WO2022127276A1

WO2022127276A1 - Information processing method and apparatus, and electronic device, storage medium and computer program

Info

Publication number: WO2022127276A1
Application number: PCT/CN2021/121449
Authority: WO
Inventors: 范畅
Original assignee: 北京市商汤科技开发有限公司
Priority date: 2020-12-18
Filing date: 2021-09-28
Publication date: 2022-06-23
Also published as: TW202226114A; CN112508626A

Abstract

An information processing method and apparatus, and an electronic device, a storage medium and a computer program. The information processing method comprises: on the basis of a video stream collected from a first target place, acquiring trajectory information of pedestrians in the video stream (S101); on the basis of the trajectory information of the pedestrians in the video stream, determining a first number of people that enter the first target place within a preset duration and a second number of people that pass by the first target place within the preset duration (S102); and on the basis of the first number of people and the second number of people, generating adjustment information for articles exhibited in a second target place (S103).

Description

Information processing method, apparatus, electronic device, storage medium, and computer program

CROSS-REFERENCE TO RELATED APPLICATIONS

This patent application claims the priority of the Chinese patent application filed on December 18, 2020, with the application number of 2020115056005 and the invention titled "An information processing method, device, electronic device and storage medium". way to be incorporated into the text.

technical field

The present disclosure relates to the technical field of computer vision, and in particular, to an information processing method, apparatus, electronic device, storage medium, and computer program.

Background technique

In order to increase store sales, each store usually adopts storefront display to attract customers. In the conventional implementation method, store operators usually use the new products of this season or this month, and products with higher sales as display items.

However, the traditional scheme of determining the displayed items relies on sales data, which often cannot reflect the actual effect of the displayed items, and considering the privacy protection of customers, the access to some sales data is limited, which will lead to the The accuracy and comprehensiveness of sales data are poor. Therefore, an adjustment information generation scheme for display items is urgently needed, so as to get rid of the dependence of the traditional display item scheme on sales data.

SUMMARY OF THE INVENTION

The embodiments of the present disclosure provide at least one information processing solution.

In a first aspect, an embodiment of the present disclosure provides an information processing method, including: acquiring trajectory information of pedestrians in the video stream based on a video stream collected from a first target location; based on the trajectory information of pedestrians in the video stream , determine the number of first people entering the first target place and the number of second people passing through the first target place within a preset time period; Adjustment information of items displayed in the second target place.

In the embodiment of the present disclosure, the above-mentioned technical means can be used to determine the human flow data of different dimensions in combination with the collected video streams, which may specifically include the number of first and second human flows that can respectively reflect the number of people entering the first place and passing through the first target place. quantity. Based on the obtained people flow data in different dimensions related to the first target place, an adjustment plan can be formulated for the items displayed in the second target place, that is, adjustment information is generated.

It can be seen that, in the case where the first target place is the same as the second target place, through the above implementation manner, targeted adjustment information can be generated based on the flow data of people in different dimensions. In the case where the first target place is different from the second target place, through the above-mentioned implementation manner, an adjustment scheme suitable for the second target place can be obtained based on the flow data of people in different dimensions in the first target place. Obviously, in this implementation, an adjustment scheme suitable for the second target place can be obtained without additionally examining the flow of people in the second target place.

In addition, considering that for the first target place, whether the first place is a public place or a non-public place, for security reasons, video capture components such as cameras are usually deployed. That is to say, the data sources for realizing the above technical solutions usually belong to existing resources, and there is no need to collect additional video streams. In this way, the technical solution provided by the present disclosure can obtain an adjustment solution suitable for the second target site through the rational use of existing resources, which can undoubtedly get rid of the excessive dependence on sales data of the traditional item display solution, and realize the current situation. There are full utilization of resources. In addition, the obtained adjustment scheme of the displayed items can be more adapted to the actual needs of the second target place.

In a possible implementation manner, the second target location is the same as the first target location, or the second target location is an associated location associated with the first target location.

In a possible implementation manner, the first target place includes a first store within a set range area, and based on the first number of people and the second number of people The adjustment information of the displayed items includes: determining the store entry rate of the first store within the preset time period based on the first number of people and the second number of people; The store entry rate within the preset time period is used to generate adjustment information for the items displayed in the second target field.

In the embodiment of the present disclosure, by counting the number of first people entering the first store within the preset time period and the number of second people passing through the first store, it is possible to determine and reflect the store entry rate of the first store within the preset time period. The store entry rate can reflect the popularity of the items displayed in the first store within a preset period of time, so that the adjustment plan can be formulated directly based on the store entry rate for the second target place associated with the first store, and the whole process does not need to go through Manually count the sales data of the second target site, which saves labor costs and improves the accuracy of the determined adjustment plan.

In a possible implementation manner, the first store includes at least two stores, and the adjustment for the items displayed in the second target place is generated based on the store entry rate of the first store within the preset time period Information, including: based on the corresponding store entry rate of each store in the first store within the same statistical period, and the items displayed by each store in the same statistical period, generating a target site for the second target site Adjustment information for the items displayed inside.

In the embodiment of the present disclosure, the store entry rate of stores displaying different items can be counted in the same statistical period, for example, the store entry rate of multiple stores in a shopping mall in the same quarter can be counted, so that the display of multiple stores can be determined. The popularity of the items in the same statistical period, and then the adjustment information for the items displayed in the second target place can be generated. This process does not need to count the sales data of the second target place in the statistical period, saving labor costs, And the accuracy of the determined adjustment scheme is improved.

In a possible implementation manner, the generating method is based on the store entry rate corresponding to each store in the first store in the same statistical period and the items displayed in each store in the same statistical period. The adjustment information for the items displayed in the second target place includes: determining the first target store and the second target store from the first stores based on the corresponding store entry rate of each store in the same statistical period , the first target store is the store corresponding to the lowest entry rate in the first store, and the second target store is the store corresponding to the highest entry rate in the first store; the first target store is As the second target place, adjustment instruction information for the items displayed in the second target place is generated based on the items displayed in the second target store.

