CN107077507B

CN107077507B - Information pushing method, device and system

Info

Publication number: CN107077507B
Application number: CN201680002672.3A
Authority: CN
Inventors: 高斌
Original assignee: Cloudminds Beijing Technologies Co Ltd
Current assignee: Cloudminds Beijing Technologies Co Ltd
Priority date: 2016-10-21
Filing date: 2016-10-21
Publication date: 2021-06-04
Anticipated expiration: 2036-10-21
Also published as: WO2018072207A1; CN107077507A

Abstract

The invention relates to the technical field of information pushing, and provides an information pushing method, device and system. The system comprises a first terminal which uploads a first picture historically; the server is used for acquiring pictures uploaded by each terminal; the second terminal uploads a second picture; and the server acquires the second picture, analyzes the first picture and the second picture, confirms that the similarity between the target objects corresponding to the same position in the first picture and the second picture is smaller than a first preset threshold value, and sends push information corresponding to the target objects to the first terminal. According to the embodiment of the invention, whether the target object at the same position contained in the second picture uploaded by the second terminal changes or not in the first picture is judged by analyzing the pictures uploaded by different terminals according to the similarity between the target objects contained in the pictures, and the changed push information is sent to the first terminal, so that the first user can timely acquire the state of the changed target object in the first picture.

Description

Information pushing method, device and system

[ technical field ] A method for producing a semiconductor device

The present invention relates to the field of information push technologies, and in particular, to a method, an apparatus, and a system for information push.

[ background of the invention ]

With the development of society, information push is always accompanied, for example: conventional subscription newspapers, subscription periodicals, and the like. With the popularization of the internet, the information push mode is also converted from an entity into a public subscription number similar to that in WeChat, a consultation subscription in an internet platform and the like. In the existing push mode, a certain subscription type is set by a user in a form, and then, the obtained consultation of each subscription type is sent to the user in a targeted manner by a background. For example: and after the background server acquires the automobile electronic magazine edited by the editor, the background server sends the automobile electronic magazine to the subscribing user. The existing information push is a broadcast-like push mode, and the content acquired by the user may contain many contents which are not concerned by the user, so that the information push is a loose push mode.

The current popular matters are photographing and commenting when a user goes out or photographing and sunning a friend circle, wherein the user can express that the user goes to a certain place or visits a certain scenic spot besides sunning the user's beauty. The inventor finds that with the increase of the urban development speed, the surrounding environment is changed day by day, and the user cannot know the place where the user has taken a picture and has been reserved in the normal situation if the place is rebuilt or modified. The existing information pushing method cannot push the environment information reconstructed or modified at the place to the user who has taken pictures at the place historically.

[ summary of the invention ]

One of the technical problems to be solved by the embodiments of the present invention is how to upload a picture at a certain position to a user, and after knowing that one or more target objects included in the picture have changed, the picture can actively send push information to the user.

The embodiment of the invention adopts the following technical scheme:

in a first aspect, an embodiment of the present invention provides an information pushing system, where the information pushing system includes a server and at least two terminals, where the at least two terminals include a first terminal and a second terminal; the server stores a first picture uploaded by a first terminal, and specifically comprises the following steps:

the second terminal is used for uploading a second picture;

the server is further configured to obtain the second picture, analyze the first picture and the second picture, confirm that a similarity between target objects at a same position in the first picture and the second picture is smaller than a first preset threshold, and send push information corresponding to the target objects to the first terminal.

Preferably, the server is further configured to:

searching one or more pictures with similarity greater than a second preset threshold compared with the characteristic information of the target object according to the characteristic information of the target object contained in the second picture;

and generating the push information according to the one or more pictures.

Preferably, the first terminal uploads a first picture, and the uploaded content also carries first picture related information, where the first picture related information includes one or more of content position information, picture resolution, and generation time information of the first picture, specifically:

the server is also used for correcting the first picture and the related information of the first picture when receiving the first picture, and managing the first picture according to the correction result in a classifying way; the classification management comprises the following steps: storing the pictures in a classified manner according to one or more items of the same type of the position information, the same interval type of the picture resolution and the same time period type of the generation time;

the server is further used for obtaining the first picture with the matched type according to one or more items of content position information, picture resolution and generation time information of the second picture in the related information of the second picture.

Preferably, the similarity between the target objects is formed by the similarity between one or more regions constituting the target objects, and the server acquires the second picture and analyzes the first picture and the second picture, specifically including:

the server screens the noise information in the first picture and the second picture to obtain the areas of the first picture and the second picture corresponding to the target object;

and comparing the areas corresponding to the target object in the first picture and the second picture by using feature identification to obtain the area similarity corresponding to the target object in the first picture and the second picture.

In a second aspect, an embodiment of the present invention provides an information pushing method, where the information pushing method includes:

receiving a first picture uploaded by a first terminal;

receiving a second picture uploaded by a second terminal;

analyzing the first picture and the second picture, confirming that the similarity between the target objects corresponding to the same position in the first picture and the second picture is smaller than a first preset threshold value, and sending push information corresponding to the target objects to the first terminal.

Preferably, the method further includes acquiring first picture related information while receiving a first picture uploaded by a first terminal, where the first picture related information includes one or more of content location information, picture resolution, and generation time information of the first picture, and the method further includes:

when the first picture is received, the first picture and the related information of the first picture are corrected, and the first picture is classified and managed according to the correction result; the classification management comprises the following steps: storing the pictures in a classified manner according to one or more items of the same type of the position information, the same interval type of the picture resolution and the same time period type of the generation time;

before analyzing the first picture and the second picture, the method further includes:

and obtaining the first picture with the matched type according to one or more items of content position information, picture resolution and generation time information of the second picture in the related information of the second picture.

Preferably, the classification management specifically includes:

retrieving a picture library according to the feature information of one or more target objects contained in the first picture and the related information of the first picture;

and confirming a calibration picture for calibrating the one or more target objects from the picture library.

Preferably, the analyzing the first picture and the second picture to confirm that the similarity between the target objects at the same position in the first picture and the second picture is smaller than a first preset threshold specifically includes:

analyzing the position information corresponding to the first picture and the second picture, and determining that the first picture and the second picture are in the same geographical position;

and matching the second picture with a calibration picture for calibrating one or more target objects in the first picture, and confirming that the similarity between the target objects at the same position in the first picture and the second picture is less than a first preset threshold value.

Preferably, the similarity between the target objects is composed of similarities between one or more regions constituting the target objects, and the analyzing the first picture and the second picture specifically includes:

screening the noise information in the first picture and the second picture to obtain the areas of the first picture and the second picture corresponding to the target object;

Preferably, the method further comprises:

and generating push information according to the one or more pictures.

