of privacy and security of the guest, the room number is not affixed to the door of each room in the hotel, so when the user checks in the hotel, the user can Provide a navigation application to help users navigate from their current location (such as the front desk in the lobby) to a destination location (such as their own room). In practical applications, the user can obtain the navigation application provided by the hotel by scanning, etc., and then can locate the user's current location through the above positioning algorithm, or the user can manually enter the current location such as the lobby front desk, and enter The destination location, such as its own room number, triggers the navigation application to send a navigation request to the server for navigating the user from the current location to the destination location.

In this embodiment, it is assumed that the target user terminal device sends a navigation request to the server for navigating the user from the current position to the destination position. Therefore, after receiving the navigation request, the server plans the navigation from the current position to the destination position. The route is sent to the navigation application, that is, to the target user terminal device, so that the user executes the navigation route to walk according to the navigation route. While the user is walking according to the navigation path, the target user terminal device may send the target positioning signal strength vector detected at that time to the server at a certain interval for the server to locate the position of the user at this time, so as to obtain until this time The user position trajectory of the user up to this point. Based on this, in this scenario, if the user position trajectory reflects the user's intention to continue executing the navigation path, that is, if the user position trajectory indicates that the navigation path has not been performed, the server updates the user position node in the navigation path.

That is, if the end point of the user's position trajectory has not reached the end of the navigation path at this time, the user is considered to be still in the process of executing the navigation path, that is, still in the process of using the navigation application. At this time, The user position node indicating the user position in the navigation path will be updated according to the user position located by the last received target positioning signal strength vector, so that the user knows the current own position in real time.

In summary, by deploying several positioning devices at appropriate locations in the hotel scene, and based on the server-side positioning algorithm and the processing logic of user intention recognition, the hotel scene can automatically sense the user's intentions in order to provide users with more intelligent service.

FIG. 5 is a flowchart of Embodiment 5 of a service providing method according to an embodiment of the present invention. As shown in FIG. 5, the method may include the following steps:

501. Receive a service request triggered by a user. The user location and service content required by the user are included in the service request.

502: Determine a target service person whose current position matches the position corresponding to the service content and the location of the user from each service person according to the positioning signal strength vector reported by the employee terminal device of each service person.

503. Send the service request to the target service personnel.

In the hotel scene, users may have certain service requirements, such as the need for a data cable, the need to add a quilt, and so on. At this time, optionally, the user may trigger the above service request through the APP provided by the hotel in the user terminal device, or may also trigger the service request through other smart devices provided by the hotel, such as a smart TV, and the service request includes the location of the user And what services they need. Therefore, the server parses the service request to learn the user's intention, and then dispatches the most appropriate service personnel to provide the service to the user.

Among them, the determination of the most suitable service personnel (referred to as the target service personnel in this embodiment) takes into consideration the location of the service personnel, the location of the user, and the location corresponding to the service content required by the user. For example, suppose a user who lives on the third floor needs a data cable, and the data cable is in a storage room on the first floor. At this time, the server finds that the service staff A is closest to the storage room, and the server changes the Forwarding the service request to the service staff A is equivalent to dispatching the task to the service staff A; or, suppose both the service staff A and the service staff B are close to the storage room, but the service staff A has a jurisdiction of 2-3 Building, the jurisdiction of service staff B is 4-5th floor, then the server can further select service staff A from service staff A and service staff B to provide the service in combination with the user location (3rd floor).

In the above process, the location of each service person is involved. The location process of each service person is similar to the location location process of the user in the embodiment shown in FIG. 4, and will not be described again.

The service providing apparatus according to one or more embodiments of the present invention will be described in detail below. Those skilled in the art can understand that all of these service providing devices can be configured by using commercially available hardware components and configured by the steps taught in this solution.

FIG. 6 is a schematic structural diagram of a service providing apparatus according to an embodiment of the present invention. As shown in FIG. 6, the apparatus includes a data receiving module 11, a data processing module 12, and a service scheduling module 13.

The data receiving module 11 is configured to receive collected data of at least two collection devices.

A data processing module 12 is configured to identify a user position and trajectory on the collected data by combining position attributes associated with the collected data.

A service scheduling module 13 is configured to provide a user with a service corresponding to the user's intention according to the user's intention reflected by the user's location trajectory.

Optionally, the data processing module 12 may be configured to: perform user identification on the collected data to determine target collection data that sequentially collects the same user identity information; and according to the location attributes corresponding to the target collection data, respectively To determine a user location track of a user corresponding to the same user identity information.

