WO2020134231A1 - 信息推送方法、装置及信息展示系统 - Google Patents

信息推送方法、装置及信息展示系统 Download PDF

Info

Publication number
WO2020134231A1
WO2020134231A1 PCT/CN2019/107448 CN2019107448W WO2020134231A1 WO 2020134231 A1 WO2020134231 A1 WO 2020134231A1 CN 2019107448 W CN2019107448 W CN 2019107448W WO 2020134231 A1 WO2020134231 A1 WO 2020134231A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
target user
target
human body
video image
Prior art date
Application number
PCT/CN2019/107448
Other languages
English (en)
French (fr)
Inventor
车军
陈鑫嘉
陆海先
邓凡
许剑华
Original Assignee
杭州海康威视数字技术股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杭州海康威视数字技术股份有限公司 filed Critical 杭州海康威视数字技术股份有限公司
Publication of WO2020134231A1 publication Critical patent/WO2020134231A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0261—Targeted advertisements based on user location
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement

Definitions

  • the present application relates to the field of information push technology, and in particular, to an information push method and device, an information display system, an electronic device, and a computer-readable medium.
  • the above-mentioned information transmission method is an extensive information propagation method, which cannot effectively push the information to the target user accurately, resulting in a low information conversion rate. Therefore, the above method has the problems of low information push efficiency and poor push accuracy.
  • the purpose of this application is to provide an information pushing method and device, an information display system, an electronic device, and a computer-readable medium.
  • the first aspect of this application provides an information push method, including:
  • a second aspect of the present application provides an information pushing device, including:
  • a first human body feature extraction module configured to acquire a video image of a first target user through a first camera, and extract first human body feature information of the first target user according to the video image;
  • a surveillance video image matching module configured to obtain surveillance video images matched with the first human body characteristic information collected by a plurality of second cameras in the target place according to the first human body characteristic information
  • a motion path prediction module used to determine the current motion trajectory of the first target user in the target location according to the position of the first target user in the monitored video image, and predict the first target user Movement path within the first preset time period in the future;
  • the information pushing module is used to determine each information display device provided along the motion path, and push the information to be displayed associated with the first target user to the information display device.
  • a third aspect of the present application provides an information display system, including: a camera, a server, and information display equipment;
  • Both the camera and the information display device are in communication connection with the server;
  • the camera is used to collect video images in the target place and transmit the video images to the server;
  • the server is used to predict the movement path of the first target user by performing the method provided in the first aspect of the present application, and push the association with the first target user to each information display device provided along the movement path Information to be displayed;
  • the information display device is used to display the information to be displayed.
  • a fourth aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and executed by the processor to execute the computer program The method described in the first aspect of the present application.
  • a fifth aspect of the present application provides a computer-readable medium on which computer-readable instructions are stored, which can be executed by a processor to implement the method of the first aspect.
  • a sixth aspect of the present application provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the method described in the first aspect of the present application.
  • the information pushing method provided in the first aspect of the present application includes: acquiring a video image of a first target user through a first camera, and extracting first human body characteristic information of the first target user according to the video image; A human body characteristic information, acquiring monitoring video images matched with the first human body characteristic information collected by a plurality of second cameras in the target place; determining the location based on the position of the first target user in the monitoring video image Said the current movement trajectory of the first target user in the target place, and predicted the movement path of the first target user in the first preset time period in the future; determining each information display device set along the movement path, And push the information to be displayed associated with the first target user to the information display device.
  • the information push method provided in the first aspect of the present application can use monitoring video to determine the current movement track of the first target user, and accordingly predict the movement path of the first target user, and then The information display device set in the motion path pushes the information to be displayed, and when the user continues to move forward, the information to be displayed can be seen through the information display device. Therefore, the method can accurately deliver the information to be displayed to The first target user uses the information display device to realize the directional and regular push of the information to be displayed, which has high precision and push efficiency.
  • FIG. 1 shows a flowchart of an information pushing method provided by some embodiments of the present application
  • FIG. 2 shows a schematic diagram of an information pushing device provided by some embodiments of the present application
  • FIG. 3 shows a schematic diagram of an information display system provided by some embodiments of the present application.
  • FIG. 4 shows a schematic diagram of an electronic device provided by some embodiments of the present application.
  • FIG. 5 shows a schematic diagram of a computer-readable medium provided by some embodiments of the present application.
  • FIG. 6 shows a schematic diagram of another information display system provided by some embodiments of the present application.
  • FIG. 7 shows a schematic diagram of a coordinate system mapping provided by some embodiments of the present application.
  • first and second are used to distinguish different objects, not to describe a specific order.
  • the terms “including” and “having” and any variations thereof are intended to cover non-exclusive inclusions.
  • a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.
  • Embodiments of the present application provide an information pushing method and device, an information display system, an electronic device, and a computer-readable medium.
  • the embodiments of the present application will be described below with reference to the drawings.
  • FIG. 1 shows a flowchart of an information pushing method provided by some embodiments of the present application.
  • the information pushing method is applied to a server.
  • the server may include hardware.
  • Software can also be included.
  • the server includes hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server.
  • the server includes software, it can be implemented as multiple software or software modules (for example, to provide distributed services), or as a single software or software module. There is no specific limitation here.
  • the information pushing method may include the following steps:
  • Step S101 Obtain the video image of the first target user through the first camera, and extract the first human body characteristic information of the first target user according to the video image.
  • the first camera may be located at the entrance and exit of the target place, and when the first user enters the target place, the first camera may be used to capture the video image of the first target user, and then through image recognition technology
  • the first human body characteristic information of the first target user is extracted from the video image.
  • the first human body characteristic information may be used to represent one or more characteristics of the first target user's identity, gender, age, clothing characteristics, and posture characteristics, for example, the first human body characteristic information may be ⁇ Male, 26 years old, red Jacket ⁇ , indicating that the first target user is a male and is 26 years old. He was wearing a red coat when photographed by the first camera, so as to facilitate tracking of the first target user in the surveillance video according to the first human body characteristic information.
  • the target venue may include but is not limited to shopping malls, supermarkets, gourmet cities, office buildings, playgrounds, parks, communities, etc., and the embodiments of the present application are not limited.
  • Step S102 Acquire monitoring video images matched with the first human body characteristic information collected by multiple second cameras in the target location according to the first human body characteristic information.
  • a plurality of second cameras can also be provided in the target place, and the second camera can shoot surveillance video in the target place, and when the first target user moves in the target place, the first human body characteristic information can be used , From the surveillance video collected by the second camera, a surveillance video image that matches the first human body characteristic information is identified.
  • Step S103 Determine the current movement track of the first target user in the target place according to the position of the first target user in the monitoring video image, and predict the movement path of the first target user in the first preset time period in the future.
  • the position of the first target user in the surveillance video image may be expressed in the form of coordinates in the plane coordinate system of the four vertices of the rectangular image area where the first target user is located in the surveillance video image, According to the imaging principle of the camera, there is a correspondence between the position in the monitoring video image and the position in the actual space. Therefore, the current trajectory of the first target user in the target location can be determined according to the position of the first target user in the monitoring video image.
  • Step S104 Determine each information display device provided along the motion path, and push the information to be displayed associated with the first target user to the information display device.
  • the information to be displayed may be information associated with the first target user, and may specifically include information that meets the information acquisition needs of the first target user, or information that meets the interest preferences of the first target user, or includes needs Information delivered to the first target user.
  • the information to be displayed may be advertisement information of a business preferred by the first target user; for another example, when the target location is an office building, the information to be displayed may be a notification related to the first target user, Announcement information, etc.; for another example, when the target location is a playground, the information to be displayed may be the current number of people in the queue for the amusement item purchased by the first target user, the performance time of the program, etc.; for another example, when the target location is a community,
  • the information to be displayed may be information such as water and electricity charges and property fee payment notices for the first target user; the above are exemplary descriptions of the embodiments of the present application, and those skilled in the art may implement them directly or after modification in combination with the above descriptions. Within the scope of protection of this application.
  • the information push method provided in the above embodiments of the present application can use the surveillance video to determine the current movement trajectory of the first target user, and accordingly predict the movement path of the first target user, which can then follow the movement path
  • the information display device is set to push the information to be displayed.
  • the information to be displayed can be obtained through the information display device. Therefore, this method can accurately deliver the information to be displayed to the first target user, using the information display device to achieve The directional and regular push of the displayed information has high accuracy and push efficiency.
  • the information display device may push the information to be displayed to the user in one or more of images, text, audio, and video, and may directly push the information to be displayed to the user, or may indirectly push the information to be displayed to the user
  • the information may display the information to be displayed in the form of an image on the display screen of the information display device, or for example, may send the information to be displayed to the terminal device carried by the user, so that the user's terminal device displays the pending information to the user
  • the present information is not limited in this embodiment.
  • the current movement track of the first target user in the target location may be determined according to the position of the first target user in the monitoring video image, which may include:
  • the current movement track of the first target user in the target place is determined according to the time information and the plane coordinate position of the monitoring video images collected by each second camera.
  • the surveillance video in the target location can be collected by using the existing surveillance equipment (ie, the second camera), and the current movement track of the first target user can be determined according to the surveillance video. No additional equipment is required. Determine the current movement trajectory of the first target user and predict its future movement path when the first target user is actively involved, and then push the information to be displayed to the information display in front of the first target user in a targeted and real-time manner
  • the display in the device, where front refers to the direction of the first target user has the advantages of easy implementation, no additional cost, and high accuracy of information push.
  • the plane coordinate position of the first target user in the target place can be determined, include:
  • the mapping relationship corresponding to the second camera is determined according to the installation position of the second camera, and the mapping relationship includes the mapping relationship between the pixel coordinate system of the surveillance video image collected by the second camera and the plane coordinate system of the target site;
  • the pixel coordinates are converted into plane coordinate positions of the first target user in the target place.
  • the plane coordinate position of the first target user in the target place can be accurately determined according to the monitoring video image, which helps to improve the accuracy of the subsequent prediction of the movement path of the first target user.
  • the time information and plane of the monitoring video images collected by each second camera are based on The coordinate position to determine the current movement track of the first target user in the target place may include:
  • the plane coordinate positions collected from the same time are deduplicated to obtain the plane coordinate positions after deduplication;
  • the plane coordinate positions after deduplication are sorted to obtain the current movement trajectory of the first target user in the target place.
  • the plane coordinate positions of multiple first target users can be effectively deduplicated and the current motion trajectory can be generated.
  • deduplication data redundancy can be effectively reduced, the amount of calculation can be reduced, the calculation efficiency can be improved, and more Quickly and efficiently realize the push of the information to be displayed to ensure the real-time nature of the information push.
  • predicting the movement path of the first target user in the first preset time period in the future includes:
  • a motion trajectory prediction algorithm based on Kalman filtering is used to predict the motion path of the first target user in the first preset time period in the future.
  • the motion trajectory prediction algorithm based on Kalman filtering has high accuracy. Therefore, through the above-mentioned embodiment, the predicted motion path of the first target user in the target place can be predicted more accurately. It should be noted that the implementation of the present application is not limited to the motion trajectory prediction algorithm based on Kalman filtering, and other motion trajectory prediction technologies provided by related technologies may also be used. The present application is not limited by the embodiments.
  • predicting the movement path of the first target user in the first preset time period in the future may include:
  • the movement path of the first target user in the first preset time period in the future is predicted.