Preferably, the generating push information according to the one or more pictures specifically includes:

screening one or more pushed pictures with the picture generation time interval of a specified duration; and/or screening one or more push graphs, wherein the visual angle of an object contained in the picture is the same as and/or complementary to the visual angle of the same object in the first picture;

and combining the one or more push pictures and the first picture to obtain the push information.

Preferably, the combining the one or more push graphs and the first picture to obtain the push information specifically includes:

adding the one or more push graphs and the first picture to the push information;

adding preset position information of the one or more push pictures and the first picture in the push information;

and adding the time information of each corresponding picture to the push information.

In a third aspect, an embodiment of the present invention provides an information pushing method, where the information pushing method includes:

uploading a first picture and related information of the first picture;

receiving push information, wherein the push information carries the first picture and one or more push pictures; wherein the one or more push pictures and the one or more target objects contained in the first picture are in the same geographical location.

Preferably, the method further comprises:

and uploading historical path data of the terminal, wherein the historical path data comprises position information and time information of the historical path.

Preferably, the method further comprises:

and setting not to receive the push information which has the same position information as the historical path and has the time difference with the historical path within a preset threshold value.

Preferably, the method further comprises:

and setting one or more of the number of the pushed pictures carried in the received pushing information, the resolution of the pushed pictures, the source of the pushed pictures and the angle of the target object in the pushed pictures.

In a fourth aspect, an embodiment of the present invention provides an information pushing apparatus, including:

the first picture receiving module is used for receiving a first picture uploaded by a first terminal;

the second picture receiving module is used for receiving a second picture uploaded by a second terminal;

and the push information module is used for analyzing the first picture and the second picture, confirming that the similarity between the target objects corresponding to the same position in the first picture and the second picture is smaller than a first preset threshold value, and sending push information corresponding to the target objects to the first terminal.

In a fifth aspect, the present invention further provides an information pushing apparatus, where the information pushing apparatus includes:

the uploading module is used for uploading the first picture and the related information of the first picture;

the push information receiving module is used for receiving push information, and the push information carries the first picture and one or more push pictures; wherein the one or more push pictures and the one or more target objects contained in the first picture are in the same geographical location.

In a sixth aspect, an embodiment of the present invention further provides an electronic device, configured to implement the information pushing method step in any of the second aspect or the third aspect, where the method includes:

at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being stored by the memory with a program of instructions executable by the at least one processor, the instructions being programmed to perform the information push method steps of any one of the second or third aspects.

In a seventh aspect, an embodiment of the present invention further provides a non-volatile computer storage medium, where the computer storage medium stores computer-executable instructions, which are executed by one or more processors, for performing the information push method according to any one of the second aspects, or for performing the information push method according to any one of the third aspects.

According to the embodiment of the invention, whether the target object contained in the second picture uploaded by the second terminal changes compared with the first picture or not is judged according to the similarity between the target objects contained in the pictures by analyzing the pictures uploaded by different terminals. Wherein the target object refers to an object in the same position (usually, a geographical position) in reality. And if the change occurs, the generated push information is sent to the first terminal, so that the first user can timely acquire the latest state of the changed target object in the first picture which is historically uploaded by the first user. The target object which is interested by the first user can be associated through the first picture uploaded by the first terminal, and the change of the target object can be identified according to pictures uploaded by other users in the system, so that the information which is interested by the user can be accurately fed back, and the accuracy and the effectiveness of pushing the information are improved.

[ description of the drawings ]

Fig. 1 is a schematic diagram of an information push system according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a target object distribution diagram according to an embodiment of the present invention;

fig. 3 is a schematic illustration showing an azimuth angle of a shot according to an embodiment of the present invention;

fig. 4 is a flowchart of an information pushing method according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a target object obtained from a captured azimuth angle according to an embodiment of the present invention;

fig. 6 is a schematic view illustrating an azimuth angle of a shot according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a target object obtained from a shot azimuth angle according to an embodiment of the present invention;

fig. 8 is a flowchart of an information pushing method according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 12 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 13 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 14 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 15 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 16 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 17 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 18 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 19 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 20 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

[ detailed description ] embodiments

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

In the description of the present invention, the terms "inner", "outer", "longitudinal", "lateral", "upper", "lower", "top", "bottom", and the like indicate orientations or positional relationships based on those shown in the drawings, and are for convenience only to describe the present invention without requiring the present invention to be necessarily constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.

In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

Example 1:

an embodiment of the present invention provides an information push system, as shown in fig. 1, where the information push system includes a server 1, and at least two terminals (for example,

terminals

2, 3, and 4 shown in fig. 1), where the at least two terminals include a first terminal 2 and a second terminal 3. Different users can use different intelligent terminals to connect with the server 1, and the server 1 authenticates the user by using the personal account created by the user, so that even the same user can use different intelligent terminals to complete the personal account login. Therefore, in this embodiment, the first terminal 2 generally refers to one or more terminals belonging to the same user, and the message transmission between the server 1 and the user is completed through an intelligent terminal, on which a personal account of the current user is logged. The information push system of this embodiment is specifically implemented as follows:

the server 1 stores a first picture uploaded by the first terminal 2;

the first picture may be obtained by a smart phone or a single-shot photo as the first terminal 2, may be obtained by downloading the first terminal 2 from a network, or may be obtained by synthesizing software in the first terminal 2. And the uploading mode of the server 1 comprises uploading the first picture to a friend circle, backing up the first picture to the network server 1, loading the first picture to an album in the self space, and the like.

The mode of receiving the pictures uploaded by each terminal by the server 1 includes that the server 1 directly receives the pictures uploaded by each terminal, for example: the server 1 acts as a data backup server for the user, the server acts as a circle of friends server for the user, etc. The server 1 may also indirectly obtain the pictures uploaded by the terminal from a third-party server, where the third-party server may be a server for maintaining microblogs, a server for managing circle of friends, a server for managing a school network, and the like. The uploading of the pictures from the terminal to the server 1 in the embodiments of the present invention includes that the server 1 directly receives the pictures uploaded from the terminal and the server 1 indirectly obtains the pictures uploaded from the terminal from a third-party server.

The second terminal 3 is used for uploading a second picture;

as described above, the second terminal 3 may be a second picture completion directly uploaded to the server 1; or the second terminal 3 may upload the second picture to the third-party server first, and then the third-party server forwards the second picture to the server 1.

The server 1 is further configured to obtain the second picture, analyze the first picture and the second picture, confirm that a similarity between target objects at a same position in the first picture and the second picture is smaller than a first preset threshold, and send push information corresponding to the target objects to the first terminal 2.