Optionally, the at least two acquisition devices include N first cameras located on a floor walkway, and the acquisition data includes video data collected by the N first cameras; at this time, the data processing module 12 It can be used to perform face recognition on the video data collected by the N first cameras to determine M target video data that sequentially captures the same target face image, 1 <M≤N; if the target The face image exists in a preset legal user database, and the user position corresponding to the target face image is determined according to the floor number and location number associated with the respective M first cameras corresponding to the M target video data. Track.

Optionally, the data processing module 12 may be configured to: if the M first cameras correspond to the same floor number and the position numbers of the M first cameras reflect that the walking direction of the user corresponds to the elevator Direction, it is determined that the user position trajectory of the user is walking in the direction of the elevator.

Correspondingly, the service scheduling module 13 may be configured to control the elevator to run to the floor corresponding to the floor number according to the user's intention to board the elevator as reflected in the user location trajectory.

Optionally, the data processing module 12 may be configured to: if the M first cameras correspond to the same floor number and the position numbers of the M first cameras reflect that the user walks to the user Near the room, it is determined that the user position trajectory of the user is walking toward the user's room.

Correspondingly, the service scheduling module 13 may be configured to perform preset control on the smart device in the room corresponding to the user according to the user's intention to return to the room reflected by the user's location trajectory.

Optionally, the at least two acquisition devices include a second camera located at the door of the room. At this time, the data processing module 12 may be configured to perform user contouring on the video data collected by the N first cameras, respectively. Feature recognition to determine K target video data of the same target user's contour features, 1 <K≤N; if the K first cameras corresponding to the K target video data correspond to the same floor number and all The position numbers of the K first cameras reflect that a user with the contour characteristics of the target user walks to the target room, and then it is determined that the user position trajectory of the user is walking toward the target room.

Accordingly, the service scheduling module 13 may be configured to: control the second camera corresponding to the target room to collect video data according to the intention of entering the target room reflected by the user location trajectory; identify the second camera A face image in video data collected by a camera; if the face image matches a reference face image corresponding to the target room, preset control is performed on the smart device in the target room.

Optionally, the at least two acquisition devices include multiple user terminal devices, and the collected data includes positioning signal strength vectors and user terminal device identifiers collected by the multiple user terminal devices at different times, and the positioning signals The intensity vector corresponds to a plurality of pre-deployed positioning devices. At this time, the data processing module 12 may be used to: determine a target positioning signal strength vector sequence corresponding to the same target user terminal device identifier; and according to the target positioning signal strength The vector sequence determines a user position trajectory of a user corresponding to the target user terminal device identification.

Accordingly, optionally, the service scheduling module 13 may be configured to: if the user location trajectory reflects that the user intends to walk in the direction of the elevator of the target floor, control the elevator to run to the target floor.

Accordingly, optionally, the service scheduling module 13 may be further configured to: preset the smart device in the room corresponding to the user if the position track of the user reflects that the user intends to walk toward the user's room control.

Optionally, the data receiving module 11 may be further configured to receive a navigation request sent by the target user terminal device, where the navigation request is used to navigate the user from a current location to a destination location.

Accordingly, the data processing module 12 may be further configured to: send a navigation path from the current position to the destination position to the target user terminal device.

At this time, the service scheduling module 13 may be further configured to: if the user position trajectory reflects that the user intends to continue to execute the navigation path, update the user position node in the navigation path.

Optionally, the data processing module 12 may be configured to: for any positioning signal strength vector in the target positioning signal strength vector sequence, determine the strength of the positioning signal from the plurality of positioning devices with the positioning signal strength vector. A target positioning device corresponding to a signal strength greater than or equal to a preset threshold in the vector; acquiring a test position set corresponding to the target positioning device, wherein all the positions measured in advance at each test position in the test position set The signal strength of the target positioning device is greater than or equal to the preset threshold; and the target user terminal device is determined according to a distance between each of the positioning signal strength vectors and a reference positioning signal strength vector corresponding to each test position The user position of the corresponding user at this time is identified, wherein the reference positioning signal strength vector is the signal strengths of the plurality of positioning devices measured in advance at the corresponding test positions.

Optionally, the data receiving module 11 may be further configured to receive a service request triggered by a user, the user location of the user and the service content required by the user included in the service request.

Correspondingly, the data processing module 12 may be further configured to determine the location and location of the current location corresponding to the service content from the service personnel according to the positioning signal strength vector reported by the employee terminal device of each service personnel. The target service personnel whose location matches the user; and the service request is sent to the target service personnel.

The apparatus shown in FIG. 6 can execute the methods in the embodiments shown in FIG. 1 to FIG. 5. For the parts that are not described in detail in this embodiment, reference may be made to the related description of the embodiments shown in FIG. 1 to FIG. 5. For the implementation process and technical effect of the technical solution, refer to the description in the embodiments shown in FIG. 1 to FIG. 5, and details are not described herein again.