  • the current orientation information of the first target user and the travel route information in the target place can be combined to predict the movement path of the first target user in the target place.
  • the current orientation information of the first target user and the target place The traffic route information within serves as a constraint condition. Therefore, through the above embodiment, the movement path of the first target user in the target place can be more accurately predicted.
  • obtaining the surveillance video images collected by the multiple second cameras in the target place and matching the first human body characteristic information according to the first human body characteristic information may include:
  • the surveillance video image corresponding to the selected second human body characteristic information is determined as the surveillance video image matching the human body characteristic information.
  • the surveillance video image with matching information helps to improve the accuracy of the current motion path determined subsequently.
  • the method may further include: updating the first human body characteristic information according to the selected second human body characteristic information.
  • the method before pushing the information to be displayed associated with the first target user to the information display device, the method may further include:
  • the information to be displayed associated with the first target user is determined according to the preference information.
  • the preference information is used to indicate the interest preference of the first target user.
  • the first target user can be matched with the information to be displayed that better suits his interest preference according to the preference information, thereby achieving accurate push of the information to be displayed, because The information to be displayed conforms to the interest preference of the first target user. Therefore, the implementation manner of the present application will not arouse the user's dislike, which further helps to improve the information conversion rate.
  • determining the preference information of the first target user may include:
  • the preference information of the first target user is determined.
  • determining the historical behavior information of the target user may include
  • the historical behavior information of the first target user is determined according to the monitored video image.
  • any image-based behavior recognition method provided in the prior art may be used to determine the historical behavior information of the first target user, which is not limited in this embodiment of the present application.
  • the summary of some modified embodiments to determine each information display device provided along the motion path may include:
  • the specified distance can be set according to actual experience or user needs.
  • the mobility of the first target user is often limited. Therefore, within a certain period of time, the first target user can only move through the information display device within a certain distance and push it to other information display devices beyond the certain distance.
  • the information may not be available to the user, so this embodiment can enable the information display device within a specified distance in front of the first target user to display the information to be displayed, that is, the first target user can display related information
  • the information to be displayed can be targeted to accurately deliver the information to be displayed, improve the efficiency of information delivery, and help improve the information conversion rate.
  • the method may further include: The mobile terminal pushes the information to be displayed.
  • the information to be displayed may be pushed in the form of a short message, or may be pushed through a social platform, instant messaging software, or other application programs, which is not limited in this application.
  • the target place may include a consumption place such as a shopping mall
  • the preference information of the first target user may include consumption tendency information
  • the information to be displayed may include advertisement information associated with the consumption tendency of the first target user, corresponding To determine the preference information of the first target user, which may include:
  • the commodity information browsed by the first target user may refer to the information of the commodity browsed by the first target user;
  • the consumption tendency information of the first target user is determined.
  • Users browsing products are often out of interest in products. It can be considered that users are more likely to purchase viewed products than products not viewed by users. Therefore, the first target user can determine the first A target user's consumption tendency information.
  • determining the commodity information browsed by the first target user in the target place according to the monitoring video collected from the target place may include:
  • image feature extraction technology is used to extract the feature information of the commodity browsed by the first target user
  • the commodity information matching the feature information of the commodity browsed by the first target user from the commodity database.
  • a user browses a product it is often due to the user's interest in one or more features of the product. For example, when the user browses a pair of shoes, it may be due to the manufacturer of the shoe or the shoe. Is interested in color, so relative to product information that does not match the feature information of the product viewed by the first target user, the first target user is interested in product information that matches the feature information of the product viewed by the first target user The possibility is higher. Collecting and pushing to the first target user product information that matches the feature information of the product browsed by the first target user can achieve more accurate pushing of information to the user.
  • the product information viewed by the first target user can be determined through the monitoring video, and then the consumption of the first target user can be determined accordingly
  • the tendency information has higher real-time performance, and can more accurately determine the current preferred product of the first target user.
  • determining the consumption tendency information of the first target user according to the commodity information browsed by the first target user may include:
  • the consumption preference information decision information may include one or more of identity information, historical consumption information, and historical browsing information; the identity information may be used to indicate the identity of the first target user The historical consumption information may be used to indicate the commodities that the first target user has purchased within the preset historical time period, and the historical browsing information may be used to indicate the commodities that the first target user viewed within the preset historical time period.
  • the consumption target information of the first target user is determined according to the decision information of the commodity information and consumption trend information browsed by the first target user.
  • the consumption target information decision information such as the identity information, historical consumption information and historical browsing information of the first target user can be introduced to assist in determining the consumption target information of the first target user.
  • the user's consumption preferences therefore, through the above embodiment, the consumption tendency information of the first target user can be determined more accurately, so that the information display device in front of the first target user can be targeted Displaying the advertisement information associated with the consumption tendency of the first target user can guide the consumption behavior of the first target user in a more targeted and real-time manner, and realize refined business decision support.
  • FIG. 2 is a schematic diagram of an information pushing device according to an implementation manner of the present application. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method embodiment.
  • the device embodiments described below are only schematic.
  • an information pushing device 10 provided by an embodiment of the present application includes:
  • the first human body feature extraction module 101 is configured to obtain a video image of a first target user through a first camera, and extract first human body feature information of the first target user according to the video image;
  • the monitoring video image matching module 102 is configured to obtain monitoring video images collected by multiple second cameras in the target place and matching the first human body characteristic information according to the first human body characteristic information;
  • the motion path prediction module 103 is used to determine the current motion trajectory of the first target user in the target location according to the position of the first target user in the monitoring video image, and to predict the first target user within a first preset time period in the future The path of movement
  • the information pushing module 104 is used to determine each information display device provided along the motion path, and push the information to be displayed associated with the first target user to the information display device.
  • the motion path prediction module 103 includes:
  • a plane coordinate determination unit used to determine the plane coordinate position of the first target user in the target location according to the position of the first target user in the monitoring video image and the installation position of each second camera;
  • the movement trajectory determining unit is used to determine the current movement trajectory of the first target user in the target location according to the time information and plane coordinate positions of the monitoring video images collected by the respective second cameras.
  • the plane coordinate determination unit includes:
  • the pixel coordinate determination subunit is used to determine the pixel coordinates of the first target user in the surveillance video image collected by the second camera;
  • the mapping relationship determination subunit is used to determine the mapping relationship corresponding to the second camera according to the installation position of the second camera, and the mapping relationship includes the mapping relationship between the pixel coordinate system of the surveillance video image collected by the second camera and the plane coordinate system of the target site ;
  • the coordinate system mapping subunit is used to convert the pixel coordinates to the plane coordinate position of the first target user in the target location according to the mapping relationship.
  • the movement track determination unit includes:
  • the position deduplication sub-unit is used to deduplicate the plane coordinate positions collected at the same time according to the time information of the monitoring video images collected by each second camera, to obtain the plane coordinate positions after deduplication;
  • the position sorting subunit is used to sort the de-duplicated plane coordinate positions according to time information to obtain the current movement track of the first target user in the target place.
  • the motion path prediction module 103 includes:
  • the Kalman prediction unit is used to predict the movement path of the first target user in the first preset time period in the future according to the current movement trajectory, using a movement trajectory prediction algorithm based on Kalman filtering.
  • the motion path prediction module 103 includes:
  • An orientation information determining unit configured to determine the current orientation information of the first target user according to the monitored video image
  • Passing route determination unit used to obtain the passing route information in the target place
  • the movement path determining unit is configured to predict the movement path of the first target user in the first preset time period in the future based on the current movement trajectory, orientation information, and traffic route information.
  • the monitoring video image matching module 102 includes:
  • a second feature extraction unit configured to extract multiple second human feature information in the surveillance video images collected by multiple second cameras in the target location
  • a human body characteristic matching unit configured to match the first human body characteristic information with the second human body characteristic information one by one, and select the second human body characteristic information that matches the first human body characteristic information
  • the matching image selection unit is configured to determine the surveillance video image corresponding to the selected second human body characteristic information as the surveillance video image matching the human body characteristic information.
  • the device 10 further includes:
  • the human body characteristic update module is configured to update the first human body characteristic information according to the selected second human body characteristic information.
  • the device 10 further includes:
  • a preference information determination module configured to determine preference information of the first target user
  • the information to be displayed determination module is used to determine the information to be displayed associated with the first target user according to the preference information.
  • the preference information determination module includes:
  • the user information determination unit is used to determine the identity information and/or historical behavior information of the target user
  • the preference information determining unit is configured to determine the preference information of the first target user according to the identity information and/or historical behavior information.
  • the user information determination unit includes
  • the behavior information determination subunit is used to determine the historical behavior information of the first target user according to the monitored video image.
  • the information pushing module includes:
  • the information pushing unit is used to determine each information display device set along the motion path and within a specified distance in front of the first target user.
  • the information pushing device 20 provided by the embodiment of the present application has the same beneficial effects as the information pushing method provided by the foregoing embodiment of the present application based on the same inventive concept.
  • An embodiment of the present application also provides an information display system corresponding to the information push method provided in the foregoing embodiment.
  • the information display system and the aforementioned information push method are based on the same inventive concept, so the description is relatively simple.
  • the description of the embodiment of the information pushing method part of the content will not be repeated.
  • FIG. 3 is a schematic diagram of an information display system provided by an embodiment of the present application.
  • the information display system may include: a camera 21 (including a first camera located at the entrance and a second camera located in the target place), a server 22, and an information display device 23;
  • Both the camera 21 and the information display device 23 are in communication connection with the server 22;
  • the camera 21 is used to collect video images in the target place and transmit the video images to the server 22;
  • the server 22 is used to predict the movement path of the first target user by executing the information pushing method provided by any of the foregoing embodiments of the present application, and push the information associated with the first target user to each information display device 23 provided along the movement path Information to be displayed;
  • the information display device 23 is used to display the information to be displayed.
  • the information display system provided by the embodiment of the present application has the same beneficial effects as the information pushing method provided by the foregoing embodiment of the present application based on the same inventive concept.
  • Embodiments of the present application also provide an electronic device corresponding to the information pushing method provided in the foregoing embodiment.
  • the electronic device may be an electronic device for a server, such as a server, including an independent server and a distributed server cluster.
  • FIG. 4 illustrates a schematic diagram of an electronic device provided by some embodiments of the present application.
  • the electronic device 30 includes: a processor 300, a memory 301, a bus 302, and a communication interface 303.
  • the processor 300, the communication interface 303, and the memory 301 are connected through the bus 302;
  • the processor 300 executes the information pushing method provided in any of the foregoing embodiments of the present application when the computer program is executed.
  • the memory 301 may include a high-speed random access memory (RAM: Random Access Memory), or may include a non-volatile memory (non-volatile memory), such as at least one disk memory.
  • RAM Random Access Memory
  • non-volatile memory such as at least one disk memory.