Wherein, the first preset threshold may be set by a background operator, for example: the first preset threshold is set to 30% -50%. The one or more pictures with the similarity smaller than the first preset threshold represent that the target object at the same position in the first picture is in different states. Preferably, the first preset threshold may also be adjusted according to an evaluation feedback given by the first terminal 2 after receiving the recommendation message (usually, the evaluation feedback is completed by the first user operating the first terminal 2). For example: if the first terminal 2 feeds back the push information effectively, the first preset threshold value may be reserved or the parameter value of the first preset threshold value may be further increased; if the first terminal 2 feeds back the push information inaccurately, the parameter value of the first preset threshold may be decreased. The first preset threshold generally determines the change size of the target object, and if the first preset threshold is set to be larger, it indicates that the change phase difference of the target object is smaller, so that the existence of misjudgment is easily caused. The misjudgment here means that a picture in which the target object which is not substantially changed is located is pushed to the user, possibly due to misjudgment caused by picture pixels or partial occlusion.

In the embodiment of the present invention, the target object at the same position refers to an object at the same position in a real environment recorded by the first picture and the second picture. The target object can be generally specified as an object with characteristics which do not change within a certain time, such as a building in a picture, a signboard in a picture, a street in a picture, a storefront in a picture and the like; for dynamic objects such as people, vehicles, animals, weather, etc., the server 1 will not default to the dynamic object without characteristics that do not change for a certain period of time as the target object unless there is a special setting in the system (for example, a setting by a user logging in a homepage or logging in an APP manner, or a setting by an operator in a system parameter of the server 1). In the embodiments of the present invention, the target object and the dynamic object, as well as other recognizable contents, may be collectively referred to as an object. When analyzing the first picture and the second picture, it is preferable to perform a round of screening of the target object to exclude the dynamic object that is likely to dynamically change, and therefore, objects other than the target object are also referred to as noise information during the screening process.

The confirmation of the target object at the same position includes multiple modes, for example: when the server 1 obtains the first picture and the second picture, the server also obtains the position information of the corresponding first picture and the second picture, and then the target object at the same position in the first picture and the second picture can be judged according to the position information. In a preferred scheme, the position information includes not only longitude and latitude positioning information, but also shooting azimuth angle information. The shot azimuth angle information can further improve the identification accuracy of the target object.

With the embodiment of the present invention, in addition to the above-mentioned determining the target object at the same position in the first picture and the second picture by using the position information, the contour extraction in the picture may be performed first in an image processing manner, the picture is divided into one or more objects (including the above-mentioned target object and the dynamic object, etc.), and the one or more target objects are screened out; then, the target objects at the same position in the first picture and the second picture are identified according to a target object distribution diagram (the effect diagram is shown in fig. 2, wherein the irregular graph is the target object distribution diagram) formed by the key points (such as vertices, center points, inflection points, etc.) of the one or more target objects. In addition, the method may further include performing, by using a target identification algorithm, first performing contour extraction in the picture, dividing the picture into one or more objects (including the target object and the dynamic object, etc.), screening out one or more target objects, and quickly matching one or more target objects at the same position in the first picture and the second picture, where the similarity between the target objects is greater than a second preset threshold, according to the target contour between the pictures (for example, two target objects 1 and 2 shown in fig. 2 are greater than two corresponding target objects 1 and 2 in the other picture, respectively, where the one or more target objects are members of a plurality of target objects in the target object distribution diagram), and then combining the target object distribution diagram based on the target object, so as to efficiently find a result of the target objects at the same position in the first picture and the second picture, where the similarity is less than the first preset threshold (i.e. by using individual point locations in the target distribution diagram, and quickly completing pairing of corresponding point positions of the target object distribution diagram between the two pictures). The image processing mode and the target recognition algorithm can be used for processing the pictures without carrying the position information independently and can also be used as an auxiliary verification method in the analysis of the pictures carrying the position information. The target object distribution diagram can complete the angle rotation of the target object distribution diagram by combining the shot azimuth angle information in the corresponding position information, so that the target objects in two pictures with different shooting angles can be more accurately identified. As shown in fig. 3, the shooting azimuth angle is 30 degrees to the east south, and the corresponding rotation method may use the existing algorithm formula, which is not described herein again.

According to the embodiment of the invention, whether the target object at the same position included in the second picture uploaded by the second terminal 3 changes compared with the target object at the same position in the first picture is judged according to the similarity between the target objects at the same position in reality included in the pictures by analyzing the pictures uploaded by different terminals (including the first terminal and the second terminal in the embodiment). And if the change occurs, the generated push information is sent to the first terminal 2, so that the first user can timely acquire the latest state of the target object in the first picture which is historically uploaded by the first user after the change occurs. The target object which is interested by the first user can be associated through the first picture uploaded by the first terminal 2, and the change of the target object can be identified according to pictures uploaded by other users in the system, so that the information which is interested by the user can be accurately fed back, and the accuracy and the effectiveness of pushing the information are improved.

In the embodiment of the present invention, in the first picture and the second picture, when it is determined that the similarity between the target objects at the same position is smaller than a first preset threshold, the push information corresponding to the target object is sent to the first terminal 2. The push information may be a message including one or more of the name of the target object, the time when the target object changes, and the link address for browsing the second picture. In addition, in order to enable the first user to refer to another picture related to the target object at the same position, an embodiment of the present invention further provides an extension scheme, specifically:

the server 1 searches one or more pictures with similarity greater than a second preset threshold compared with the characteristic information of the target object according to the characteristic information of the target object contained in the second picture.

The second preset threshold may be set by a background operator, for example, the second preset threshold is set to 60% -80%. One or more pictures with the similarity greater than the second preset threshold are generally in the same state as the target object in the second picture, and are uploaded to the server 1 by other terminals.

And generating the push information according to the one or more pictures. The simplest generation method is to set the corresponding arrangement order of the one or more pictures, and send the one or more pictures to the first terminal 2 by being carried in the push information, so that the first terminal 2 can display the one or more pictures in the display screen to the first user after receiving the push information.

In the embodiment of the present invention, the server 1 analyzes the first picture and the second picture, and therefore, how to locate the corresponding first picture for the second picture in a huge picture library is a problem that is preferably overcome. Thus, a method of how to manage a picture library is also provided in connection with an embodiment of the present invention. Specifically, the method comprises the following steps:

the first terminal 2 uploads a first picture, and the uploaded content also carries first picture related information, where the first picture related information includes one or more items of content position information, picture resolution, and generation time information of the first picture, specifically:

the server 1 is further configured to collate the first picture and the information related to the first picture when receiving the first picture, and classify and manage the first picture according to a collation result; the classification management comprises the following steps: storing the pictures in a classified manner according to one or more items of the same type of the position information, the same interval type of the picture resolution and the same time period type of the generation time;

the server 1 is further configured to obtain the first picture with the matched type according to one or more items of content position information, picture resolution, and generation time information of the second picture in the related information of the second picture.