In the embodiment of the present disclosure, by counting the corresponding store entry rates of different stores in the same statistical period, the first target store with the lowest store entry rate and the second target store with the highest store entry rate within the preset range can be selected. Further, according to the items displayed in the second target store, an adjustment plan can be formulated for the second target place that is the same as the first target store, and there is no need to additionally investigate the store entry rate in the second target place, which can save labor costs and improve the determination of resource allocation. s efficiency.

In a possible implementation manner, the first store is one, and the adjustment information for the items displayed in the second target place is generated based on the store entry rate of the first store within the preset time period, Including: generating adjustment information for the items displayed in the second target place based on the respective store entry rates of the first store in different statistical time periods and the items displayed by the first store in different statistical time periods respectively .

In the embodiment of the present disclosure, the store entry rate of the same store in different statistical time periods can be counted, so as to determine the correlation between the items displayed in the same store and different statistical time periods, such as which statistical time period the items displayed in the store are in. The most popular, so that based on the relationship between the items displayed in the same store and different statistical time periods, an adjustment plan can be formulated for the second target place, and the items displayed in the second target place in different statistical time periods can be determined. This process can save manual offline. Count the cost of store entry rate and improve the efficiency of resource allocation.

In a possible implementation manner, based on the respective store entry rates of the first store in different statistical time periods, and the items displayed by the first store in different statistical time periods, generating The adjustment information of the items displayed in the second target place includes: in the case that the items displayed by the first store in different statistical periods are the same, based on the corresponding store entry rates of the first store in different statistical periods , determine the target display period corresponding to the items displayed in the first store; the store entry rate corresponding to the target display period is greater than or equal to the preset store entry rate threshold; based on the target display period, generate the target display period Adjustment information for items displayed in the second target location.

In the embodiment of the present disclosure, in the case where the items displayed in the first store are the same in different statistical time periods, by counting the store entry rates of the same store in different statistical time periods, the popular target of the items displayed in the first store can be selected Display period, based on this, an adjustment plan can be made for the items displayed in the second target field during the target display period. This process can save the time required to manually count the store entry rate of the second target field in different display periods, and no need The sales data of the second target site in different display periods are counted, so that the formulation efficiency of the adjustment plan can be improved.

In a possible implementation manner, based on the respective store entry rates of the first store in different statistical time periods, and the items displayed by the first store in different statistical time periods, generating Second, the adjustment information of the items displayed in the target place, including: in the case that the items displayed by the first store in different statistical periods are different, based on the corresponding store entry of the first shop in different statistical periods determine the matching degree between the items displayed in the first store in different statistical periods and the corresponding display period; based on the determined matching degree, generate an adjustment for the items displayed in the second target place during a specific display period information.

In the embodiment of the present disclosure, in the case where the items displayed by the first store in different statistical periods are not the same, by counting the store entry rates of the same store in different statistical periods, it can be quickly determined that the first store displays in different statistical periods The matching degree between the items displayed in the first statistical period and the corresponding display period, for example, the store entry rate corresponding to the first statistical period is high, which can reflect the higher matching degree between the items displayed in the first statistical period and the first statistical period. Therefore, it is determined that the items sold by the first store in the first statistical period are suitable for sale in the first statistical period, otherwise they are not suitable for sale in the first statistical period. The adjustment plan is formulated for the displayed items. This process can save the time required to manually count the entry rate of the second target site in different display periods, and it is also unnecessary to count the sales data of the second target site in different display periods, so that it can be Improve the efficiency of formulating adjustment plans.

In a possible implementation manner, the determining the store entry rate of the first store within the preset time period based on the first flow of people and the second flow of people includes: based on the first flow of people The number of people and the second number of people to obtain the total number of people; the ratio of the first number of people to the total number of people is used as the store entry rate of the first store within the preset time period.

In the embodiment of the present disclosure, when the first target place is a store, the store entry rate of the store within a preset period of time can be determined through video stream detection, which saves the time required to manually count the store entry rate and improves the store entry rate. statistical efficiency.

In a possible implementation manner, the acquiring the trajectory information of pedestrians in the video stream based on the video stream collected from the first target location includes: performing pedestrian detection on the target video frame in the video stream, identifying obtain the position information of each pedestrian contained in the target video frame; determine the position information of the target pedestrian in the video stream according to the position information of each pedestrian contained in the target video frame; The location information in the video stream is used to determine the trajectory information of the target pedestrian.

In the embodiment of the present disclosure, by using the pedestrian detection technology, the position information of each pedestrian in the video frame can be quickly determined, so that the position information of the target pedestrian in the video stream can be determined based on the position information of each pedestrian, and then the position information of the target pedestrian can be quickly determined. The trajectory information of the target pedestrian.

In a possible implementation manner, before determining the position information of the target pedestrian in the video stream according to the position information of each pedestrian included in the target video frame, the information processing method further includes: acquiring The feature information of pedestrians in the target video frames; based on the feature information of pedestrians contained in different target video frames respectively, determine the feature similarity between pedestrians contained in the different target video frames; The pedestrian corresponding to the maximum similarity at the preset similarity threshold is used as the target pedestrian.

In the embodiments of the present disclosure, it is proposed that the target pedestrians in different target video frames can be determined by extracting the characteristic information of the pedestrians contained in the target video frames, so as to provide convenience for the subsequent tracking of the target pedestrians to determine the trajectory information of the target pedestrians.

In a possible implementation manner, determining the number of the first flow of people entering the first target place within a preset time period based on the trajectory information of pedestrians in the video stream includes: based on the trajectory information and a first determination A flag, the number of pedestrians entering the first target place within the preset time period is counted to obtain the first number of people flow, and the first determination flag is used to judge whether pedestrians enter the first target place.

In the embodiment of the present disclosure, in the process of tracking the trajectory of the pedestrian, it can be more accurately determined whether the pedestrian enters the first target place by combining with the pre-drawn first judgment mark for judging whether the pedestrian enters the first target place. This process can save time for manually counting the number of people, and improve the efficiency of counting the number of people.