  • the communication connection between the network element of the system and at least one other network element is achieved through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local network, metropolitan area network, etc. may be used.
  • the bus 302 may be an ISA bus, a PCI bus, an EISA bus, or the like.
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the memory 301 is used to store a program, and the processor 300 executes the program after receiving the execution instruction.
  • the information pushing method disclosed in any of the embodiments of the present application may be applied to the processor 300 or implemented by the processor 300 .
  • the processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in the processor 300 or instructions in the form of software.
  • the aforementioned processor 300 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP) or an application specific integrated circuit (ASIC), ready-made programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA ready-made programmable gate array
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present application may be implemented or executed.
  • the general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied and executed by a hardware decoding processor, or may be executed and completed by a combination of hardware and software modules in the decoding processor.
  • the software module may be located in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, and registers.
  • the storage medium is located in the memory 301, and the processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.
  • the electronic device provided by the embodiment of the present application and the method for pushing information provided by the embodiment of the present application are based on the same inventive concept and have the same beneficial effects.
  • Embodiments of the present application also provide a computer-readable medium corresponding to the information pushing method provided in the foregoing embodiment.
  • the computer-readable storage medium is an optical disc 40, on which a computer program is stored ( That is, a program product), when the computer program is executed by the processor, it will execute the information pushing method provided by any of the foregoing embodiments.
  • examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), and other types of random access Memory (RAM), read-only memory (ROM), electrically erasable and programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media are not repeated here.
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access Memory
  • ROM read-only memory
  • EEPROM electrically erasable and programmable read-only memory
  • flash memory or other optical and magnetic storage media are not repeated here.
  • the computer-readable storage medium provided by the foregoing embodiments of the present application and the information pushing method provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects.
  • Embodiments of the present application also provide a computer program product containing instructions corresponding to the information pushing method provided in the foregoing embodiment, which, when running on a computer, causes the computer to execute the information pushing method provided in any of the foregoing embodiments.
  • the computer program product containing instructions provided by the above embodiments of the present application and the information pushing method provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects.
  • FIG. 6 shows a schematic diagram of another information display system provided by some embodiments of the present application.
  • the information display system and the information provided by the foregoing embodiments The push method is based on the same inventive concept, and part of the content can be understood with reference to each other. In the description of the following embodiments, it can be understood by referring to the schematic diagram of the information display system shown in FIG. 3.
  • the information display system may include: a user identification subsystem 61, a user tracking subsystem 62, a commodity identification subsystem 63, a data analysis subsystem 64, and a data service subsystem 65;
  • the user identification subsystem 61 is used to identify the first target user entering the target location
  • the user tracking subsystem 62 is used to track the movement track of the first target user and predict the movement path of the first target user according to the current movement track of the first target user in the target venue;
  • the commodity identification subsystem 63 is used to identify the commodity information of the commodity browsed by the first target user
  • the data analysis subsystem 64 is used to determine preference information (such as consumption tendency information) of the first target user according to the commodity information of the commodity browsed by the first target user;
  • the data service subsystem 65 is used to display advertisement information associated with consumption tendency information on the movement path of the first target user.
  • the user identification subsystem 61 includes:
  • the identity recognition module is used to identify the first target user who enters the target location through image recognition technology based on the surveillance video collected from the target location.
  • the user identification subsystem 61 may analyze the video frames of the monitoring video collected by the monitoring device D installed in the target place, detect users entering the target place in real time, and use image recognition technology to identify the first target user to Identify the identity, gender, age, clothing characteristics and human body characteristics of the first target user.
  • the user recognition subsystem 61 can also collect face images of persons entering and exiting the target place and identify them to determine whether the person is a user or a store clerk.
  • the user tracking subsystem 62 can obtain the first target user and his body characteristics appearing in the scene by analyzing the video frames collected by the monitoring devices in the target place. The same first target user is on the same and different monitoring devices. When it appears in the field of view, it is determined whether it is the same monitoring device through comparison of human body characteristics. Thus, the current movement trajectory of the first target user in the entire target place is formed. Based on the above description, the user tracking subsystem 62 can determine which stores the first target user has entered, where they have stopped, the current location, and predicted their movement path.
  • the user tracking subsystem 62 may include:
  • the entrance and exit analysis module is used to determine whether the first target user enters or leaves the target place based on the surveillance video collected from the entrance and exit of the target place, and to determine the identity information and human body characteristics of the first target user entering the target place based on image recognition technology; Image recognition technology extracts the body characteristics of the first target user who enters the target location;
  • the target analysis module in the area is used to identify the first target user in the video frame of the monitoring video through image recognition technology based on the monitoring video collected from the target location, and to map the first target user in the video frame through coordinate system mapping The coordinate information of is mapped to the location information at the target site;
  • the first target user tracking module is used to match the human body characteristics and historical motion characteristics of the video frames of the monitoring video collected by multiple monitoring devices, determine the current motion trajectory of the first target user in the target venue, and according to the current motion trajectory Predict the movement path of the first target user in the target venue.
  • the target analysis module in the area may include:
  • the monitoring video coordinate calibration unit is used to establish a mapping relationship between the pixel coordinate system of the monitoring video collected by the monitoring device and the plane coordinate system of the target place.
  • the entrance and exit analysis module can have at least the following two functions:
  • Human body feature extraction A machine learning method is used to extract the complete human body features of each person (including users and shop assistants) entering and leaving the target place. The human body features can distinguish different users.
  • the embodiment of the present application uses the first target user as a guide object for exemplary illustration, and the first target user may be any user;
  • Movement state analysis According to the direction of the movement of the first target user and its characteristics in the image, analyze whether the first target user is entering the target place or leaving the target place, the motion state can be used to establish the current track index management unit Or delete the current motion track index of the first target user.
  • the target analysis module in the area can analyze the video frames of the monitoring video collected by the monitoring devices A, B, C, etc. in the target location to at least achieve the following functions:
  • Target detection and feature extraction A machine learning method is used to extract the complete human body characteristics of each person who enters and exits the target place, which can distinguish different users;
  • Coordinate system mapping map the coordinate information of the first target user in the pixel coordinate system of the video frame to the position information in the plane coordinate system of the target place, as shown in FIG. 7, for example, the first target user is in the monitoring device
  • the pixel coordinates (m, n) in the surveillance video of B are converted to the position coordinates (x, y) of the first target user in the plane coordinate system of the target place through the coordinate system mapping, where the previously established monitoring equipment can be used
  • the mapping relationship between the pixel coordinate system of the collected surveillance video and the plane coordinate system of the target site is coordinate system mapped.
  • the first target user tracking module can at least achieve the following functions:
  • Target management maintain the current trajectory index of the first target user in the target place (which can be implemented using a linked list), establish or delete the first target user according to the information that the first target user enters or leaves the target place determined by the entrance and exit analysis module , When the first target user enters, create a new current trajectory index for the first target user; when the first target user leaves, delete the current trajectory index;
  • Multi-target tracking using the human body characteristics of the first target user collected by multiple monitoring devices A, B, C, etc. in the target place in the time domain and the human body characteristics of the first target user in the current motion track index The comparison of spatio-temporal and image features, and associating the first target users whose consecutive frames meet the spatio-temporal constraints and the image similarity to form the current movement trajectory of the first target user in the plane coordinate system.
  • the first target user tracking module can also achieve the following functions:
  • Coordinate merging when the same first target user is photographed by multiple monitoring devices, the position coordinates under the plane coordinate system converted from each monitoring device should be the same, and the duplicate coordinates need to be merged at this time. Determine the unique location information of the first target user;
  • Trajectory prediction According to the historical current motion trajectory of the first target user in the current motion trajectory index, a prediction algorithm such as Kalman filtering is used to predict the current motion trajectory of the first target user to obtain the motion characteristics of the first target user, Determine the movement path of the first target user in the target place;
  • a prediction algorithm such as Kalman filtering is used to predict the current motion trajectory of the first target user to obtain the motion characteristics of the first target user, Determine the movement path of the first target user in the target place;
  • Target matching Using the previously extracted human body characteristics of the first target user and combining their motion characteristics, the first target user in the current motion track index is matched with the information extracted from the current frame on the space-time and image;
  • Feature update when the matching requirements are met in space-time and image, the human body characteristics and position information in the current index of the first target user's movement track are updated.
  • the first target user tracking module may include:
  • the current movement track index management unit is used to establish or delete the current movement track index of the first target user according to the first target user entering or leaving the target place;
  • Multi-monitoring device tracking unit used to match the similarity of human body features and historical motion features in multiple surveillance videos according to multiple surveillance videos taken by multiple surveillance devices, through matching of human body features and historical motion features
  • the first target user of the degree threshold condition associates, determines the current movement trajectory of the first target user, and predicts the movement path of the first target user in the target venue according to the current movement trajectory.
  • the multi-monitoring device tracking unit may include:
  • the coordinate merging subunit is used to merge multiple location information of the first target user determined according to the monitoring video collected by the multiple monitoring devices when the first target user is photographed by multiple monitoring devices to determine the first target The user's unique location information;
  • the trajectory prediction subunit is used for predicting the movement path of the first target user in the target place according to the current movement trajectory and using the current movement trajectory prediction algorithm.
  • the commodity identification subsystem 63 can analyze the video frames collected by the monitoring equipment installed in the store. When the user takes the commodity, the image features of the commodity are extracted and compared with the commodity registration data to obtain the identification of the commodity. Brand, type, model and other information.
  • the commodity identification subsystem 63 may include:
  • Commodity feature extraction module which is used to extract the feature information of the commodity browsed by the first target user based on the surveillance video collected from the target location, using image feature extraction technology
  • the commodity information matching module is used to query commodity information matching the feature information of the commodity browsed by the first target user from the commodity database.
  • the data analysis subsystem 64 can realize the following functions:
  • the data analysis subsystem 64 is also used to perform statistical analysis on the consumption information and browsing information of multiple first target users in the target venue to determine the first target users with different identity characteristics Shopping trends, and determine the popularity of each store.
  • the data service subsystem 65 can use the data of the data analysis subsystem to place advertisements and business information on the user's shopping path in real time. If the user does not form a consumption, he will actively push the shopping guide information of related products to the user through the mobile phone APP in the future.
  • the data service subsystem 65 is further used to push advertisement information associated with consumption tendency information to the mobile terminal used by the first target user.
  • the information display system provided by the embodiments of the present application has the same beneficial effects as the information pushing method provided by the foregoing embodiments of the present application based on the same inventive concept.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code that contains one or more of the Executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can also be executed in reverse order, depending on the functions involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented with a dedicated hardware-based system that performs specified functions or actions Or, it can be realized by a combination of dedicated hardware and computer instructions.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the unit is only a division of logical functions.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some communication interfaces, devices or units, and may be in electrical, mechanical, or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the technical solution of the present application essentially or part of the contribution to the related technology or part of the technical solution can be embodied in the form of a software product, the computer software product is stored in a storage medium, including several
  • the instructions are used to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