In addition to one or more of the content position information, the picture resolution, and the generation time information of the first picture, the verification may be performed on first picture related information edited by the first terminal 2 for the first picture transmitted by the first terminal, for example: the title of the first picture, the position information of the first picture entered by the first user (especially in the manner of user screenshots), etc. In addition, the checking process may further include confirming the position information in the picture, that is, completing the confirmation of the position information in the picture through an operation similar to the above-mentioned target object matching.

The classification management mode comprises classifying the first picture into a group of pictures with the same position information as the first picture, and storing the pictures.

Therefore, when the photo uploaded by the terminal is received each time, the pictures can be stored in a group of pictures with common position information through the checking process, so that the range (number) of the pictures can be effectively limited and analyzed according to the position information when the pictures are analyzed in the following process.

Example 2:

the embodiment of the present invention further provides an information pushing method, which can be executed by the server 1 in the information pushing system in embodiment 1. The first terminal and the second terminal are named only for convenience of distinguishing descriptions, and home users corresponding to the first terminal and the second terminal are called a first user and a second user. The second terminal may represent any terminal owned by a second user having the function of uploading pictures in reality, and the first terminal, except for having the function of uploading pictures by the second terminal, is usually the first user or a subscriber of the server push information in this embodiment (the subscription may be initiated by the first user actively, or may be owned by the first user as default by the server). In the embodiment of the present invention, since the terminals used by the first user or the second user may be of different types, in order to facilitate description, the first terminal and the second terminal are uniformly used as an intelligent terminal of the corresponding first user and an intelligent terminal of the second user, as shown in fig. 4, the information push method includes:

in step 201, a first picture uploaded by a first terminal is received.

The first picture uploaded by the first terminal and received by the server may be a picture uploaded by the terminal directly received by the server described in embodiment 1, or a picture uploaded by the terminal may be acquired indirectly from a third-party server by the server described in embodiment 1.

The first picture can be obtained by a smart phone or a single-shot photo as a first terminal; the first picture can also be downloaded by a personal computer, a tablet computer or a smart phone network as a first terminal; in addition, the first picture may be generated by the first terminal in a screenshot mode.

In step 202, a second picture uploaded by the second terminal is received.

The second picture generation manner of the second terminal and the server receiving manner may refer to the generation manner of the first picture of the first terminal in step 201, and are not described herein again.

In step 203, the first picture and the second picture are analyzed, and if it is confirmed that the similarity between the target objects at the same position in the first picture and the second picture is smaller than a first preset threshold, the push information corresponding to the target objects is sent to the first terminal.

In the embodiment of the present invention, the target object at the same position refers to a target object at the same position in a real environment recorded by the first picture and the second picture. The target object generally refers to an object with characteristics that do not change for a certain time, such as a building in a picture, a signboard in a picture, a street in a picture, a storefront in a picture, and the like. For a dynamic object such as a person, a vehicle, an animal, weather, or the like, the server usually defaults to not use the dynamic object without constant characteristics for a certain time as a target object unless there is a setting, wherein the target object and the dynamic object are collectively referred to as an object. Therefore, when the first picture and the second picture are analyzed, a round of screening of target objects is preferentially performed, and the objects which are easy to change dynamically are excluded. In an embodiment of the present invention, the dynamic object is also referred to as noise information with respect to the target object.

The confirmation of the target object at the same position includes multiple modes, for example: when the server acquires the first picture and the second picture, the server also acquires the position information of the corresponding first picture and the second picture, and then the target object at the same position in the first picture and the second picture can be judged according to the position information. In a preferred scheme, the location information includes not only longitude and latitude positioning information but also shooting azimuth angle information, and the shooting azimuth angle information can further improve the identification accuracy of the target object, specifically: and adjusting the rotation angle of the target object distribution diagram generated in the image processing mode in the first picture and/or the second picture according to the shot azimuth angle information. The shot azimuth angle information can be obtained through calculation according to a GPS (global positioning system) positioner and/or a gyroscope of the smart phone.

In the embodiment of the present invention, the object region calculated by using the target recognition algorithm in the first picture and/or the second picture may also be adjusted according to the shot azimuth angle information, for example: if the longitude and latitude in the position information of the second picture relative to the first picture are the same, and the difference between the shooting azimuth angle information of the second picture and the shooting azimuth angle information of the first picture is 30 degrees, when a target object with the highest similarity in the first picture and the second picture and at the same position is matched, the characteristic region of the target object in the first picture or the second picture is taken, and the corresponding partial characteristic region needs to be ignored, wherein the partial characteristic region is caused by the fact that the information contained by the target object in the first picture and the information contained by the target object in the second picture are not equal due to the difference of the shooting azimuth angle information by 30 degrees. The effect of the target object shot at the shooting angle shown in fig. 3 is shown in fig. 5, and the effect of the target object shot at the shooting angle shown in fig. 6 is shown in fig. 7, so that the shadow feature area is omitted when the target objects in fig. 5 and 7 are matched corresponding to the shooting angles, and the shadow feature area does not participate in the matching process of the similarity of the target objects. Therefore, the information inequality of the target object between the first picture and the second picture caused by the shooting angle is avoided.

With reference to the embodiment of the present invention, in addition to determining the target object at the same position in the first picture and the second picture according to the position information, the image processing method may specifically include: firstly, extracting outlines in a picture, dividing the picture into one or more objects (including the target object, the dynamic object and the like), and screening out one or more target objects; then, according to a target object distribution diagram formed by the central points of the one or more target objects, the target objects at the same position in the first picture and the second picture are identified. In addition, by using a target recognition algorithm, firstly, extracting the contour in the picture, dividing the picture into one or more objects (including the target object, the dynamic object and the like), screening out the one or more target objects, quickly matching the target objects at the same position with the similarity greater than a preset threshold value in the first picture and the second picture according to the target contour between the pictures, and then combining the target object distribution diagram based on the target objects, the result that the target objects at the same position in the first picture and the second picture have the similarity less than the first preset threshold value can be found more quickly.

According to the embodiment of the invention, whether the target object at the same position contained in the second picture uploaded by the second terminal changes compared with the first picture or not is judged according to the similarity between the target objects at the same position in reality contained in the pictures by analyzing the pictures uploaded by different terminals. And if the change occurs, the generated push information is sent to the first terminal, so that the first terminal can timely acquire the latest state of the target object in the first picture which is historically uploaded by the first terminal after the change occurs. The target object which is interested by the user can be associated through the first picture uploaded by the user, and the change of the target object can be identified according to pictures uploaded by other terminals, so that the information which is interested by the user can be accurately fed back, and the accuracy and the effectiveness of pushing the information are improved.