In a possible implementation manner, determining the number of second flows of people passing through the first target place within a preset time period based on the trajectory information of pedestrians in the video stream includes: based on the trajectory information, a first determination mark and a second judgment mark, the number of pedestrians passing through the first target place within the preset time period and not entering the first target place is counted to obtain the second number of pedestrians, the first judgment mark It is used for judging whether the pedestrian enters the first target place, and the second judgment flag is used for judging whether the pedestrian passes through the first target place.

In the embodiment of the present disclosure, in the process of tracking the trajectory of the pedestrian, a pre-drawn first judgment mark for judging whether the pedestrian enters the first target place and the first judgment mark for judging whether the pedestrian passes through the first target place can be combined. The second judgment flag can more accurately determine whether the pedestrian passes through the first target place. This process can save the time for manually counting the number of people, and improve the efficiency of counting the number of people.

In a possible implementation manner, the information processing method further includes: in the case where it is determined that the number of the first crowd is greater than a first preset threshold, generating first warning prompt information.

In the embodiment of the present disclosure, the number of people entering the first target place within a preset time period can be counted, and when it is determined that the number of people entering the first target place is large within the preset time period, early warning information can be generated to improve pedestrians' Security when entering the first target site.

In a possible implementation manner, the information processing method further includes: determining, based on the trajectory information and the first determination flag, the number of third people who have left the first target place within the preset time period, and The first judgment flag is used for judging whether the pedestrian enters the first target place; when it is determined that the number of the third pedestrian flow is greater than the second preset threshold, second warning prompt information is generated.

In the embodiment of the present disclosure, the number of people leaving the first target place within a preset time period can be counted, and when it is determined that the number of people leaving the first target place is large within the preset time period, early warning information can be generated, so as to improve the safety of pedestrians. Safety when leaving the first target site.

In a possible implementation manner, the information processing method further includes: based on the historical number of people staying at the first target place within the preset time period, the number of the first flow of people and the number of the third flow of people, Determine the net personnel stock of the first target place within the preset time period; when it is determined that the net personnel stock of the first target place within the preset time period is greater than a third preset threshold, generate the first Three warning information.

In the embodiment of the present disclosure, the net stock of personnel in the first target place can be detected in real time, and if it is determined that the net stock of personnel exceeds the threshold, an early warning prompt can be given. Safety of pedestrians staying in the first target site.

In a second aspect, an embodiment of the present disclosure provides an information processing apparatus, including: an acquisition module, configured to acquire the trajectory information of pedestrians in the video stream based on a video stream collected from a first target location; a determination module, configured to Determine, based on the trajectory information of pedestrians in the video, the number of the first flow of people entering the first target place and the number of second flows of people passing through the first target place within a preset time period; The first flow of people and the second flow of people are used to generate adjustment information for the items displayed in the second target place.

In a third aspect, embodiments of the present disclosure provide an electronic device, including: a processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor, and when the electronic device runs, the processing The processor and the memory communicate through a bus, and the machine-readable instructions execute the steps of the information processing method according to the first aspect when the machine-readable instructions are executed by the processor.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to execute the information processing method according to the first aspect. step.

In a fifth aspect, an embodiment of the present disclosure provides a computer program, where the computer program carries program code, and the instructions included in the program code are executed by a processor to cause the processor to execute any implementation manner of the first aspect. the steps of the information processing method.

In order to make the above-mentioned objects, features and advantages of the present disclosure more obvious and easy to understand, the preferred embodiments are exemplified below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

In order to explain the technical solutions of the embodiments of the present disclosure more clearly, the following briefly introduces the accompanying drawings required in the embodiments, which are incorporated into the specification and constitute a part of the specification. The drawings illustrate embodiments consistent with the present disclosure, and together with the description serve to explain the technical solutions of the present disclosure. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as limiting the scope. Other related figures are obtained from these figures.

FIG. 1 shows a flowchart of an information processing method provided by an embodiment of the present disclosure;

FIG. 2 shows a flowchart of a method for determining trajectory information of a target pedestrian provided by an embodiment of the present disclosure;

FIG. 3 shows a schematic diagram of a scenario for determining the first number of people flow and the second number of people flow provided by an embodiment of the present disclosure;

FIG. 4 shows a flowchart of a method for generating adjustment information for items displayed in a second target place provided by an embodiment of the present disclosure;

FIG. 5 shows a flowchart of a method for early warning provided by an embodiment of the present disclosure;

FIG. 6 shows a flowchart of another method for early warning provided by an embodiment of the present disclosure;

FIG. 7 shows a schematic structural diagram of an information processing apparatus provided by an embodiment of the present disclosure;

FIG. 8 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only These are some, but not all, embodiments of the present disclosure. The components of the disclosed embodiments generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the disclosure provided in the accompanying drawings is not intended to limit the scope of the disclosure as claimed, but is merely representative of selected embodiments of the disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present disclosure.

It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

The term "and/or" in this paper only describes an association relationship, which means that there can be three kinds of relationships, for example, A and/or B, which can mean: the existence of A alone, the existence of A and B at the same time, the existence of B alone. a situation. In addition, the term "at least one" herein refers to any combination of any one of the plurality or at least two of the plurality, for example, including at least one of A, B, and C, and may mean including from A, B, and C. Any one or more elements selected from the set of B and C.

For tourist attractions, shopping streets and other places, in order to increase store sales, each store usually adopts storefront display to attract customers. In the conventional implementation method, store operators usually use new products in this quarter or this month, and products with high sales volume as display items. These schemes for determining display items generally rely on sales data, and it is difficult and efficient to obtain accurate sales data. Therefore, how to efficiently and accurately generate an adjustment plan for the store is an urgent problem to be solved.

Based on the above research, the present disclosure provides an information processing method, which can determine people flow data of different dimensions in combination with the collected video streams, which can specifically include the number of first people flow that can respectively reflect entering the first place and passing through the first target place. and the number of second people. Based on the obtained people flow data in different dimensions related to the first target place, an adjustment plan can be formulated for the items displayed in the second target place, that is, adjustment information is generated.