一种信息推送方法及装置、信息展示系统、电子设备以及计算机可读介质。其中，所述方法，包括：通过第一摄像机获取第一目标用户的视频图像，并根据所述视频图像提取第一目标用户的第一人体特征信息（S101）；根据所述第一人体特征信息，获取目标场所内多个第二摄像机采集的与第一人体特征信息相匹配的监控视频图像（S102）；根据所述第一目标用户在所述监控视频图像中的位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹，并预测第一目标用户在未来第一预设时间段内的运动路径（S103）；确定沿所述运动路径设置的各个信息展示设备，并向所述信息展示设备推送与第一目标用户相关联的待展示信息（S104）。该信息推送方法具有较高的精准性和推送效率。

Description

信息推送方法、装置及信息展示系统
本申请要求于2018年12月28日提交中国专利局、申请号为201811628227.5申请名称为“信息推送方法、装置及信息展示系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息推送技术领域，特别是涉及一种信息推送方法及装置、一种信息展示系统、一种电子设备以及计算机可读介质。
背景技术
随着计算机技术和互联网技术的快速发展，信息在人类日常生活和工作中起到越来越重要的作用，不同用户可能对不同的信息感兴趣，例如用户A可能对服装的信息感兴趣，而用户B可能对数码产品的信息感兴趣，而传统的通过公告栏、广告牌、广播等传递信息的方式，向不同的用户推送相同的信息，虽然受众面广但缺乏针对性，致使大多数情况下用户并不能通过上述传递信息的方式获取到感兴趣的信息，因此，上述信息传递方式属于粗放式的信息传播方式，无法高效地将信息准确地推送给目标用户，导致信息转换率较低，因此，上述方式具有信息推送效率较低、推送精准度较差的问题。
鉴于上述问题，需要提供一种精准度较高的信息推送方法，以提高信息推送效率。
发明内容
本申请的目的是提供一种信息推送方法及装置、一种信息展示系统、一种电子设备以及一种计算机可读介质。
本申请第一方面提供一种信息推送方法，包括：
通过第一摄像机获取第一目标用户的视频图像，并根据所述视频图像提取所述第一目标用户的第一人体特征信息；
根据所述第一人体特征信息，获取目标场所内多个第二摄像机采集的与所述第一人体特征信息相匹配的监控视频图像；
根据所述第一目标用户在所述监控视频图像中的位置，确定所述第一目 标用户在所述目标场所内的当前运动轨迹，并预测所述第一目标用户在未来第一预设时间段内的运动路径；
确定沿所述运动路径设置的各个信息展示设备，并向所述信息展示设备推送与所述第一目标用户相关联的待展示信息。
本申请第二方面提供一种信息推送装置，包括：
第一人体特征提取模块，用于通过第一摄像机获取第一目标用户的视频图像，并根据所述视频图像提取所述第一目标用户的第一人体特征信息；
监控视频图像匹配模块，用于根据所述第一人体特征信息，获取目标场所内多个第二摄像机采集的与所述第一人体特征信息相匹配的监控视频图像；
运动路径预测模块，用于根据所述第一目标用户在所述监控视频图像中的位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹，并预测所述第一目标用户在未来第一预设时间段内的运动路径；
信息推送模块，用于确定沿所述运动路径设置的各个信息展示设备，并向所述信息展示设备推送与所述第一目标用户相关联的待展示信息。
本申请第三方面提供一种信息展示系统，包括：摄像机、服务器和信息展示设备；
所述摄像机和所述信息展示设备均与所述服务器通信连接；
所述摄像机用于采集目标场所内的视频图像，并将所述视频图像传输至所述服务器；
所述服务器用于通过执行本申请第一方面提供的方法，预测所述第一目标用户的运动路径，并向沿所述运动路径设置的各个信息展示设备推送与所述第一目标用户相关联的待展示信息；
所述信息展示设备用于展示所述待展示信息。
本申请第四方面提供一种电子设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器运行所述计算机程序时执行以实现本申请第一方面所述的方法。
本申请第五方面提供一种计算机可读介质，其上存储有计算机可读指令，所述计算机可读指令可被处理器执行以实现第一方面所述的方法。
本申请第六方面提供一种包含指令的计算机程序产品，当其在计算机上 运行时，使得计算机执行本申请第一方面所述的方法。
本申请第一方面提供的信息推送方法，包括：通过第一摄像机获取第一目标用户的视频图像，并根据所述视频图像提取所述第一目标用户的第一人体特征信息；根据所述第一人体特征信息，获取目标场所内多个第二摄像机采集的与所述第一人体特征信息相匹配的监控视频图像；根据所述第一目标用户在所述监控视频图像中的位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹，并预测所述第一目标用户在未来第一预设时间段内的运动路径；确定沿所述运动路径设置的各个信息展示设备，并向所述信息展示设备推送与所述第一目标用户相关联的待展示信息。相较于相关技术，本申请第一方面提供的信息推送方法，可以利用监控视频确定第一目标用户的当前运动轨迹，并据此预测所述第一目标用户的运动路径，进而可以向沿所述运动路径设置的信息展示设备推送待展示信息，当用户继续前行时即可通过所述信息展示设备看到所述待展示信息，因此，本方法可以精准地将所述待展示信息投放给所述第一目标用户，利用所述信息展示设备实现对所述待展示信息的定向、定时推送，具有较高的精准性和推送效率。
附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本申请的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了本申请的一些实施方式所提供的一种信息推送方法的流程图；
图2示出了本申请的一些实施方式所提供的一种信息推送装置的示意图；
图3示出了本申请的一些实施方式所提供的一种信息展示系统的示意图；
图4示出了本申请的一些实施方式所提供的一种电子设备的示意图；
图5示出了本申请的一些实施方式所提供的一种计算机可读介质的示意图；
图6示出了本申请的一些实施方式所提供的另一种信息展示系统的示意图；
图7示出了本申请的一些实施方式所提供的一种坐标系映射的示意图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施方式。虽然附图中显示了本公开的示例性实施方式，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施方式所限制。相反，提供这些实施方式是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
需要注意的是，除非另有说明，本申请使用的技术术语或者科学术语应当为本申请所属领域技术人员所理解的通常意义。
另外，术语“第一”和“第二”是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
本申请实施方式提供了一种信息推送方法及装置、一种信息展示系统、一种电子设备以及一种计算机可读介质。下面结合附图对本申请的实施例进行说明。
请参考图1，其示出了本申请的一些实施方式所提供的一种信息推送方法的流程图，该信息推送方法应用于服务端，本申请的一些实施例中，服务端可以包括硬件，也可以包括软件。当服务端包括硬件时，可以实现成多个服 务端组成的分布式服务端集群，也可以实现成单个服务端。当服务端包括软件时，可以实现成多个软件或软件模块(例如用来提供分布式服务)，也可以实现成单个软件或软件模块。在此不做具体限定。
如图1所示，信息推送方法，可以包括以下步骤：
步骤S101：通过第一摄像机获取第一目标用户的视频图像，并根据视频图像提取第一目标用户的第一人体特征信息。
本申请的一种实施方式中，第一摄像机可以设于目标场所的出入口处，当第一用户进入该目标场所时，可以利用第一摄像机拍摄第一目标用户的视频图像，然后通过图像识别技术从视频图像中提取出第一目标用户的第一人体特征信息。其中，第一人体特征信息可以用于表示第一目标用户的身份、性别、年龄、衣着特征、姿态特征中的一个或多个特征，例如第一人体特征信息可以是{男，26岁，红色外套}，表示第一目标用户为男性，年龄为26岁，被第一摄像机拍摄到时穿着红色外套，以便于根据第一人体特征信息实现对监控视频中第一目标用户的跟踪。
目标场所可以包括但不限于商场、超市、美食城、办公楼、游乐场、公园、小区等，本申请实施例不做限定。
步骤S102：根据第一人体特征信息，获取目标场所内多个第二摄像机采集的与第一人体特征信息相匹配的监控视频图像。
在一些实施方式中，还可以在目标场所内设置多个第二摄像机，第二摄像机可以拍摄目标场所内的监控视频，当第一目标用户在目标场所内移动时，可以根据第一人体特征信息，从第二摄像机采集监控视频中识别出与第一人体特征信息相匹配的监控视频图像。
步骤S103：根据第一目标用户在监控视频图像中的位置，确定第一目标用户在目标场所内的当前运动轨迹，并预测第一目标用户在未来第一预设时间段内的运动路径。
在一些实施方式中，第一目标用户在监控视频图像中的位置，可以是第一目标用户在监控视频图像中所处矩形图像区域的四个顶点在平面坐标系中 的坐标的形式表示的，根据摄像机的成像原理，监控视频图像中的位置和实际空间的位置存在对应关系，因此可以根据第一目标用户在监控视频图像中的位置，确定第一目标用户在目标场所内的当前运动轨迹。
根据当前运动轨迹，预测第一目标用户在未来第一预设时间段内的运动路径，可以根据实际需求，选用不同的轨迹预测算法，本实施例对此不做限制。
步骤S104：确定沿运动路径设置的各个信息展示设备，并向信息展示设备推送与第一目标用户相关联的待展示信息。
其中，待展示信息可以是与第一目标用户相关联的信息，具体的，可以包括符合第一目标用户的信息获取需求的信息，或者包括符合第一目标用户的兴趣偏好的信息，或者包括需要投放给第一目标用户的信息。
例如，当目标场所为商场时，待展示信息可以是第一目标用户喜欢的商家的广告信息；又如，当目标场所为办公楼时，待展示信息可以是与第一目标用户相关的通知、公告信息等；再如，当目标场所为游乐场时，待展示信息可以是第一目标用户已购买的游乐项目的当前排队人数、节目演出时间等信息；另如，当目标场所为社区时，待展示信息可以是针对第一目标用户的水电费、物业费缴费通知等信息；以上均为本申请实施例的示例性说明，本领域技术人员可以结合上述说明直接或变更后实施，其均应在本申请的保护范围之内。
相较于相关技术，本申请上述实施例提供的信息推送方法，可以利用监控视频确定第一目标用户的当前运动轨迹，并据此预测第一目标用户的运动路径，进而可以向沿该运动路径设置的信息展示设备推送待展示信息，当用户继续前行时即可通过信息展示设备获取待展示信息，因此，本方法可以精准地将待展示信息投放给第一目标用户，利用信息展示设备实现对待展示信息的定向、定时推送，具有较高的精准性和推送效率。其中，信息展示设备可以是以图像、文本、音频、视频中的一种或多种方式向用户推送待展示信息，并且可以是直接向用户推送待展示信息，也可以是间接向用户推送待展示信息，例如，可以是在信息展示设备的显示屏上以图像的形式显示待展示 信息，又例如，可以是向用户携带的终端设备发送待展示信息，以使得用户的终端设备向用户显示该待展示信息，本实施例对此不做限制。
在本申请实施例的一些变更实施方式中，可以根据第一目标用户在监控视频图像中的位置，确定第一目标用户在目标场所内的当前运动轨迹，可以包括：
根据第一目标用户在监控视频图像中的位置、以及各个第二摄像机的安装位置，确定第一目标用户在目标场所内的平面坐标位置；
根据各个第二摄像机采集监控视频图像的时间信息以及平面坐标位置，确定第一目标用户在目标场所内的当前运动轨迹。
通过本实施方式，可以借助现有的监控设备(即第二摄像机)采集目标场所内的监控视频，并根据监控视频确定第一目标用户的当前运动轨迹，不需要额外添置设备，即可在不需要第一目标用户主动参与的情况下确定第一目标用户的当前运动轨迹，并预测其未来的运动路径，进而可以针对性地、实时地将待展示信息推送至第一目标用户前方的信息展示设备中进行展示，其中，前方是指第一目标用户前进的方向，具有便于实施、不需额外付出成本、信息推送准确性高等优点。
在本申请实施例的另一些变更实施方式中，根据第一目标用户在监控视频图像中的位置、以及各个第二摄像机的安装位置，确定第一目标用户在目标场所内的平面坐标位置，可以包括：
确定第一目标用户在第二摄像机采集的监控视频图像中的像素坐标；以及，
根据第二摄像机的安装位置，确定第二摄像机对应的映射关系，映射关系包括第二摄像机采集的监控视频图像的像素坐标系与目标场所的平面坐标系的映射关系；
根据映射关系，将像素坐标转换为第一目标用户在目标场所内的平面坐标位置。