When the server runs the method described in this embodiment, the number of pictures that the server can receive from each terminal in a period of time may be very large, so it is very necessary to provide a progressive filtering mechanism and a classification management manner.

What is essential for the progressive screening mechanism and the classification management manner is that a server receives a first picture uploaded by a first terminal and also acquires first picture related information, wherein the first picture related information includes one or more of content position information, picture resolution and generation time information of the first picture, and the method further includes:

In addition to one or more of the content position information, the picture resolution, and the generation time information of the first picture, the verification may be performed on first picture related information edited by the first terminal for the first picture sent by the first terminal, for example: the title of the first picture, the position information of the first picture entered by the first user (especially in the manner of user screenshots), etc. In addition, the checking process may further include confirming the position information in the picture, that is, completing the confirmation of the position information in the picture through an operation similar to the above-mentioned target object matching.

For the verification of the picture information, the corresponding calibration picture is usually confirmed by combining the related information of the first picture, and the verification is completed by matching the target object in the calibration picture with the target object of the first picture. It is equivalent to synchronously carrying out the matching process in the checking process and the matching process in the method step. Optionally, a staff member on the server side may be added to complete the calibration process.

The classification management mode comprises the following steps: if the related information of the first picture comprises the content position information of the first picture, classifying the first picture into a group of pictures with the same position information as the first picture to finish storage; and/or retrieving a picture library according to the feature information of one or more target objects contained in the first picture and the related information of the first picture, and confirming a calibration picture for calibrating the one or more target objects from the picture library.

The calibration picture contains more comprehensive information of the corresponding target object, and the simple understanding is that the pixels reach the specified values and the noise is small enough compared with the target object. For the server, the calibration picture can be generated by shooting of a special person, and can also be selected from pictures of a target object at the same position shot by a plurality of users.

The calibration pictures may be multiple, and each calibration picture includes one or more target objects in the first picture. Compared with the target object in the first picture, the target object information contained in the corresponding calibration picture is more comprehensive, and the characteristic information of the target object of the calibration picture is used as the characteristic information of the target object in the first picture to participate in the analysis of the pictures subsequently received by the server (wherein the subsequently received pictures can comprise the second picture), so that the method is more efficient and accurate.

The progressive screening mechanism comprises: the server firstly determines whether the position information in the picture related information is consistent with the position information of the first picture or not for the received picture, and if not, matching is not carried out; and if the first picture and the calibration picture of the first picture are consistent, calling the first picture or the calibration picture of the first picture to finish the confirmation of the target object. Secondly, if it is determined that the picture related information does not include the position information, the image processing method and/or the target recognition algorithm are/is utilized to confirm the target object, which is not repeated herein.

Based on the foregoing classification management manner and the related information of the first picture and the second picture includes location information, the analyzing performed in step 203 analyzes the first picture and the second picture, and confirms that the similarity between the target objects at the same location in the first picture and the second picture is smaller than a first preset threshold, specifically including:

in step 2031, the position information corresponding to the first picture and the second picture is analyzed to determine that the first picture and the second picture are located at the same geographic position. And if the first picture and the second picture are determined to be in different geographical positions, skipping the subsequent execution steps and directly ending the process.

In step 2032, the second picture and the calibration picture that calibrates one or more target objects in the first picture are matched, and it is determined that the similarity between the target objects at the same position in the first picture and the second picture is smaller than a first preset threshold.

In the foregoing manner of classification management, the use of calibration images and the storage according to the location information are introduced, however, for the calibration image of the first image sent by the first terminal, when the target object in the first image of the first terminal is changed in the confirmation step 203, in addition to sending the push information corresponding to the target object to the first terminal, the method further includes:

in step 204, the recommendation message is sent to the user corresponding to the one or more pictures having the calibration relationship with the calibration picture of the first picture.

The server may manage, for each picture uploaded by the terminal, associating one or more calibration pictures with the terminal, typically by means of said classifying, after checking that the terminal contains a location object related to reality. The purpose is to more accurately and efficiently analyze pictures uploaded by other terminals like a second picture in the follow-up process. However, in step 204, the association relationship between the terminal upload picture and the calibration picture is further utilized, which is equivalent to calibrating a group of pictures in the same time period as the target object state included in the first picture by the calibration picture, so that the analysis of the first picture and the second picture (described by taking the second picture as an example) in the group of pictures can be completed, and the transmission of the push information of the user corresponding to the pictures in the whole group can be completed, thereby not only reducing the number of analysis times (i.e. not taking each picture in the group to be analyzed with the second picture), but also facilitating to improve the push efficiency. Although the picture uploaded by the terminal is taken as the judgment basis in each embodiment of the invention, because one user can finish uploading different pictures at different time and different places through a plurality of terminals, the user account is taken as the identification basis for the picture uploaded to the server by the terminal in the specific implementation process, namely the picture in the server does not use different terminal IDs as the basis for distinguishing the picture attributions, but the user account logged in by the terminal is taken as the basis for distinguishing whether the picture is from the same user.

With reference to the embodiment of the present invention, when "sending the push information corresponding to the target object to the first user" in step 203 is executed, there is a preferred implementation scheme, specifically:

in step 301, according to the feature information of the target object included in the second picture, one or more pictures with similarity greater than a second preset threshold compared to the feature information are searched.

The second preset threshold may be set by a background operator, for example, the second preset threshold is set to 60% -80%. And one or more pictures with the similarity larger than a second preset threshold are generally in the same state as the target object in the second picture, and are uploaded to the server by other terminals.

In step 302, push information is generated according to the one or more pictures.

The preferred implementation manner can cooperate with the calibration pictures in the classification management manner to generate the push information, that is, the push information simultaneously includes the one or more pictures and the one or more calibration pictures.

In combination with step 302 in the preferred implementation, there is an implementable method for generating a recommendation message, specifically including:

in step 3021, one or more pushed pictures whose picture generation time is separated by a specified duration are screened out; and/or screening one or more push graphs, wherein the visual angle of an object contained in the picture is the same as and/or complementary to the visual angle of the same object in the first picture.

The specified time interval is determined according to the number of pictures contained in the push information set by the user or the system and the difference between the first picture generation time and the second picture generation time. For example: the first picture generation time is a, the second picture generation time is B, the number of push pictures carried in the push information set by the user is N, and the specified duration is (B-a)/N. If the pictures at the positions separated by the specified duration cannot be obtained, the picture closest to the position separated by the specified duration is taken.