In addition, in the case where the first target place is the same as the second target place, through the above implementation manner, targeted adjustment information can be generated based on the flow data of people in different dimensions. In the case where the first target place is different from the second target place, through the above-mentioned implementation manner, an adjustment scheme suitable for the second target place can be obtained based on the flow data of people in different dimensions in the first target place. Obviously, in this implementation, an adjustment scheme suitable for the second target place can be obtained without additionally examining the flow of people in the second target place.

In order to facilitate the understanding of this embodiment, an information processing method disclosed in the embodiment of the present disclosure is first introduced in detail. The device includes, for example, a terminal device or a server or other processing device, and the terminal device may be a user equipment (User Equipment, UE), a mobile device, a user terminal, and the like. In some possible implementations, the information processing method may be implemented by a processor invoking computer-readable instructions stored in a memory.

Referring to FIG. 1, which is a flowchart of an information processing method provided by an embodiment of the present disclosure, the information processing method includes the following S101-S103:

S101 , based on the video stream collected from the first target place, acquire the track information of pedestrians in the video stream.

Exemplarily, the first target place includes a place where the flow of people needs to be counted, such as each exhibition hall in an exhibition hall, each store in a shopping street or a shopping mall, etc. The embodiment of the present disclosure will take the first target place as a store as an example. , which explains how to process information to generate adjustment information for items displayed in the store. It should be noted that, in the application scenario of the technical solution provided by the embodiment of the present disclosure, the first target place may include, but is not limited to, a store.

Exemplarily, when acquiring a video stream for a store, in order to collect the flow of people entering or passing through the store, a video capture component may be set outside the store, and the video capture component may include a color camera or a grayscale camera. Make adjustments so that the camera can simultaneously capture the target area passing through the store or entering the store. Pedestrians who pass through the store can be understood as pedestrians who pass through the entrance of the store but do not enter; pedestrians who enter the store can be understood as pedestrians who enter the store from the entrance of the store. Therefore, video capture can be performed on the target area corresponding to the entrance of the store to obtain a video stream for the store.

It should be noted that, for stores such as shopping malls, for security reasons, corresponding cameras are usually deployed at the entrance of the store and in the aisles at the entrance of the store, and the video streams collected by such cameras can often be directly applied. in the technical scheme. That is to say, the technical solution provided by the present disclosure can extend the existing video data, that is, the video stream collected by the cameras originally deployed at the store entrance and the aisle at the store entrance. In this way, for the technical solution provided by the present disclosure, there is no need to deploy additional cameras, the maintenance cost of the data source, etc., can be saved, and existing resources can also be fully utilized.

Exemplarily, after the video stream for the first target place is obtained, the video stream can be framed, so that pedestrian detection and tracking can be performed on the video frames in the video stream, so that the position change of the pedestrian in the video stream can be determined. , to get the trajectory information of pedestrians in the video stream.

S102: Determine, based on the trajectory information of pedestrians in the video stream, the number of the first flow of people entering the first target place and the number of the second flow of people passing through the first target place within a preset time period.

Exemplarily, the preset duration may be a duration set by the user according to requirements. For example, when the store entry rate needs to be counted during the working hours of the store in one day, the preset duration may include the duration from the opening of the store to the closing of the store. Among them, the user refers to the person who has the authority to adjust the displayed items, such as the operator/manager of the store, the person in charge of the shopping mall, or has the ability to provide directional opinions for adjusting the information, which is not limited here.

Of course, the preset duration can also be automatically generated according to certain rules, for example, set based on the opening period of the area of the first target site. In the actual application process, with the adjustment of the rules, the preset duration can also be automatically adjusted periodically or non-periodically. For example, if the business hours are different in summer and autumn, the preset duration can also be According to the time node specified in the rules, it can be adjusted to a longer period or a shorter period, and the specific adjustment method is not limited.

Exemplarily, the track information of pedestrians in the video stream obtained within the preset time length and the target area corresponding to the entrance of the store in the video stream can be used to determine the number of the first flow of people entering the store within the preset time length, and The number of second people passing through the store.

S103, based on the first number of people and the second number of people, generating adjustment information for the items displayed in the second target place.

Exemplarily, the second target location is the same as the first target location, or the second target location is an associated location that is associated with the first target location.

For example, the first target location and the second target location are the same store, such as store A. In this way, through the number of the first traffic entering Store A and the number of second traffic passing through Store A within a preset time period, a specific target for the store can be generated. A Adjustment information of displayed items.

For another example, the second target location and the first target location are associated locations. The associated place refers to an association relationship between two types of places (the first target place and the second target place), and the association relationship may be a place belonging to the same series or a place with a subordinate relationship. Wherein, belonging to the same series of places means that the first target place and the second target place are of the same type and/or the same object-oriented. For example, the first target place and the second target place belong to the same shoe store. It can be a shoe store of the same brand, or both the first target location and the second target location are for children. Sites with affiliation relationships refer to the relationship between the first target site and the second target site in a progressive or declining hierarchy. For example, the first target site and the second target site are of the same type, but the first target site is relatively The second target place belongs to a member store or a high-end store, and similarly, the first target place belongs to an ordinary store or a cheap store compared to the second target place. For example, the first target location is store A, and the second target location is store A's chain store - store B. Considering the correlation between chain stores, although the flow of people in store A cannot be equal to the flow of people in store B, there will be a certain similarity in the flow of people in the two stores. Therefore, you can enter store A within the preset time. The first flow of people and the second flow of people passing through store A are generated, and the adjustment information for the items displayed in store B is generated.

Exemplarily, the adjustment information for the items displayed in the second target place may include, but is not limited to, the adjustment information for the placement order of the displayed items, the adjustment information for the types of the displayed items, etc. The number of two people flow can reflect the store's entry rate within the preset time period, and it can reflect the user's preference for the items displayed in the store. For example, if the store’s entry rate is very low (that is, the number of first and second traffic is low, for example, lower than their corresponding regular traffic), it can reflect that the items displayed in the store may not be affected by users. I like it, so I can adjust the items displayed in the store appropriately.