The internal function and structure of the service providing device have been described above. In a possible design, the structure of the service providing device may be implemented as an electronic device, such as a server. As shown in FIG. 7, the electronic device may include a processor 21 、 Memory 22. The memory 22 is configured to store a program that supports a service providing apparatus to execute the service providing method provided in the embodiments shown in FIG. 1 to FIG. 5, and the processor 21 is configured to execute the memory stored in the memory 22. program of.

The program includes one or more computer instructions, and when the one or more computer instructions are executed by the processor 21, the following steps can be implemented:

Receiving acquisition data from at least two acquisition devices;

Optionally, the processor 21 is further configured to execute all or part of the steps in the foregoing embodiments shown in FIG. 1 to FIG. 5.

The structure of the service providing apparatus may further include a communication interface 23, which is used for the service providing apparatus to communicate with other equipment or a communication network.

In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions used by the service providing device, which includes a program involved in executing the service providing method in the method embodiments shown in FIG. 1 to FIG. 5 described above. .

The device embodiments described above are only schematic, and the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located One place, or it can be distributed across multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the objective of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without creative labor.

Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary universal hardware platform, and of course, it can also be implemented by a combination of hardware and software. Based on such an understanding, the above-mentioned technical solution essentially or part that contributes to the existing technology may be embodied in the form of a computer product. The present invention may use one or more computer-usable storages containing computer-usable program code therein. The form of a computer program product implemented on a medium (including but not limited to disk storage, CD-ROM, optical storage, etc.).

The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and combinations of processes and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, so that instructions generated by the processor of the computer or other programmable data processing device may be used to Means for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to work in a specific manner such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, the instructions The device implements the functions specified in one or more flowcharts and / or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of steps can be performed on the computer or other programmable device to produce a computer-implemented process, which can be executed on the computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more flowcharts and / or one or more blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

Memory may include non-persistent memory, random access memory (RAM), and / or non-volatile memory in computer-readable media, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media includes permanent and non-persistent, removable and non-removable media. Information storage can be accomplished by any method or technology. Information may be computer-readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), and read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transmitting medium may be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media, such as modulated data signals and carrier waves.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, but not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still Modifications to the technical solutions described in the foregoing embodiments, or equivalent replacements of some of the technical features thereof; and these modifications or replacements do not depart the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

A service providing method, comprising:

Receiving acquisition data from at least two acquisition devices;

Combine the position attributes of the collected data with each other to perform user position trajectory recognition on the collected data;

And providing a user with a service corresponding to the user's intention according to the user's intention reflected by the user's position trajectory.
The method according to claim 1, further comprising:

Pushing service information to the user according to the user intention and the user characteristic information of the user.
The method according to claim 2, wherein the user characteristic information comprises at least one of the following information:

The time information corresponding to the user's intention, the user's behavior record information, and the user's check-in purpose.
The method according to any one of claims 1 to 3, wherein the performing user position trajectory identification on the collected data in combination with position attributes associated with the collected data each comprises:

Performing user identification on the collected data to determine target collection data that sequentially collects the same user identity information;

A user position trajectory of a user corresponding to the same user identity information is determined according to position attributes corresponding to the target collected data respectively.
The method according to claim 4, wherein the at least two acquisition devices include N first cameras located on a floor walking passage, and the acquisition data includes video data collected by the N first cameras;

The performing user identification on the collected data to determine target collection data that sequentially collects identity information of the same user includes:

Performing face recognition on the video data collected by the N first cameras to determine M target video data that sequentially captures the same target face image, 1 <M ≦ N;

The determining a user location trajectory of a user corresponding to the same user identity information according to location attributes corresponding to the target collected data includes:

If the target face image exists in a preset legal user database, determine the corresponding target face image corresponding to the floor number and position number of the M first cameras corresponding to the M target video data. User location trajectory of the user.
The method according to claim 5, wherein the determining of the user corresponding to the target face image is based on the floor number and location number associated with the respective M first cameras corresponding to the M target video data. User location trajectory, including:

If the M first cameras correspond to the same floor number and the position numbers of the M first cameras reflect that the walking direction of the user corresponds to the elevator direction, then it is determined that the user's position trajectory of the user is toward the elevator Walking direction

The step of providing a service corresponding to the user intent to the user according to the user intent reflected in the user location track includes:

And controlling the elevator to run to the floor corresponding to the floor number according to the intention of the user to take the elevator reflected by the user position trajectory.
The method according to claim 5, wherein the determining of the user corresponding to the target face image is based on the floor number and location number associated with the respective M first cameras corresponding to the M target video data. User location trajectory, including:

If the M first cameras correspond to the same floor number and the position numbers of the M first cameras reflect that the user walks near the user's room, it is determined that the user position trajectory of the user is toward Walking in the direction of the user's room;

The step of providing a service corresponding to the user intent to the user according to the user intent reflected in the user location track includes:

Perform preset control on the smart device in the room corresponding to the user according to the user's intention to return to the room reflected by the user's position trajectory.
The method according to claim 5, wherein the at least two acquisition devices include a second camera located at a door of the room;

The performing user identification on the collected data to determine target collection data that sequentially collects identity information of the same user includes:

Performing user profile feature recognition on the video data collected by the N first cameras to determine K target video data that sequentially capture the same target user profile feature, 1 <K≤N;

The determining a user location trajectory of a user corresponding to the same user identity information according to location attributes corresponding to the target collected data includes:

If the K first cameras corresponding to the K target video data correspond to the same floor number, and the position numbers of the K first cameras reflect that a user with the target user profile feature walks to the target room, Determining that the user position trajectory of the user is walking toward the target room;

The step of providing a service corresponding to the user intent to the user according to the user intent reflected in the user location track includes:

Controlling the second camera corresponding to the target room to collect video data according to the intention of entering the target room reflected by the user position trajectory;

Identifying a face image in video data collected by the second camera;

If the face image matches a reference face image corresponding to the target room, preset control is performed on the smart device in the target room.
The method according to claim 4, wherein the at least two acquisition devices include a plurality of user terminal devices, and the acquisition data includes positioning signal strength vectors and User terminal equipment identification, the positioning signal strength vector corresponding to a plurality of pre-deployed positioning devices;

The performing user identification on the collected data to determine target collection data that sequentially collects identity information of the same user includes:

Determining a target positioning signal strength vector sequence corresponding to the same target user terminal equipment identifier;

The determining a user location trajectory of a user corresponding to the same user identity information according to location attributes corresponding to the target collected data includes:

A user position trajectory of a user corresponding to the target user terminal device identifier is determined according to the target positioning signal strength vector sequence.
The method according to claim 9, wherein the providing the user with a service corresponding to the user intention according to the user intention reflected by the user location track comprises:

If the user position trajectory reflects that the user intends to walk in the direction of the elevator of the target floor, the elevator is controlled to run to the target floor.
The method according to claim 9, wherein the providing the user with a service corresponding to the user intention according to the user intention reflected by the user location track comprises:

If the user position trajectory reflects that the user intends to walk toward the user's room, preset control is performed on the smart device in the room corresponding to the user.
The method according to claim 9, further comprising:

Receiving a navigation request sent by the target user terminal device, where the navigation request is used to navigate the user from a current location to a destination location;

Sending a navigation path from the current location to the destination location to the target user terminal device;

The step of providing a service corresponding to the user intent to the user based on the user intent reflected in the user location trajectory includes:

If the user position trajectory reflects that the user intends to continue executing the navigation path, updating the user position node in the navigation path.
The method according to any one of claims 9 to 12, wherein the determining a user location trajectory of a user corresponding to the target user terminal device identifier according to the target positioning signal strength vector sequence comprises:

For any positioning signal strength vector in the target positioning signal strength vector sequence, a signal corresponding to a signal strength greater than or equal to a preset threshold in the any positioning signal strength vector is determined from the plurality of positioning devices. Target positioning device

Acquiring a set of test positions corresponding to the target positioning device, wherein the signal strength of the target positioning device measured in advance at each test position in the test position set is greater than or equal to the preset threshold;

Determining the user position of the user corresponding to the target user terminal device identifier at this time according to the distance between the any positioning signal strength vector and the reference positioning signal strength vector corresponding to each test position, wherein the reference positioning The signal strength vector is the signal strength of the plurality of positioning devices measured in advance at the corresponding test positions.
The method according to claim 13, further comprising:

Receiving a service request triggered by a user, the user location of the user and the service content required by the user included in the service request;

Determining the target service personnel whose current position matches the location corresponding to the service content and the location of the user from the service personnel according to the positioning signal strength vector reported by the employee terminal device of each service personnel;

Sending the service request to the target service person.
A service providing device, comprising:

A data receiving module, configured to receive data collected by at least two acquisition devices;

A data processing module, configured to identify a user's position and trajectory on the collected data by combining position attributes associated with the collected data;

A service scheduling module is configured to provide a user with a service corresponding to the user's intention according to the user's intention reflected by the user's location trajectory.