The visual angle of each object can be confirmed by the shot azimuth angle information, and is not described herein again.

In step 3022, the one or more push graphs and the first picture are combined to obtain the push information.

In the embodiment of the present invention, an optional combination implementation scheme is further provided for the combination manner of step 3022, which specifically includes:

adding the one or more push pictures and the first picture to the push information; adding preset position information of the one or more push pictures and the first picture in the push information; and adding the time information of each corresponding picture to the push information. The time information is used for being displayed together with the one or more push pictures and the first picture.

Example 3:

the information push method described in embodiment 2 of the present invention is described by being deployed from a server side, and embodiment 3 of the present invention is described by being deployed from a user side to explain how to implement the information push method proposed by the present invention, and the information push method includes:

in step 401, a first picture and first picture related information are uploaded.

Wherein the first picture comprises one or more target objects; the picture related information comprises one or more items of content position information, picture resolution and generation time information of the first picture.

Uploading the first picture to a friend circle, backing up the first picture to a network server, loading the first picture to an album in the self space, and the like

In step 402, receiving push information, where the push information carries the first picture and one or more push pictures; wherein the one or more push pictures and the one or more target objects contained in the first picture are in the same geographical location.

Wherein, the push information optionally further includes time information of each push picture, and after step 402 is executed, preferably further includes step 403, specifically:

in step 403, the one or more pushed pictures are arranged on the pushing interface according to the time information of each pushed picture. Optionally, the first picture is arranged at a starting position of the one or more pushed pictures, or the first picture is arranged on the one or more pushed pictures in a top-set manner.

With reference to the embodiment of the present invention, in addition to the first picture and the information related to the first picture, there is an optional scheme for the content uploaded in step 401, specifically:

The terminal is one or more terminals belonging to a user, wherein the terminal includes the first terminal described in embodiment 1-2, and the user is specifically the first user in embodiment 1-2. According to the position information and the time information of the historical path, the user can set that the push information which is the same as the position information of the historical path and has the time difference with the historical path within a preset threshold value is not received. The preset threshold may be set by the user, typically to 1 day, 1 week or 1 month. The longer the preset threshold set by the user is, the more hierarchy the frequency of receiving the push information by the user can be reduced, so that the push information requirements of different users can be met. Therefore, in an optional scheme, in addition to "setting not to receive push information that is the same as the position information of the historical route and has a time difference with the historical route within a preset threshold", a time parameter may be set, where the time parameter is used for the server to package and send one or more pieces of push information corresponding to the user when judging that the current time meets the time parameter, and the purpose of completing push information in a personalized manner may also be achieved. Both the above two manners relate to the delayed sending of the push information, and if the delayed sending requirement is combined with the calibration of a group of pictures, which are in the same time period as the target object state included in the first picture, by the calibration picture described in embodiment 2, the analysis of the first picture and the second picture (where the second picture is described as an example) in the group of pictures can be completed, and the generation of the push information of the user corresponding to the picture in the whole group can be completed. In the embodiment of the present invention, for a user with a preset threshold or a time parameter, the push information generated for the user may be temporarily stored, and the corresponding push information is sent after the preset threshold or the time parameter is met.

In the method according to the embodiment of the present invention, the user may set one or more of the resolution of the pushed picture, the source of the pushed picture, and the angle of the target object in the pushed picture, in addition to the number of the pushed pictures carried in the received pushed information.

For setting the push picture resolution, for example: the user can set the resolution of the picture pushed by the server to be 1280 × 1960 or the resolution to be less than 760 × 1280 by logging in a platform provided by the server, and the like. The resolution setting of the pictures is mainly finished according to the habit and the requirement of the user for browsing the pictures and the flow state owned by the user. In the specific implementation process, a network state monitoring function of the intelligent terminal of the user can be added, and when the current network state of the intelligent terminal of the user is confirmed to be connected with wifi or a wired network, a high-resolution recommendation graph is used; when the current network state of the intelligent terminal of the user is confirmed to be a mobile network (such as a 3G network and a 4G network), the low-resolution recommendation map is used.

Besides the above-mentioned method of avoiding the push information from occupying too much traffic of the user by determining the network status, there is another alternative implementation. Specifically, the method comprises the following steps: the resolution of one or more recommended pictures carried in the recommendation message received by the first terminal is not the resolution of the original pictures stored in the server, but is compressed; the compressed picture is composed of partial pixel information in the original picture, and when the first user clicks the recommendation message display interface to specify the recommendation picture, the compressed part of the recommendation picture selected by the user is sent to the user by the server, so that the picture with complete pixel information is generated with the recommendation picture clicked by the user.

For push picture sources, for example: the user may set to receive only pictures uploaded by specified type objects as the source of pushed pictures, where the specified type objects include third party companies, friends of the user, people in specified groups, people in specified school districts, people in specified enterprises, and so on.

For target object angles in the pushed picture, for example: the user can set the server to preferentially select one or more pictures containing the specified angle range of the target object as the push pictures for generating the push information.

Example 4:

the embodiment of the invention also provides an information pushing device, and the information pushing device can be used for operating the information pushing method in the embodiment 2. In a specific implementation process, the information pushing apparatus may be a server, may also be a home computer with sufficient computing power, and may also be a virtual execution interface in a big data cloud, as shown in fig. 9, where the information pushing apparatus includes:

The first picture receiving module and the second picture receiving module are respectively connected with the push information module.

According to the embodiment of the invention, the similarity of the target objects at the same position in reality contained in the pictures uploaded by different terminals is analyzed through the information pushing module, so that whether the target objects at the same position contained in the second picture uploaded by the second terminal are changed or not in comparison with the first picture is judged. And if the change occurs, the generated push information is sent to the first terminal, so that the first user can timely acquire the latest state of the changed target object in the first picture which is historically uploaded by the first user. The target object which is interested by the first user can be associated through the first picture uploaded by the first terminal, and the change of the target object can be identified according to pictures uploaded by other terminals in the system, so that the information which is interested by the first user can be accurately fed back, and the accuracy and the effectiveness of pushing the information are improved.

In the implementation process of the embodiment of the present invention, an optional implementation manner also exists, where a first picture receiving module receives a first picture uploaded by a first terminal and also obtains first picture related information, where the first picture related information includes one or more of content location information, picture resolution, and generation time information of the first picture, as shown in fig. 10, the apparatus further includes a classification management module, the classification management module is connected to the first picture receiving module and the second picture receiving module, and the first picture receiving module and the second picture receiving module are connected to a push information module via the classification management module, specifically:

the classification management module is used for correcting the first picture and the related information of the first picture, and classifying and managing the first picture according to the correction result. The classification management may specifically refer to the content described in embodiment 2, and details are not repeated here.