In the embodiment of the present disclosure, the trajectory information of pedestrians in the video stream is obtained by collecting the video stream from the first target place, so that the pedestrian entering the first target place within a preset time period can be further quickly determined based on the trajectory information of pedestrians. The number of people passing through the first target place and the number of second people passing through the first target place, so that the adjustment information for the items displayed in the second target place can be quickly determined based on the quickly determined first and second flow numbers.

The foregoing S101 to S103 will be described below with reference to specific embodiments.

For the above S101, when determining the trajectory information of pedestrians in the video stream based on the video stream collected from the first target location, as shown in FIG. 2, S201-S203 may be included:

S201: Perform pedestrian detection on a target video frame in the video stream, and identify the position information of each pedestrian included in the target video stream.

Exemplarily, the target video frame is each frame of video frames obtained sequentially in the order of collection time after the video stream is subjected to frame-by-frame processing, or it can be the frame-by-frame processing of the video stream at intervals of one frame or set in the order of collection time. The video frame obtained by the frame is not limited here.

Exemplarily, a pedestrian recognition algorithm may be used to perform pedestrian detection on the target video frame to obtain position information of each pedestrian included in the target video frame. In addition, considering that there may be occlusion between different pedestrians in the target video frame, the complete body information of the whole person may not be detected from the target video frame. Therefore, when pedestrian detection is performed on the target video frame in the video stream, it can be Consider adopting the head and shoulders detection algorithm to complete the detection of pedestrians in the target video frame, and determine the position information of each pedestrian contained in the target video frame. Among them, the head and shoulders detection algorithm refers to the identification of the pedestrian's head and shoulders in the target video frame to obtain the position information indicating the pedestrian's head feature points and shoulders, so as to obtain the detection indicating the pedestrian's head and shoulders position. frame, the position of the center position of the detection frame in the target video frame can be used as the position of the pedestrian in the target video frame.

S202: Determine the position information of the target pedestrian in the video stream according to the position information of each pedestrian included in the target video frame.

Exemplarily, after the capture pose of the video capture component is fixed, the target video frame in the video stream may correspond to the same coordinate system, and by determining the position information of each pedestrian contained in the target video frame under the same coordinate system, it can be Determine the location information of the target pedestrian in the video stream.

The target pedestrian may be each pedestrian in the target video frame, or may be a specific pedestrian or multiple pedestrians. In this way, the position information of the target pedestrian in the video stream can be determined based on the position information of the target pedestrian in the target video frame. For example, the position information of the target pedestrian in the target video frame in the first frame is position A, and in the second frame The position information in the target video frame is position B, and the position information in the third frame of the target video frame is position C, then the position information of the target pedestrian in the video stream is arranged in time sequence, including position A, position B and position C in turn .

S202: Determine the trajectory information of the target pedestrian according to the position information of the target pedestrian in the video stream.

Exemplarily, the track information of the target pedestrian can be quickly determined according to the position information of the target pedestrian in the video stream and the time sequence of the target video frames, for example, the position information of the target pedestrian in the video stream determined above includes the position A. , position B and position C, and the acquisition time of the first frame target video frame is earlier than the acquisition time of the second frame target video frame, and the second frame target video frame acquisition time is earlier than the third frame target video frame acquisition time, so The trajectory information of the target pedestrian is from position A to position B, and then from position B to position C.

Exemplarily, the target video frame may contain multiple different pedestrians. Therefore, in the process of pedestrian detection on the target video frame, in order to determine the trajectory information of the target pedestrian, it is necessary to determine the target in different target video frames. Therefore, before determining the position information of the target pedestrian in the video stream according to the position information of each pedestrian included in the target video frame, the information processing method provided by the embodiment of the present disclosure further includes the following S2011-S2013:

S2011: Acquire characteristic information of pedestrians in the target video frame.

Exemplarily, after it is determined that the video frame of the target frame contains the head and shoulders information of the pedestrian, feature information for describing the head and shoulders of the pedestrian can be extracted from the target video frame, for example, the outline feature, shape feature, and color feature of the head and shoulders may be included. , one or more combinations of texture features and motion features.

S2012 , based on the feature information of pedestrians contained in different target video frames respectively, determine the feature similarity between pedestrians contained in different target video frames.

Exemplarily, for example, for any two adjacent target video frames, they are respectively denoted as the first target video frame and the second target video frame, if the first target video frame and the second target video frame both contain three pedestrians respectively. , the pedestrians contained in each target video frame can be distinguished by the serial number and other identifiers. For example, the three pedestrians in the first target video frame are recorded as the first pedestrian, the second pedestrian and the third pedestrian. Similarly, The three pedestrians in the second target video frame are recorded as the first pedestrian, the second pedestrian, and the third pedestrian, respectively.

Further, based on the feature information of the first pedestrian in the first target video frame and the corresponding feature information of the three pedestrians in the second target video frame, it can be determined that the first pedestrian in the first target video frame is The feature similarity between the three pedestrians contained in the second target video frame, and then determine the similarity between the second pedestrian contained in the first target video frame and the three pedestrians contained in the second target video frame in the same way. feature similarity, and the feature similarity between the third pedestrian and the three pedestrians contained in the second target video frame, respectively.

S2013, taking the pedestrian corresponding to the maximum similarity higher than the preset similarity threshold in the feature similarity as the target pedestrian.

Exemplarily, taking the above process of determining the feature similarity between the first pedestrian in the first target video frame and the three pedestrians included in the second target video frame as an example, for example, the first pedestrian in the first target video frame The feature similarity between the individual pedestrian and the second pedestrian contained in the second target video frame is higher than the threshold, and is the largest similarity among the obtained three feature similarities, then the first pedestrian in the first target video frame The same pedestrian as the second pedestrian in the second target video frame can be recorded as the target pedestrian, and it can also be determined that the second pedestrian and the third pedestrian in the first target video frame are the same pedestrian.