通过本实施方式，可以根据监控视频图像准确地确定出第一目标用户在目标场所内的平面坐标位置，有助于提高后续预测第一目标用户的运动路径准确性。
考虑到，同一时间可能有多个第二摄像机拍摄到第一目标用户，因此，在上述实施方式的基础上，在一些变更实施方式中，根据各个第二摄像机采集监控视频图像的时间信息以及平面坐标位置，确定第一目标用户在目标场所内的当前运动轨迹，可以包括：
根据各个第二摄像机采集监控视频图像的时间信息，对采集自同一时间的平面坐标位置进行去重，得到去重后的平面坐标位置；
根据时间信息，对去重后的平面坐标位置进行排序，得到第一目标用户在目标场所内的当前运动轨迹。
通过本实施方式，可以有效地对多个第一目标用户的平面坐标位置进行去重并生成当前运动轨迹，通过去重可以有效地降低数据冗余，降低运算量，提高运算效率，进而可以更加快速、高效地实现待展示信息的推送，确保信息推送的实时性。
在本申请实施例的另一些变更实施方式中，预测第一目标用户在未来第一预设时间段内的运动路径，包括：
根据当前运动轨迹，采用基于卡尔曼滤波的运动轨迹预测算法预测第一目标用户在未来第一预设时间段内的运动路径。
基于卡尔曼滤波的运动轨迹预测算法具有较高的准确性，因此，通过上述实施方式，可以较为准确地预测第一目标用户在目标场所内的预测运动路径。需要说明的是，本申请实施方式并不限于基于卡尔曼滤波的运动轨迹预测算法，也可以采用相关技术提供的其他的运动轨迹预测技术，本申请是实施例不做限定。
在本申请实施例的另一些变更实施方式中，预测第一目标用户在未来第一预设时间段内的运动路径，可以包括：
根据监控视频图像确定第一目标用户当前的朝向信息；
获取目标场所内的通行路线信息；
根据当前运动轨迹、朝向信息和通行路线信息，预测第一目标用户在未来第一预设时间段内的运动路径。
通过本实施方式，可以结合第一目标用户当前的朝向信息和目标场所内的通行路线信息，对第一目标用户在目标场所内的运动路径进行预测，第一目标用户当前的朝向信息和目标场所内的通行路线信息起到约束条件的作用，因此，通过上述实施方式，可以更加精准地对第一目标用户在目标场所内的运动路径进行预测。
在本申请实施例的另一些变更实施方式中，根据第一人体特征信息，获取目标场所内多个第二摄像机采集的与第一人体特征信息相匹配的监控视频图像，可以包括：
提取目标场所内多个第二摄像机采集的监控视频图像中的多个第二人体特征信息；
将第一人体特征信息与第二人体特征信息进行匹配，选出与第一人体特征信息相匹配的第二人体特征信息；
将选出的第二人体特征信息所对应的监控视频图像确定为与人体特征信息相匹配的监控视频图像。
可以认为不同用户的人体特征不同，因此如果两个人体特征信息相匹配，则可以认为这两个人体特征信息是通过采集同一用户得到的，因此通过本实施方式，可以准确地找出与人体特征信息相匹配的监控视频图像，有助于提高后续确定的当前运动路径的精准度。
在本申请实施例的另一些变更实施方式中，方法还可以包括：根据选出的第二人体特征信息更新第一人体特征信息。
通过本实施方式，可以根据大量的第二人体特征信息对第一人体特征信息进行迭代更新，从而提高第一人体特征信息的全面性和准确性，有助于提 高后续确定的当前运动路径的精准度。
在本申请实施例的另一些变更实施方式中，向信息展示设备推送与第一目标用户相关联的待展示信息之前，还可以包括：
确定第一目标用户的偏好信息；
根据偏好信息确定与第一目标用户相关联的待展示信息。
其中，偏好信息用于表示第一目标用户的兴趣偏好，通过本实施方式，可以根据偏好信息为第一目标用户匹配更符合其兴趣偏好的待展示信息，进而实现待展示信息的精准推送，由于待展示信息符合第一目标用户的兴趣偏好，因此，本申请实施方式不会引起用户的反感，进而有助于提高信息转换率。
在上述实施方式的基础上，在本申请实施例的一些变更实施方式中，确定第一目标用户的偏好信息，可以包括：
确定目标用户的身份信息和/或历史行为信息；
根据身份信息和/或历史行为信息，确定第一目标用户的偏好信息。
在一些实施方式中，确定目标用户的历史行为信息，可以包括
根据监控视频图像确定第一目标用户的历史行为信息。
具体的，可以采用现有技术中提供的任意基于图像的行为识别方法确定第一目标用户的历史行为信息，本申请实施例不做限定。
在前述任一实施方式的基础上，在一些变更实施方式汇总，确定沿运动路径设置的各个信息展示设备，可以包括：
确定沿运动路径设置的、在第一目标用户前方指定距离内的各个信息展示设备。
其中，指定距离可以根据实际经验或者用户需求进行设置。第一目标用户的移动能力往往是有限的，因此在一定时间段内第一目标用户沿运动路径前进，只能经过一定距离内的信息展示设备，而对于该一定距离以外的其他 信息展示设备推送的信息可能无法被用户获取到，因此通过本实施方式，可以使得在第一目标用户前方指定距离内的信息展示设备展示待展示信息，即可以在第一目标用户靠近后再展示与其相关联的待展示信息，从而可以有针对性地实现待展示信息的精准投放，提升信息投放效率，且有利于提升信息转化率。
考虑到，第一目标用户可能因聊天等原因忽视信息展示设备展示的待展示信息，因此，在本申请实施例提供的一些实施方式中，方法，还可以包括：向第一目标用户所使用的移动终端推送待展示信息。本实施方式中，待展示信息可以以短信的形式进行推送，也可以通过社交平台、即时通信软件、或其他应用程序等进行推送，本申请对此并不限制。
在一些变更实施方式中，目标场所可以包括商场等消费场所，第一目标用户的偏好信息可以包括消费倾向信息，待展示信息可以包括与第一目标用户的消费倾向相关联的广告信息，相应的，确定第一目标用户的偏好信息，可以包括：
根据采集自目标场所内的监控视频确定第一目标用户在目标场所内的所浏览的商品信息，第一目标用户所浏览的商品信息可以是指第一目标用户所浏览的商品的信息；
根据第一目标用户所浏览的商品信息，确定第一目标用户的消费倾向信息。用户浏览商品往往是出于对商品的兴趣，可以认为相比于用户未浏览的商品，用户购买浏览过的商品的可能性更高，因此可以根据第一目标用户所浏览的商品信息，确定第一目标用户的消费倾向信息。
其中，根据采集自目标场所内的监控视频确定第一目标用户在目标场所内的所浏览的商品信息，可以包括：
根据采集自目标场所内的监控视频，采用图像特征提取技术提取第一目标用户所浏览的商品的特征信息；
从商品数据库中查询与第一目标用户所浏览的商品的特征信息相匹配的商品信息。用户浏览一件商品，往往是出于用户对该商品的一个或多个特征 的兴趣，例如用户浏览一双鞋，可能是出于对该鞋的生产厂家感兴趣，也可能是出于对该鞋的颜色感兴趣，因此相对于与第一目标用户所浏览的商品的特征信息不匹配的商品信息，第一目标用户对与第一目标用户所浏览的商品的特征信息相匹配的商品信息感兴趣的可能性更高，采集并向第一目标用户推送与第一目标用户所浏览的商品的特征信息相匹配的商品信息，可以实现更准确地向用户推送信息。
通过上述实施方式，可以通过监控视频确定第一目标用户浏览过(包括拿起商品进行浏览、和/或距离商品在指定距离内进行浏览)的商品信息，进而据此确定第一目标用户的消费倾向信息，具有较高的实时性，可以更为准确地判断第一目标用户当前所偏好的商品。
在另一些实施方式中，根据第一目标用户所浏览的商品信息，确定第一目标用户的消费倾向信息，可以包括：
确定第一目标用户的消费倾向信息决策信息，消费倾向信息决策信息可以包括身份信息、历史消费信息和历史浏览信息中的一种或多种信息；身份信息可以用于表示第一目标用户的身份，历史消费信息可以用于表示第一目标用户在预设历史时间段内购买过的商品，历史浏览信息可以用于表示第一目标用户在预设历史时间段内浏览过的商品。
根据第一目标用户所浏览的商品信息和消费倾向信息决策信息，确定第一目标用户的消费倾向信息。
用户感兴趣的商品可能较多，而在一定时间段内用户的行为可能只能够反映出用户感兴趣的部分商品。例如，用户对数码产品和服装都感兴趣，但是出于一些原因，用户只浏览了数码产品，则仅根据用户所浏览的商品信息，难以准确判断出用户实际的消费偏好。而通过上述实施方式，可以引入第一目标用户的身份信息、历史消费信息和历史浏览信息等消费倾向信息决策信息，以辅助确定第一目标用户的消费倾向信息，由于消费倾向信息决策信息能够反映出较长时间尺度上，用户的消费偏好，因此，通过上述实施方式，可以更加准确地确定第一目标用户的消费倾向信息，从而可以在第一目标用户前方的信息展示设备中有针对性地展示与该第一目标用户的消费倾向相关 联的广告信息，可以更具针对性地、实时性地对第一目标用户的消费行为进行引导，实现精细化的经营决策支持。
在上述的实施例中，提供了一种信息推送方法，与之相对应的，本申请还提供一种信息推送装置。请参考图2，其为本申请实施方式所提供的一种信息推送装置的示意图。由于装置实施例基本相似于方法实施例，所以描述得比较简单，相关之处参见方法实施例的部分说明即可。下述描述的装置实施例仅仅是示意性的。
如图2所示，本申请实施例提供的一种信息推送装置10，包括：
第一人体特征提取模块101，用于通过第一摄像机获取第一目标用户的视频图像，并根据视频图像提取第一目标用户的第一人体特征信息；
监控视频图像匹配模块102，用于根据第一人体特征信息，获取目标场所内多个第二摄像机采集的与第一人体特征信息相匹配的监控视频图像；
运动路径预测模块103，用于根据第一目标用户在监控视频图像中的位置，确定第一目标用户在目标场所内的当前运动轨迹，并预测第一目标用户在未来第一预设时间段内的运动路径；
信息推送模块104，用于确定沿运动路径设置的各个信息展示设备，并向信息展示设备推送与第一目标用户相关联的待展示信息。
在本申请实施例的一些变更实施方式中，运动路径预测模块103，包括：
平面坐标确定单元，用于根据第一目标用户在监控视频图像中的位置、以及各个第二摄像机的安装位置，确定第一目标用户在目标场所内的平面坐标位置；
运动轨迹确定单元，用于根据各个第二摄像机采集监控视频图像的时间信息以及平面坐标位置，确定第一目标用户在目标场所内的当前运动轨迹。
在本申请实施例的一些变更实施方式中，平面坐标确定单元，包括：
像素坐标确定子单元，用于确定第一目标用户在第二摄像机采集的监控视频图像中的像素坐标；以及，
映射关系确定子单元，用于根据第二摄像机的安装位置，确定第二摄像机对应的映射关系，映射关系包括第二摄像机采集的监控视频图像的像素坐标系与目标场所的平面坐标系的映射关系；
坐标系映射子单元，用于根据映射关系，将像素坐标转换为第一目标用户在目标场所内的平面坐标位置。
在本申请实施例的一些变更实施方式中，运动轨迹确定单元，包括：
位置去重子单元，用于根据各个第二摄像机采集监控视频图像的时间信息，对采集自同一时间的平面坐标位置进行去重，得到去重后的平面坐标位置；
位置排序子单元，用于根据时间信息，对去重后的平面坐标位置进行排序，得到第一目标用户在目标场所内的当前运动轨迹。
在本申请实施例的一些变更实施方式中，运动路径预测模块103，包括：
卡尔曼预测单元，用于根据当前运动轨迹，采用基于卡尔曼滤波的运动轨迹预测算法预测第一目标用户在未来第一预设时间段内的运动路径。
在本申请实施例的一些变更实施方式中，运动路径预测模块103，包括：
朝向信息确定单元，用于根据监控视频图像确定第一目标用户当前的朝向信息；
通行路线确定单元，用于获取目标场所内的通行路线信息；
运动路径确定单元，用于根据当前运动轨迹、朝向信息和通行路线信息，预测第一目标用户在未来第一预设时间段内的运动路径。
在本申请实施例的一些变更实施方式中，监控视频图像匹配模块102，包括：
第二特征提取单元，用于提取目标场所内多个第二摄像机采集的监控视 频图像中的多个第二人体特征信息；
人体特征匹配单元，用于将第一人体特征信息与第二人体特征信息一一进行匹配，选出与第一人体特征信息相匹配的第二人体特征信息；
匹配图像选取单元，用于将选出的第二人体特征信息所对应的监控视频图像确定为与人体特征信息相匹配的监控视频图像。
在本申请实施例的一些变更实施方式中，装置10，还包括：
人体特征更新模块，用于根据选出的第二人体特征信息更新第一人体特征信息。
在本申请实施例的一些变更实施方式中，装置10，还包括：
偏好信息确定模块，用于确定第一目标用户的偏好信息；
待展示信息确定模块，用于根据偏好信息确定与第一目标用户相关联的待展示信息。
在本申请实施例的一些变更实施方式中，偏好信息确定模块，包括：
用户信息确定单元，用于确定目标用户的身份信息和/或历史行为信息；
偏好信息确定单元，用于根据身份信息和/或历史行为信息，确定第一目标用户的偏好信息。
在本申请实施例的一些变更实施方式中，用户信息确定单元，包括
行为信息确定子单元，用于根据监控视频图像确定第一目标用户的历史行为信息。
在本申请实施例的一些变更实施方式中，信息推送模块，包括：
信息推送单元，用于确定沿运动路径设置的、在第一目标用户前方指定距离内的各个信息展示设备。
本申请实施例提供的信息推送装置20，与本申请前述实施例提供的信息推送方法出于相同的发明构思，具有相同的有益效果。