In combination with the embodiment of the present invention, there is also an optional implementation scheme, where the classification management module further includes a feature retrieval module and a target object calibration module, as shown in fig. 11, and the method specifically includes:

the characteristic retrieval module is used for retrieving a picture library according to the characteristic information of one or more target objects contained in the first picture and the related information of the first picture;

the target object calibration module is configured to confirm a calibration picture for calibrating the one or more target objects from the picture library.

With reference to the embodiment of the present invention, an optional implementation scheme also exists, as shown in fig. 12, the information pushing module further includes a location information confirming module and a calibration picture matching module, and specifically includes:

the position information confirming module is used for analyzing the position information corresponding to the first picture and the second picture and determining that the first picture and the second picture are in the same geographical position;

the calibration picture matching module is configured to match the second picture with calibration pictures for calibrating one or more target objects in the first picture, and determine that the similarity between target objects at the same position in the first picture and the second picture is smaller than a first preset threshold.

In combination with the embodiment of the present invention, there is also an optional implementation scheme, where a similarity between target objects is composed of similarities between one or more regions constituting the target objects, and the information pushing module further includes a screening module and a region similarity calculation module, as shown in fig. 13, and specifically includes:

the screening module is used for screening the noise information in the first picture and the second picture to obtain the areas of the first picture and the second picture corresponding to the target object;

the region similarity calculation module compares regions corresponding to the target object in the first picture and the second picture by using feature recognition to obtain the region similarity corresponding to the target object in the first picture and the second picture.

In combination with the embodiment of the present invention, there is also an optional implementation scheme, where the push information module further includes a push image matching module and a push information generating module, as shown in fig. 14, specifically:

the pushed picture matching module is used for searching one or more pictures with similarity greater than a second preset threshold compared with the characteristic information of the target object according to the characteristic information of the target object contained in the second picture;

the push information generating module is used for generating push information according to the one or more pictures.

In combination with the embodiment of the present invention, there is also an optional implementation scheme, where the push information generating module further includes a first screening module and/or a second screening module, as shown in fig. 15, specifically:

the first screening module is used for screening one or more pushed pictures with the picture generation time interval of a specified duration;

the second screening module is used for screening one or more push graphs, the visual angles of the objects contained in the pictures are the same as and/or complementary to the visual angle of the same object in the first picture;

wherein the one or more push graphs are used to generate the push information.

It should be noted that, for the information interaction, execution process, and other contents between the modules and units in the apparatus, the specific contents may refer to the description in embodiment 2 of the present invention because the same concept is based on the information push method embodiment of the present invention, and the corresponding modules may also be combined according to the method described in embodiment 2, and are not described herein again.

Example 5:

the embodiment of the invention also provides an information pushing device, and the information pushing device can be used for operating the information pushing method in the embodiment 3. In a specific implementation process, the information pushing apparatus may be a smart phone, a tablet computer, a personal PC, or the like, and as shown in fig. 16, the information pushing apparatus includes:

According to the embodiment of the invention, the first user can be ensured to timely acquire the latest state after the target object in the first picture which is historically uploaded by the first user changes through the information receiving and pushing module. The target object which is interested by the first user can be associated through the first picture uploaded by the first terminal, and the change of the target object can be identified according to pictures uploaded by other terminals in the system, so that the information which is interested by the first user can be accurately fed back, and the accuracy and the effectiveness of pushing the information are improved.

In combination with the embodiment of the present invention, there is also an optional implementation scheme, as shown in fig. 17, the upload module further includes:

and the historical path data uploading module is used for uploading historical path data of the terminal, wherein the historical path data comprises position information and time information of a historical path.

With reference to the embodiment of the present invention, there is also an optional implementation scheme, as shown in fig. 18, the apparatus further includes a first setting module, specifically:

the first setting module is used for setting the push information which is not received and has the same position information with the historical path and the time difference with the historical path within a preset threshold value.

With reference to the embodiment of the present invention, there is also an optional implementation scheme, as shown in fig. 19, where the apparatus further includes a second setting module, specifically:

the second setting module is used for setting one or more of the number of the pushed pictures carried in the received pushing information, the resolution of the pushed pictures, the source of the pushed pictures and the angles of the target objects in the pushed pictures.

It should be noted that, for the information interaction, execution process, and other contents between the modules and units in the apparatus, the specific contents may refer to the description in embodiment 3 of the present invention because the same concept is based on the information pushing method embodiment of the present invention, and the corresponding modules may also be combined according to the method described in embodiment 3, and are not described herein again.

Example 6:

an embodiment of the present invention further provides an electronic device, configured to implement the information push method according to any one of embodiments 2 to 3, as shown in fig. 20, where the method includes:

at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions are stored by the memory with a program of instructions executable by the at least one processor, the instructions are programmed to perform the steps of the information push method as set forth in any one of embodiments 2-3.

In fig. 20, a processor is taken as an example, the processor and the memory may be connected by a bus or in other manners, and fig. 20 is taken as an example of being connected by a bus.

The memory, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the information pushing method in embodiments 2 and 3, and corresponding program instructions/modules (e.g., the respective modules shown in fig. 9-15). The processor executes various functional applications and data processing of the information pushing apparatus by running the nonvolatile software program, instructions, and modules stored in the memory, that is, the functions of the information pushing method according to embodiment 2 and the modules and units according to embodiment 4, or the functions of the information pushing method according to embodiment 3 and the modules and units according to embodiment 5.

The memory may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The program instructions/modules are stored in the memory, and when executed by the one or more processors, perform the information pushing method in the above embodiment 2, for example, perform the above-described steps shown in fig. 4; the various modules, units described in FIGS. 9-15 may also be implemented; or performing the information pushing method in the above-mentioned embodiment 3, for example, performing the above-mentioned steps shown in fig. 8; the various modules, units described in fig. 16-19 may also be implemented.

The social device of embodiments of the present invention may exist in a variety of forms, performing the various steps described above and shown in FIG. 4; and the various modules, units described in FIGS. 9-15, or the various steps shown in FIG. 8; and the various modules and units described in fig. 16-19, the social device includes but is not limited to:

(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.

(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.

(3) A portable entertainment device: such devices can display and play video content, and generally also have mobile internet access features. This type of device comprises: video players, handheld game consoles, and intelligent toys and portable car navigation devices.

(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.

(5) Other electronic devices with video playing function or internet connection function.

The embodiment of the invention also provides a nonvolatile computer storage medium, wherein the computer storage medium comprises a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk and the like. The computer storage medium stores computer-executable instructions, which are executed by one or more processors, such as the one in fig. 20, and enable the one or more processors to execute the information pushing method in embodiment 2, such as the steps shown in fig. 4 and described above; the various modules, units described in FIGS. 9-15 may also be implemented; or the information push method in embodiment 3 is performed, for example, the steps shown in fig. 8 described above are performed; the various modules, units described in fig. 16-19 may also be implemented.