Exemplarily, when there are multiple target pedestrians, each target pedestrian can be encoded according to the same ID, that is, the same pedestrian appearing in different video frames is marked with the same ID, so as to complete the identification of multiple pedestrians. The marking process is convenient to track the trajectory of the target pedestrian through ID.

In the embodiments of the present disclosure, it is proposed that the target pedestrians in different target video frames can be determined by extracting the characteristic information of the pedestrians contained in the target video frames, which provides convenience for subsequent tracking of the target pedestrians to determine the trajectory information of the target pedestrians.

For the above S102, when determining the number of the first flow of people entering the first target place within the preset time period based on the track information of pedestrians in the video stream, the method includes: based on the track information and the first determination flag, determining the number of people entering the first target place within the preset time period. The number of pedestrians in a target place is counted to obtain the first number of pedestrian flows, wherein the first judgment flag is used to judge whether the pedestrian enters the first target place.

The first determination mark may be a pre-drawn determination line for determining whether the pedestrian enters the first target place. Specifically, the incoming direction and outgoing direction can be marked for the determination line, the trajectory direction of the pedestrian in the video stream matches the incoming direction, and it can be determined that the pedestrian is entering the first target place, and based on this, the number of the first pedestrian flow within the preset time period can be counted .

For the above S102, when determining the number of second flows of people passing through the first target place within a preset time period based on the trajectory information of pedestrians in the video stream, the method includes: based on the trajectory information, the first determination flag and the second determination flag, determining the number of the pre- Set the number of pedestrians who pass through the first target place and do not enter the first target place within the time period to be counted to obtain the second number of pedestrian flows; wherein, the first judgment mark is used to judge whether the pedestrian enters the first target place, and the second judgment mark is used for It is judged whether the pedestrian passes through the first target place.

The first judgment mark may be the above-mentioned judgment line, and the second judgment mark may be a pre-drawn judgment area for judging whether the pedestrian passes through the first target place, and the pedestrian is determined according to the track information of the pedestrian in the video stream. If the trajectory is entering the determination area and does not enter the first target place, it can be determined that the pedestrian passes through the first target place, and based on this, the number of the second pedestrian flow within the preset time period can be counted.

Exemplarily, the number of pedestrians entering the first target place within a preset time period can be determined through the pedestrian's trajectory information and the judgment line in the video stream, and the pedestrian's trajectory information, the judgment line, and the judgment area in the video stream can be determined. , and determine the number of pedestrians who pass through the first target place within a preset time period and do not enter the first target place.

In one embodiment, as shown in FIG. 3 , which is a schematic diagram of a first target place, the first target place may be a store A, where a storefront display area is deployed near the entrance and exit. Among them, the entrance and exit are the only channels set up by store A. In the actual deployment process, store A may also include multiple channels, for example, including two channels, one for the exit and one for the entrance, or both channels are entrances and exits . The store front display area may include, but is not limited to, a store window, an area in the store near the entrance and exit for displaying commodities, and the like, which is not limited herein. Referring to FIG. 3 , the determination line may be located outside the determination area, close to the side of the entrance and exit of the store.

In order to ensure the reliability of the obtained first and second flow of people, the determination line can usually be set in the area where the entrance and exit of store A are located, which can be coincident with the location of the entrance and exit of store A, or located inside store A, close to the entrance and exit. position (ie, the judgment line shown in Figure 3). The determination area may be set outside the store A, near the entrance and exit. Usually, the location of the entrance and exit can be located between the judgment line and the judgment area. Of course, the location of the entrance and exit can also overlap with the judgment line and the judgment area. The locations overlap. In the actual deployment process, the determination line may also be located within the determination area, or the determination line may overlap with an edge of the determination area near the entrance and exit and be located outside the store near the entrance and exit.

Referring to FIG. 3 , it can be determined whether the pedestrian has crossed the judgment line through the trajectory information of the pedestrian in the video stream, and since the judgment line is located in the store, the pedestrian who has crossed the judgment line can be determined as the pedestrian entering the store through the entrance and exit, thereby The number of pedestrians passing through the first target place within the preset time period is counted. In addition, it is possible to count the pedestrians who pass through the judgment area within the preset time period and do not cross the judgment line to enter the store through the track information of pedestrians in the video stream, so that it can be obtained that they pass through the first target place within the preset time period and do not enter the store. The number of pedestrians at the first target site.

It should be noted that the length of the determination line, the size of the determination area, and the relationship between each of them and the store are not limited in the present disclosure, and may include, but are not limited to, examples. In addition, similarly, one or more locations among the store B and the store C shown in FIG. 3 may also be determined as the first target location, which is not limited herein.

In one embodiment, the first target place includes a first store within a set area, and for the above S103, when generating adjustment information for the items displayed in the second target place based on the first and second traffic numbers , as shown in FIG. 4 , may include the following S301 to S302:

S301 , determining a store entry rate of a first store within a preset time period based on the number of the first flow of people and the number of the second flow of people.

Exemplarily, the set range area may include a shopping mall, a designated area in a shopping mall, a certain street, or a designated area of a certain street, and the like, and the first store may be any store within the set range area.

Exemplarily, the first flow of people may include the number of pedestrians who enter the first store within a preset time period, and the second flow of people may include the number of pedestrians who pass through the first store within the preset time period but do not enter the first store. , the store entry rate of the first store within the preset time period can be determined by the first manpower quantity and the second crowd flow quantity.

Specifically, when determining the store entry rate of the first store within a preset period of time based on the number of the first crowd and the number of the second crowd, it may include:

S3011, summing the first number of people and the second number of people to obtain the total number of people passing through the first target place within a preset time period;

S3012, taking the ratio of the first number of people flow to the total number of people flow as the store entry rate of the first store within a preset time period.

Specifically, the store entry rate of the first store within the preset time period can be determined according to the following formula:

Among them, R _t represents the entry rate of the first store within the preset time period; P _in(t) represents the number of first people entering the first store within the preset time period; P _pass(t) represents the preset time period. The number of the second flow of people passing through the first store, t is used to represent the time period corresponding to the preset duration, so as to indicate that the above parameters reflect the parameters generated in the same time period t.