本申请实施例还提供一种与前述实施例所提供的信息推送方法对应的信息展示系统，信息展示系统与前述信息推送方法出于相同的发明构思，所以描述得比较简单，相关内容请参照上述关于信息推送方法的实施例说明，部分内容不再赘述。
请参考图3，其为本申请实施方式所提供的一种信息展示系统的示意图。如图所示，信息展示系统可以包括：摄像机21(包括位于出入口处的第一摄像机和位于目标场所内的第二摄像机)、服务器22和信息展示设备23；
摄像机21和信息展示设备23均与服务器22通信连接；
摄像机21用于采集目标场所内的视频图像，并将视频图像传输至服务器22；
服务器22用于通过执行本申请前述任一实施方式所提供的信息推送方法，预测第一目标用户的运动路径，并向沿运动路径设置的各个信息展示设备23推送与第一目标用户相关联的待展示信息；
信息展示设备23用于展示待展示信息。
本申请实施例提供的信息展示系统，与本申请前述实施例提供的信息推送方法出于相同的发明构思，具有相同的有益效果。
本申请实施方式还提供一种与前述实施方式所提供的信息推送方法对应的电子设备，电子设备可以是用于服务端的电子设备，例如服务器，包括独立的服务器和分布式服务器集群等。请参考图4，其示出了本申请的一些实施方式所提供的一种电子设备的示意图。如图4所示，电子设备30包括：处理器300，存储器301，总线302和通信接口303，处理器300、通信接口303和存储器301通过总线302连接；存储器301中存储有可在处理器300上运行的计算机程序，处理器300运行计算机程序时执行本申请前述任一实施方式所提供的信息推送方法。
其中，存储器301可能包含高速随机存取存储器(RAM：Random Access Memory)，也可能还包括非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。通过至少一个通信接口303(可以是有线或者无线)实现该系统网元与至少一个其他网元之间的通信连接，可以使用互联网、广域网、本地网、城域网等。
总线302可以是ISA总线、PCI总线或EISA总线等。总线可以分为地址总线、数据总线、控制总线等。其中，存储器301用于存储程序，处理器300在接收到执行指令后，执行程序，前述本申请实施例任一实施方式揭示的信息推送方法可以应用于处理器300中，或者由处理器300实现。
处理器300可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器300中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器300可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)、网络处理器(Network Processor，简称NP)等；还可以是数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器301，处理器300读取存储器301中的信息，结合其硬件完成上述方法的步骤。
本申请实施例提供的电子设备与本申请实施例提供的用于信息推送方法出于相同的发明构思，具有相同的有益效果。
本申请实施方式还提供一种与前述实施方式所提供的信息推送方法对应的计算机可读介质，请参考图5，其示出的计算机可读存储介质为光盘40，其上存储有计算机程序(即程序产品)，计算机程序在被处理器运行时，会执行前述任意实施方式所提供的信息推送方法。
需要说明的是，计算机可读存储介质的例子还可以包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他光学、磁性存储介质，在此不再一一赘述。
本申请的上述实施例提供的计算机可读存储介质与本申请实施例提供的信息推送方法出于相同的发明构思，具有相同的有益效果。
本申请实施方式还提供一种与前述实施方式所提供的信息推送方法对应的包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行前述任意实施方式所提供的信息推送方法。
本申请的上述实施例提供的包含指令的计算机程序产品与本申请实施例提供的信息推送方法出于相同的发明构思，具有相同的有益效果。
本申请实施方式还提供一种信息展示系统，请参考图6，其示出了本申请的一些实施方式所提供的另一种信息展示系统的示意图，信息展示系统与前述实施方式所提供的信息推送方法出于相同的发明构思，部分内容可互相参照理解。在下述实施例说明中，可以参照图3所示的信息展示系统的示意图进行理解。
如图6所示，信息展示系统可以包括：用户识别子系统61、用户跟踪子系统62、商品识别子系统63、数据分析子系统64和数据服务子系统65；
用户识别子系统61，用于识别进入目标场所的第一目标用户；
用户跟踪子系统62，用于对第一目标用户的运动轨迹进行跟踪，以及根据第一目标用户在目标场所内的当前运动轨迹预测第一目标用户的运动路径；
商品识别子系统63，用于识别第一目标用户所浏览过的商品的商品信息；
数据分析子系统64，用于根据第一目标用户所浏览过的商品的商品信息，确定第一目标用户的偏好信息(例如消费倾向信息)；
数据服务子系统65，用于在第一目标用户的运动路径上展示与消费倾向 信息相关联的广告信息。
本申请实施例的一些实施方式中，用户识别子系统61包括：
身份识别模块，用于根据采集自目标场所内的监控视频，通过图像识别技术对进入目标场所内的第一目标用户进行身份识别。
例如，用户识别子系统61可以对安装在目标场所内的监控设备D采集的监控视频的视频帧进行分析，实时检测进入目标场所的用户，采用图像识别技术对第一目标用户进行身份识别，以识别出第一目标用户的身份、性别、年龄、衣着特征和人体特征。此外，用户识别子系统61还可以对进出目标场所的人员采集人脸图像并进行识别，确定该人员是用户或店员。
用户跟踪子系统62，可以通过对目标场所内各监控设备采集的视频帧进行分析，获取场景中出现的第一目标用户及其人体特征，同一个第一目标用户在同一个和不同监控设备的视场内出现时，通过人体特征的比对确定是否为同一个监控设备。由此来形成第一目标用户在整个目标场所内的当前运动轨迹。基于上述说明，用户跟踪子系统62可以确定第一目标用户进过哪些店、在哪些柜台停留过、当前位置以及预测其运动路径。
本申请实施例的另一些实施方式中，用户跟踪子系统62可以包括：
出入口分析模块，用于根据采集自目标场所的出入口的监控视频，判断第一目标用户进入或离开目标场所，并基于图像识别技术确定进入目标场所的第一目标用户的身份信息和人体特征；通过图像识别技术提取进入目标场所内的第一目标用户的人体特征；
区域内目标分析模块，用于根据采集自目标场所内部的监控视频，通过图像识别技术在监控视频的视频帧中识别出第一目标用户，以及通过坐标系映射将第一目标用户在视频帧中的坐标信息映射为在目标场所的位置信息；
第一目标用户跟踪模块，用于对多个监控设备采集的监控视频的视频帧进行人体特征和历史运动特征的匹配，确定第一目标用户在目标场所内的当前运动轨迹，以及根据当前运动轨迹预测第一目标用户在目标场所内的运动路径。在一些实施方式中，区域内目标分析模块，可以包括：
监控视频坐标标定单元，用于建立监控设备所采集的监控视频的像素坐标系与目标场所的平面坐标系的映射关系。
其中，出入口分析模块，至少可以具有以下两个功能：
a.人体特征提取：采用机器学习的方法提取每一个进出目标场所的人员(包括用户和店员)的完整的人体特征，该人体特征可以区别不同的用户，为了清楚地对本申请实施例的技术方案进行描述，本申请实施例以第一目标用户为引导对象进行示例性说明，第一目标用户可以为任意用户；
b.运动状态分析：根据第一目标用户运动的方向及其在图像中的特征，分析第一目标用户是正在进入目标场所还是离开目标场所，该运动状态可以用于当前运动轨迹索引管理单元建立或删除第一目标用户的当前运动轨迹索引。
区域内目标分析模块，可以通过对若干在目标场所内的监控设备A、B、C等采集的监控视频的视频帧进行分析，至少实现以下功能：
a.目标检测和特征提取：采用机器学习的方法提取每一个进出目标场所的人员的完整的人体特征，该人体特征可以区别不同的用户；
b.坐标系映射：将第一目标用户在视频帧中像素坐标系下的坐标信息映射为在目标场所的平面坐标系下的位置信息，例如图7所示，将第一目标用户在监控设备B的监控视频中的像素坐标(m，n)通过坐标系映射转换为第一目标用户在目标场所的平面坐标系中的位置坐标(x，y)，其中，可以利用前述建立的监控设备所采集的监控视频的像素坐标系与目标场所的平面坐标系的映射关系进行坐标系映射。
第一目标用户跟踪模块，至少可以实现以下功能：
a.目标管理：维护目标场所内第一目标用户的当前运动轨迹索引(可采用链表实现)，根据出入口分析模块确定的第一目标用户进入或离开目标场所的信息，建立或删除第一目标用户的当前运动轨迹索引，当第一目标用户进入时，新建一个针对该第一目标用户的当前运动轨迹索引；当第一目标用户离开时，删除该当前运动轨迹索引；
b.多目标跟踪：在时域上利用目标场所内的多个监控设备A、B、C等采集到的第一目标用户的人体特征与当前运动轨迹索引中的第一目标用户的人体特征进行时空和图像特征的比对，并将连续帧满足时空约束和图像相似度的第一目标用户关联起来，形成第一目标用户在平面坐标系中的当前运动轨迹。
进一步细化的，第一目标用户跟踪模块，还可以实现以下功能：
a.坐标合并：当同一个第一目标用户被多个监控设备所拍摄时，其各监控设备中转换出来的平面坐标系下的位置坐标应为同一个，此时需要对重复坐标进行合并，确定第一目标用户唯一的位置信息；
b.轨迹预测：根据当前运动轨迹索引中第一目标用户的历史当前运动轨迹，采用卡尔曼滤波等预测算法对第一目标用户的当前运动轨迹进行预则，获取第一目标用户的运动特征，确定第一目标用户在目标场所内的运动路径；
c.目标匹配：采用前面提取的第一目标用户的人体特征，并结合其运动特征，在时空和图像上对当前运动轨迹索引中的第一目标用户与当前帧提取的信息进行匹配；
d.特征更新：当在时空和图像上达到匹配要求后，更新第一目标用户的当前运动轨迹索引中的人体特征和位置信息。
本申请实施例的再一些实施方式中，第一目标用户跟踪模块，可以包括：
当前运动轨迹索引管理单元，用于根据第一目标用户进入或离开目标场所，建立或删除第一目标用户的当前运动轨迹索引；
多监控设备跟踪单元，用于根据多个监控设备拍摄的多个监控视频，通过人体特征和历史运动特征的匹配，将位于多个监控视频中的、人体特征和历史运动特征的相似度符合相似度阈值条件的第一目标用户进行关联，确定第一目标用户的当前运动轨迹，以及根据当前运动轨迹预测第一目标用户在目标场所内的运动路径。
本申请实施例的又一些实施方式中，多监控设备跟踪单元，可以包括：
坐标合并子单元，用于当第一目标用户被多个监控设备所拍摄时，将根据多个监控设备所采集的监控视频确定的第一目标用户的多个位置信息进行合并，确定第一目标用户唯一的位置信息；
轨迹预测子单元，用于根据当前运动轨迹，采用当前运动轨迹预测算法预测第一目标用户在目标场所内的运动路径。
商品识别子系统63，可以对安装在店铺内的监控设备采集到的视频帧进行分析，当用户拿取商品时，通过对商品图像特征的提取，与商品注册数据进行比对，获取识别商品的品牌，类型，型号等信息。
本申请实施例的又一些实施方式中，商品识别子系统63，可以包括：
商品特征提取模块，用于根据采集自目标场所内的监控视频，采用图像特征提取技术提取第一目标用户所浏览的商品的特征信息；
商品信息匹配模块，用于从商品数据库中查询与第一目标用户所浏览的商品的特征信息相匹配的商品信息。
数据分析子系统64，可以实现以下功能：
a.实时对单个用户在目标场所内的行为进行分析，确定用户的购物倾向；
b.对大量商场的消费信息以及不同用户拿取商品的信息进行分析，获取不同年龄段、不同性别用户的购物趋势，以及商场商品的热度信息。
本申请实施例的又一些实施方式中，数据分析子系统64，还用于对多个第一目标用户在目标场所内的消费信息和浏览信息进行统计分析，确定不同身份特征的第一目标用户的购物趋势，以及确定各商铺的热度信息。
数据服务子系统65，可以通过数据分析子系统的数据，在用户购物路径上实时投放广告和商家信息，若用户未形成消费，在后续通过手机APP主动向用户推送相关产品的导购信息。
本申请实施例的又一些实施方式中，数据服务子系统65，还用于向第一目标用户所使用的移动终端推送与消费倾向信息相关联的广告信息。
本申请实施例所提供的信息展示系统，与本申请前述实施例提供的信息推送方法出于相同的发明构思，具有相同的有益效果。
需要说明的是，附图中的流程图和框图显示了根据本申请的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上各实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述各实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围，其均应涵盖在本申请的权利要求和说明书的范围当中。