It should be noted that, for the information interaction, execution process and other contents between the modules and units in the apparatus and system, the specific contents may refer to the description in the embodiment of the method of the present invention because the same concept is used as the embodiment of the processing method of the present invention, and are not described herein again.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims

1. An information push system is characterized by comprising a server and at least two terminals, wherein the at least two terminals comprise a first terminal and a second terminal; the server stores a first picture uploaded by a first terminal, and specifically comprises the following steps:

the second terminal is used for uploading a second picture;

the server is further configured to obtain the second picture, analyze the first picture and the second picture, confirm that a similarity between target objects at the same position in the first picture and the second picture is smaller than a first preset threshold, and send push information corresponding to the target objects to the first terminal; the target object at the same position refers to an object at the same position in a real environment recorded by the first picture and the second picture, the object is an object with a constant characteristic within a certain time, and the push information includes a name of the target object and a time when the target object changes;

the server is further configured to:

and generating the push information according to the one or more pictures.

2. The information push system according to claim 1, wherein while the first terminal uploads the first picture, the uploaded content also carries first picture related information, where the first picture related information includes one or more of content location information, picture resolution, and generation time information of the first picture, specifically:

3. The information push system according to claim 1 or 2, wherein the similarity between target objects is composed of similarities between one or more regions constituting the target objects, and the server acquires the second picture and analyzes the first picture and the second picture, specifically including:

4. An information pushing method, characterized in that the information pushing method comprises:

receiving a first picture uploaded by a first terminal;

receiving a second picture uploaded by a second terminal;

analyzing the first picture and the second picture, confirming that the similarity between target objects at the same position in the first picture and the second picture is smaller than a first preset threshold value, and sending push information corresponding to the target objects to the first terminal; the target object at the same position refers to an object at the same position in a real environment recorded by the first picture and the second picture, the object is an object with a constant characteristic within a certain time, and the push information includes a name of the target object and a time when the target object changes;

the method further comprises the following steps:

and generating the push information according to the one or more pictures.

5. The information pushing method according to claim 4, wherein first picture related information is acquired while a first picture uploaded by a first terminal is received, wherein the first picture related information includes one or more of content location information, picture resolution, and generation time information of the first picture, and the method further comprises:

when the first picture is received, the first picture and the related information of the first picture are corrected, and the first picture is classified and managed according to the correction result; the classification management comprises the following steps: storing classified storage pictures according to one or more classified storage pictures with the same type of position information, the same interval type of picture resolution and the same time period type;

6. The information push method according to claim 5, wherein the classification management further comprises:

retrieving a picture library according to the feature information of one or more target objects contained in the first picture and the related information of the first picture; confirming a calibration picture for calibrating the one or more target objects from the picture library;

then, the analyzing the first picture and the second picture to confirm that the similarity between the target objects at the same position in the first picture and the second picture is smaller than a first preset threshold specifically includes:

and matching the second picture with the calibration picture for calibrating the first picture, and confirming that the similarity between the target object corresponding to the same position in the calibration picture of the first picture and the second picture is less than a first preset threshold value.

7. The information push method according to any one of claims 4 to 6, wherein the similarity between target objects is composed of similarities between one or more regions constituting the target objects, and the analyzing the first picture and the second picture specifically includes:

8. The information push method according to claim 4, wherein the generating push information according to the one or more pictures specifically includes:

9. The information push method according to claim 8, wherein the combining the one or more push graphs and the first picture to obtain the push information specifically includes:

10. An information pushing method, characterized in that the information pushing method comprises:

uploading a first picture and related information of the first picture;

receiving push information, wherein the push information carries the first picture and one or more push pictures; the one or more push pictures and one or more target objects contained in the first picture are located at the same geographical position, and the push information is sent when the server receives a second picture, analyzes the first picture and the second picture, and confirms that the similarity between the target objects at the same position in the first picture and the second picture is smaller than a first preset threshold value; the target object at the same position refers to an object at the same position in a real environment recorded by the first picture and the second picture, the object is an object with a constant characteristic within a certain time, and the push information includes a name of the target object and a time when the target object changes;

the one or more pushed pictures are obtained by the following method:

and searching one or more pictures with similarity greater than a second preset threshold compared with the characteristic information of the target object according to the characteristic information of the target object contained in the second picture.

11. The information pushing method according to claim 10, further comprising:

uploading historical path data of a terminal, wherein the historical path data comprises position information and time information of a historical path;

12. The information pushing method according to claim 10 or 11, wherein the method further comprises:

13. An information pushing apparatus, comprising:

the push information module is used for analyzing the first picture and the second picture, confirming that the similarity between target objects at the same position in the first picture and the second picture is smaller than a first preset threshold value, and sending push information corresponding to the target objects to the first terminal; the target object at the same position refers to an object at the same position in a real environment recorded by the first picture and the second picture, the object is an object with a constant characteristic within a certain time, and the push information includes a name of the target object and a time when the target object changes;

the push information module is further configured to:

and generating the push information according to the one or more pictures.

14. The information pushing apparatus according to claim 13, wherein a first picture uploaded by a first terminal is received, and first picture related information is also acquired, wherein the first picture related information includes one or more of content location information, picture resolution, and generation time information of the first picture, the apparatus further includes a classification management module, and the classification management module is connected to the first picture receiving module, specifically:

the classification management module is used for correcting the first picture and the related information of the first picture, and classifying and managing the first picture according to the correction result.

15. An information pushing apparatus, characterized in that the information pushing apparatus comprises:

the push information receiving module is used for receiving push information, and the push information carries the first picture and one or more push pictures; the one or more push pictures and one or more target objects contained in the first picture are located at the same geographical position, and the push information is sent when the server receives a second picture, analyzes the first picture and the second picture, and confirms that the similarity between the target objects at the same position in the first picture and the second picture is smaller than a first preset threshold value; the target object at the same position refers to an object at the same position in a real environment recorded by the first picture and the second picture, the object is an object with a constant characteristic within a certain time, and the push information includes a name of the target object and a time when the target object changes;

the push information receiving module is further configured to obtain the one or more push pictures in the following manner:

16. The information pushing apparatus according to claim 15, wherein the uploading module further comprises:

17. The information pushing apparatus according to claim 16, further comprising a first setting module, specifically:

18. A non-transitory computer storage medium storing computer-executable instructions for execution by one or more processors to perform the information pushing method of any one of claims 4-9 or to perform the information pushing method of any one of claims 10-12.