In the embodiment of the present disclosure, when the first target place is a store, the store entry rate of the store within a preset period of time can be determined through video stream detection, which saves the time required to manually count the store entry rate and improves the process of obtaining store entry rates. store rate efficiency.

S302 , based on the store entry rate of the first store within a preset time period, generate adjustment information for the items displayed in the second target field.

Exemplarily, the items displayed in the second target place are the same as the items displayed in the first store, so the user behavior data of the first store in a certain period of time can be counted in advance to determine the quality of the items displayed in the first store. popularity, and use this to determine adjustment information for the items displayed in the second target venue.

In one embodiment, the first store includes at least two stores, and the store entry rate of each first store can be determined in the above manner. For the above S302, based on the store entry rate of the first store within a preset time period , when generating adjustment information for the items displayed in the second target field, including: based on the corresponding store entry rate of each store in the first store within the same statistical period, and the items displayed in each store within the same statistical period, generating Adjustment information for items displayed in the second target location.

Exemplarily, the statistical period is an integer multiple of the preset time period, such as a quarter or an activity cycle, based on the corresponding store entry rate of each store in the same statistical period, and the display of each store in the same statistical period. The first user behavior statistical result for each store is determined; wherein, the first user behavior statistical result is used to reflect the user's preference for different item types in the same statistical period.

Exemplarily, the preset duration may be the working hours of the first store on that day, for example, it may be 8 hours, and the statistical period may include a quarter, such as spring. The popularity of the store during the statistical period. The statistical results can be used to adjust the items displayed in the store.

Specifically, when the adjustment information for the items displayed in the second target place is generated based on the corresponding store entry rate of each store in the first store within the same statistical period and the items displayed in each store within the same statistical period, Including the following S3021～S3022:

S3021: Determine the first target store and the second target store from the first store based on the store entry rate corresponding to each store in the same statistical period, where the first target store is the store corresponding to the lowest store entry rate among the first stores, The second target store is the store corresponding to the highest entry rate among the first stores;

S3022 , taking the first target store as the second target place, and generating adjustment instruction information for the items displayed in the second target place based on the items displayed in the second target store.

Exemplarily, a plurality of first stores in a tourist business district can be counted on the store entry rate, and the first target store with the lowest store entry rate and the second target store with the highest store entry rate in the business district can be determined, The popularity of the items displayed in the second target store is higher than that of the items displayed in the first target store in the same statistical period. Therefore, for the second target place that is the same as the items displayed in the first target store, the second target store can For the displayed items, adjustment instruction information for the displayed items in the second target place is generated.

Exemplarily, according to the type of the items displayed in the second target store and/or the order in which the displayed items are placed in the store, the adjustment instruction information for the items displayed in the second target place can be generated, for example, indicating that the second target place can Adjust according to the items displayed in the second target store, or instruct the second target place to adjust according to the order of the items displayed in the second target store, or instruct the second target place to adjust according to the items displayed in the second target store and The order of placement of items has been adjusted.

In the embodiment of the present disclosure, by counting the corresponding store entry rates of different stores in the same statistical period, the first target store with the lowest store entry rate and the second target store with the highest store entry rate within the preset range can be selected. Further, according to the items displayed in the second target store, an adjustment plan can be formulated for the second target place that is the same as the first target store, and there is no need to additionally examine the store entry rate in the second target place, which can save labor costs and improve the determination of resource allocation. s efficiency.

In another embodiment, there is one first store, and for the above S302, when generating the adjustment information for the items displayed in the second target place based on the store entry rate of the first store within the preset time period, the process includes: based on The corresponding store entry rates of the first store in different statistical time periods and the items displayed by the first store in different statistical time periods respectively determine the adjustment information for the displayed items in the second target place.

Exemplarily, different statistical periods may include different quarters. For the same store, different items may be displayed in different quarters, or the same items may be displayed in different quarters. The corresponding store entry rate in the quarter determines the popularity of the items displayed in the first store in different quarters.

Further, according to the statistics of the popularity of the items displayed in the first store in different statistical periods, the adjustment information of the items displayed in the second target place associated with the first store can be generated, so that the second target place can be based on the adjustment. information to adjust resource allocation.

Specifically, in one embodiment, based on the respective store entry rates of the first store in different statistical time periods, and the items displayed by the first store in different statistical time periods respectively, generate items for display in the second target place. When adjusting the information, include the following S3023-S3024:

S3023, in the case that the items displayed by the first store in different statistical periods are the same, determine the target display period corresponding to the items displayed in the first shop based on the corresponding store entry rates of the first shop in different statistical periods; The store entry rate corresponding to the target display period is greater than or equal to the preset store entry rate threshold;

S3024 , based on the target display period, generate adjustment information for the items displayed in the second target place during the target display period.

Exemplarily, the preset store entry rate threshold may be obtained in advance according to big data statistics, for example, according to the relationship between the store entry rate of the store and the sales quantity, the store entry rate corresponding to when the sales quantity reaches the requirement may be selected as the preset value. Store entry rate threshold; or the preset store entry rate threshold can be set manually, which is not limited here.

Exemplarily, for example, the items displayed in the first store in different quarters are the same, and it can be determined in which quarter the items displayed in the first store are most popular according to the corresponding store entry rates of the first store in different quarters. For example, the store entry rate corresponding to the first store in spring and autumn is greater than or equal to the preset store entry rate threshold, then spring and autumn can be used as the target display period corresponding to the items displayed in the first store.

Exemplarily, after the target display period corresponding to the items displayed in the first store is determined, the adjustment information for the items displayed in the second target place during the target display period may be generated based on the target display period, such as generating information indicating the second target place. The items displayed in the spring and fall are the same as the items displayed in the first store, and/or the order in which the items displayed in the spring and autumn are generated indicating the second target location is consistent with the order in which the items displayed in the first store are displayed.