Claims (16)

  1. 一种信息推送方法，其特征在于，包括：
    通过第一摄像机获取第一目标用户的视频图像，并根据所述视频图像提取所述第一目标用户的第一人体特征信息；
    根据所述第一人体特征信息，获取目标场所内多个第二摄像机采集的与所述第一人体特征信息相匹配的监控视频图像；
    根据所述第一目标用户在所述监控视频图像中的位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹，并预测所述第一目标用户在未来第一预设时间段内的运动路径；
    确定沿所述运动路径设置的各个信息展示设备，并向所述信息展示设备推送与所述第一目标用户相关联的待展示信息。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述第一目标用户在所述监控视频图像中的位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹，包括：
    根据所述第一目标用户在所述监控视频图像中的位置、以及各个第二摄像机的安装位置，确定所述第一目标用户在所述目标场所内的平面坐标位置；
    根据各个第二摄像机采集所述监控视频图像的时间信息以及所述平面坐标位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述第一目标用户在所述监控视频图像中的位置、以及各个第二摄像机的安装位置，确定所述第一目标用户在所述目标场所内的平面坐标位置，包括：
    确定所述第一目标用户在所述第二摄像机采集的监控视频图像中的像素坐标；以及，
    根据所述第二摄像机的安装位置，确定所述第二摄像机对应的映射关系，所述映射关系包括所述第二摄像机采集的监控视频图像的像素坐标系与所述目标场所的平面坐标系的映射关系；
    根据所述映射关系，将所述像素坐标转换为所述第一目标用户在所述目标场所内的平面坐标位置。
  4. 根据权利要求2所述的方法，其特征在于，所述根据各个第二摄像机采集所述监控视频图像的时间信息以及所述平面坐标位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹，包括：
    根据各个第二摄像机采集所述监控视频图像的时间信息，对采集自同一时间的所述平面坐标位置进行去重，得到去重后的平面坐标位置；
    根据所述时间信息，对所述去重后的平面坐标位置进行排序，得到所述第一目标用户在所述目标场所内的当前运动轨迹。
  5. 根据权利要求1所述的方法，其特征在于，所述预测所述第一目标用户在未来第一预设时间段内的运动路径，包括：
    根据所述当前运动轨迹，采用基于卡尔曼滤波的运动轨迹预测算法预测所述第一目标用户在未来第一预设时间段内的运动路径。
  6. 根据权利要求1所述的方法，其特征在于，所述预测所述第一目标用户在未来第一预设时间段内的运动路径，包括：
    根据所述监控视频图像确定所述第一目标用户当前的朝向信息；
    获取所述目标场所内的通行路线信息；
    根据所述当前运动轨迹、所述朝向信息和所述通行路线信息，预测所述第一目标用户在未来第一预设时间段内的运动路径。
  7. 根据权利要求1所述的方法，其特征在于，所述根据所述第一人体特征信息，获取目标场所内多个第二摄像机采集的与所述第一人体特征信息相匹配的监控视频图像，包括：
    提取目标场所内多个第二摄像机采集的监控视频图像中的多个第二人体特征信息；
    将所述第一人体特征信息与所述第二人体特征信息一一进行匹配，选出 与所述第一人体特征信息相匹配的第二人体特征信息；
    将选出的所述第二人体特征信息所对应的监控视频图像确定为与所述人体特征信息相匹配的监控视频图像。
  8. 根据权利要求7所述的方法，其特征在于，还包括：
    根据选出的所述第二人体特征信息更新所述第一人体特征信息。
  9. 根据权利要求1所述的方法，其特征在于，所述向所述信息展示设备推送与所述第一目标用户相关联的待展示信息之前，还包括：
    确定所述第一目标用户的偏好信息；
    根据所述偏好信息确定与所述第一目标用户相关联的待展示信息。
  10. 根据权利要求9所述的方法，其特征在于，所述确定所述第一目标用户的偏好信息，包括：
    确定所述目标用户的身份信息和/或历史行为信息；
    根据所述身份信息和/或所述历史行为信息，确定所述第一目标用户的偏好信息。
  11. 根据权利要求10所述的方法，其特征在于，所述确定所述目标用户的历史行为信息，包括
    根据所述监控视频图像确定所述第一目标用户的历史行为信息。
  12. 根据权利要求1所述的方法，其特征在于，所述确定沿所述运动路径设置的各个信息展示设备，包括：
    确定沿所述运动路径设置的、在所述第一目标用户前方指定距离内的各个信息展示设备。
  13. 一种信息推送装置，其特征在于，包括：
    第一人体特征提取模块，用于通过第一摄像机获取第一目标用户的视频图像，并根据所述视频图像提取所述第一目标用户的第一人体特征信息；
    监控视频图像匹配模块，用于根据所述第一人体特征信息，获取目标场所内多个第二摄像机采集的与所述第一人体特征信息相匹配的监控视频图像；
    运动路径预测模块，用于根据所述第一目标用户在所述监控视频图像中的位置，确定所述第一目标用户在所述目标场所内的当前运动轨迹，并预测所述第一目标用户在未来第一预设时间段内的运动路径；
    信息推送模块，用于确定沿所述运动路径设置的各个信息展示设备，并向所述信息展示设备推送与所述第一目标用户相关联的待展示信息。
  14. 一种信息展示系统，其特征在于，包括：摄像机、服务器和信息展示设备；
    所述摄像机和所述信息展示设备均与所述服务器通信连接；
    所述摄像机用于采集目标场所内的视频图像，并将所述视频图像传输至所述服务器；
    所述服务器用于通过执行权利要求1至12任一项所述的方法，预测所述第一目标用户的运动路径，并向沿所述运动路径设置的各个信息展示设备推送与所述第一目标用户相关联的待展示信息；
    所述信息展示设备用于展示所述待展示信息。
  15. 一种电子设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其特征在于，所述处理器运行所述计算机程序时执行以实现如权利要求1至12任一项所述的方法。
  16. 一种计算机可读介质，其特征在于，其上存储有计算机可读指令，所述计算机可读指令可被处理器执行以实现如权利要求1至12任一项所述的方法。
PCT/CN2019/107448 2018-12-28 2019-09-24 信息推送方法、装置及信息展示系统 WO2020134231A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811628227.5A CN111383039B (zh) 2018-12-28 2018-12-28 信息推送方法、装置及信息展示系统
CN201811628227.5 2018-12-28

Publications (1)

Publication Number Publication Date
WO2020134231A1 true WO2020134231A1 (zh) 2020-07-02

Family

ID=71128544

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/107448 WO2020134231A1 (zh) 2018-12-28 2019-09-24 信息推送方法、装置及信息展示系统

Country Status (2)

Country Link
CN (1) CN111383039B (zh)
WO (1) WO2020134231A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113225457A (zh) * 2020-12-29 2021-08-06 视联动力信息技术股份有限公司 数据处理方法、装置、电子设备及存储介质
CN113662494A (zh) * 2021-08-17 2021-11-19 岱川医疗(深圳)有限责任公司 内窥镜的工作站及其控制方法和其控制装置、存储介质
CN116389569A (zh) * 2023-06-05 2023-07-04 天津鹏萱汇智信息技术有限公司 一种向物联网设备推送信息的方法及系统

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111983603A (zh) * 2020-08-31 2020-11-24 杭州海康威视数字技术股份有限公司 运动轨迹接力方法、系统、装置和中心端处理设备
CN112380894B (zh) * 2020-09-30 2024-01-19 北京智汇云舟科技有限公司 一种基于三维地理信息系统的视频重叠区域目标去重方法和系统
CN112380901A (zh) * 2020-10-10 2021-02-19 杭州翔毅科技有限公司 行为轨迹生成方法、设备、存储介质及装置
CN112712392A (zh) * 2020-12-31 2021-04-27 京东数字科技控股股份有限公司 消息推送方法、装置、电子设备及存储介质
CN114338974A (zh) * 2021-12-02 2022-04-12 深圳市领航卫士安全技术有限公司 多通道的活动路径确定方法、装置、设备及存储介质
CN114428556B (zh) * 2022-04-07 2022-06-24 深圳市赢向量科技有限公司 影像广告互动控制方法及系统
CN115512479B (zh) * 2022-09-09 2024-04-09 北海市冠标智慧声谷科技有限责任公司 管理接待信息的方法以及后端设备
CN117478845B (zh) * 2023-12-27 2024-03-29 民航成都电子技术有限责任公司 基于人脸识别的定点催促登机方法、装置、设备及介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101572804A (zh) * 2009-03-30 2009-11-04 浙江大学 多摄像机智能控制方法及装置
US8781716B1 (en) * 2012-09-18 2014-07-15 Amazon Technologies, Inc. Predictive travel notifications
CN106709436A (zh) * 2016-12-08 2017-05-24 华中师范大学 面向轨道交通全景监控的跨摄像头可疑行人目标跟踪系统
CN107708100A (zh) * 2017-11-15 2018-02-16 特斯联（北京）科技有限公司 一种基于用户位置信息的广告播放方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003317187A (ja) * 2002-04-24 2003-11-07 Casio Comput Co Ltd 公衆向け情報出力システムおよび公衆向け情報出力方法並びに公衆向け出力装置
US20140164125A1 (en) * 2012-05-18 2014-06-12 Container Media, LLC System and Methods for Geographically-Driven Downstream Distribution of Mobile Content
CN106296724B (zh) * 2015-05-12 2020-04-03 杭州海康威视数字技术股份有限公司 一种目标人物的轨迹信息的确定方法、系统及处理服务器
TWI644273B (zh) * 2017-02-15 2018-12-11 立創智能股份有限公司 個人化廣告系統

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101572804A (zh) * 2009-03-30 2009-11-04 浙江大学 多摄像机智能控制方法及装置
US8781716B1 (en) * 2012-09-18 2014-07-15 Amazon Technologies, Inc. Predictive travel notifications
CN106709436A (zh) * 2016-12-08 2017-05-24 华中师范大学 面向轨道交通全景监控的跨摄像头可疑行人目标跟踪系统
CN107708100A (zh) * 2017-11-15 2018-02-16 特斯联（北京）科技有限公司 一种基于用户位置信息的广告播放方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113225457A (zh) * 2020-12-29 2021-08-06 视联动力信息技术股份有限公司 数据处理方法、装置、电子设备及存储介质
CN113662494A (zh) * 2021-08-17 2021-11-19 岱川医疗(深圳)有限责任公司 内窥镜的工作站及其控制方法和其控制装置、存储介质
CN113662494B (zh) * 2021-08-17 2023-12-26 岱川医疗(深圳)有限责任公司 内窥镜的工作站及其控制方法和其控制装置、存储介质
CN116389569A (zh) * 2023-06-05 2023-07-04 天津鹏萱汇智信息技术有限公司 一种向物联网设备推送信息的方法及系统

Also Published As

Publication number Publication date
CN111383039B (zh) 2023-08-29
CN111383039A (zh) 2020-07-07

Similar Documents

Publication Publication Date Title
WO2020134231A1 (zh) 信息推送方法、装置及信息展示系统
US9934447B2 (en) Object detection and classification
CN107909443B (zh) 信息推送方法、装置及系统
US9922271B2 (en) Object detection and classification
US10257293B2 (en) Computer-vision content detection for sponsored stories
CN106776619B (zh) 用于确定目标对象的属性信息的方法和装置
US10062100B2 (en) Methods and systems for identifying visitors to real-world shopping venues as belonging to a group
JP6536058B2 (ja) ユーザの人口統計学特性を推定する方法、コンピュータ・システム、及びプログラム
US9047654B2 (en) System and method for displaying contextual supplemental content based on image content
US20190332872A1 (en) Information push method, information push device and information push system
KR101348142B1 (ko) 얼굴인식기술을 이용하여 분류된 개인 또는 그룹 유형별 맞춤형 콘텐츠 제공 방법 및 그러한 시스템
US10210429B2 (en) Image based prediction of user demographics
KR102097781B1 (ko) 객체 정보 제공 장치 및 방법
Himeur et al. Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey
KR20190116830A (ko) 광고 시청자의 빅데이터 및 시청자객체 수 기반 광고료를 산정하는 광고 서비스 제공 방법
US20230111437A1 (en) System and method for content recognition and data categorization
Gaikwad et al. End-to-end person re-identification: Real-time video surveillance over edge-cloud environment
Wong et al. Enriched and discriminative convolutional neural network features for pedestrian re‐identification and trajectory modeling
KR20170006356A (ko) 이차원 영상 기반 고객 분석 방법 및 장치
TWI745101B (zh) 資料處理方法、裝置及電腦可讀取記錄媒體
KR20220021689A (ko) 인공지능 디지털 사이니지 시스템 및 이의 운용방법
CN111951043A (zh) 信息投放处理方法、装置、存储介质与电子设备
US20240135652A1 (en) Augmented reality announcement information delivery system, and its delivery control apparatus, method, and program
Elias et al. Tracking subjects and detecting relationships in crowded city videos
CN112837369A (zh) 数据处理方法及装置、电子设备及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19905367

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19905367

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19905367

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 04.02.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19905367

Country of ref document: EP

Kind code of ref document: A1