In another embodiment, the adjustment for the items displayed in the second target place is generated based on the respective store entry rates of the first store in different statistical time periods and the items displayed by the first store in different statistical time periods. Information, including the following S3025 ~ S3026:

S3025, in the case that the items displayed by the first store in different statistical time periods are different, determine that the first store is in different The matching degree between the items displayed in the statistical period and the corresponding display period;

S3026 , based on the determined matching degree, generate adjustment information for the items displayed in the second target place during a specific display period.

Exemplarily, for example, the items displayed by the first store in different quarters are different, according to the corresponding store entry rates of the first store in different quarters, it can be determined that the items displayed by the first store in different statistical periods correspond to The matching degree between the display periods, the higher the store entry rate corresponding to any statistical period, the higher the popularity of the items displayed by the first store in the any statistical period, and it can be considered that the first store is in the any statistical period. The higher the degree of matching between the displayed items and the item's display period, the lower the corresponding store entry rate in any statistical period, it is considered that the first store displayed the items in any statistical period and the items displayed in the display period. The lower the match.

Exemplarily, after determining the matching degree between the items displayed in the first store in different statistical periods and the corresponding display period, it can be determined according to the matching degree that the item is displayed in a specific display period, for example, when the matching degree is higher than the preset matching degree. The display period of the degree threshold, the adjustment information for the items displayed in the second target site, such as generating an indication that the items displayed in the second target site in a specific display period are the same as the items displayed in the first store in a specific period, and/or generating an indication The order in which the items displayed in the second target place during the specific display period is consistent with the order in which the items displayed in the first store during the specific period are placed

In some scenarios, a large number of inflows and outflows of people may occur in the first target place within a preset period of time. For safety reasons, it is generally necessary to detect the inflows and outflows of people in the first target place to avoid dangerous accidents.

In an implementation manner, the information processing method provided by the embodiment of the present disclosure further includes: in the case where it is determined that the number of the first flow of people is greater than the first preset threshold, generating first warning prompt information.

Exemplarily, the first preset threshold may be set according to actual needs, for example, may be set according to the type of the first target place, the statistical time period, the size of the entrance of the first target place, and the like.

The generated first warning prompt information can be information in the format of text, voice, video, etc. For example, the generated first early warning prompt information can be "Attention, the number of people entering the first target place is large, please pay attention to safety".

In the embodiment of the present disclosure, the number of people entering the first target place within a preset time period can be counted, and when it is determined that the number of people entering the first target place is large within the preset time period, early warning information can be generated to improve pedestrians’ Security when entering the first target site.

In an implementation manner, as shown in FIG. 5 , the information processing method provided by the embodiment of the present disclosure further includes the following S401 to S402:

S401 , based on the trajectory information and a first determination flag, determine the number of third pedestrians leaving the first target place within a preset time period, and the first determination flag is used to determine whether the pedestrian enters the first target place.

Exemplarily, the pre-drawn first judgment mark for judging whether the pedestrian leaves the first target place may be the same as the judgment line shown in FIG. 3 for judging whether the pedestrian enters the first target place. The outgoing direction opposite to the incoming direction is used as the direction to leave the first target place. The track direction of the pedestrian in the video stream matches the outgoing direction, and it can be determined that the pedestrian is leaving the first target place. The number of three streams.

S402 , when it is determined that the number of the third crowd is greater than the second preset threshold, generate second warning prompt information.

Exemplarily, the second preset threshold may be set according to actual needs, for example, may be set according to the type of the first target place, the statistical time period, the exit size of the first target place, and the like.

The generated second warning prompt information can be information in the format of text, voice, video, etc. For example, the generated second early warning prompt information can be "Attention, the number of people leaving the first target place is large, please pay attention to safety".

In a possible implementation, as shown in FIG. 6 , the information processing method provided by the embodiment of the present disclosure further includes the following S501 to S502:

S501, based on the number of people remaining in the history of the first target place within the preset time period, the number of the first flow of people, and the number of the third flow of people, determine the net stock of personnel in the first target place within the preset time period;

S502 , when it is determined that the net personnel stock at the first target place within a preset time period is greater than a third preset threshold, generate third warning prompt information.

Exemplarily, the number of people remaining in the history of the first target place within the preset time period may be the number of people currently existing in the first target place when the first and third crowds are counted, for example, the first target place has Pedestrians are allowed to enter from 8:00 on the same day. When calculating the current net stock of people from 9:00 to 10:00, the current number of people corresponding to the first target place at 9:00 can be used as the first target place at 9:00 to 10:00: 00 number of people left in history, the number of people left in history can be determined by the difference between the number of incoming traffic and the number of outgoing traffic counted in the historical stage (8:00-9:00).

Further, the number of people entering the first target place within the preset time period can be determined through the number of the first and third people, and the number of people who have entered the first target place within the preset time period can be determined, and the first target place can be determined. The net stock of personnel over a preset period of time.

Exemplarily, the third preset threshold may be set according to actual needs, for example, may be set according to the type of the first target place, the statistical time period, the capacity of the first target place, and the like.

The generated third warning prompt information may be information in the format of text, voice, video, etc. For example, the generated third early warning prompt information may be "Attention, there are a lot of net personnel in the first target site at the current time".

Those skilled in the art can understand that in the above method of the specific implementation, the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.

Based on the same technical concept, the embodiment of the present disclosure also provides an information processing apparatus corresponding to the information processing method. Reference may be made to the implementation of the method, and repeated descriptions will not be repeated.

Referring to FIG. 7 , which is a schematic diagram of an information processing apparatus 600 provided by an embodiment of the present disclosure, the information processing apparatus 600 includes: an obtaining module 601, configured to obtain the information in the video stream based on the video stream collected from the first target location. The track information of pedestrians; the determining module 602 is used for determining the number of the first flow of people entering the first target place and the number of the second flow of people passing through the first target place within a preset time period based on the track information of the pedestrians in the video; the generating module 603 , which is used to generate adjustment information for the items displayed in the second target place based on the first number of people and the second number of people.

In a possible implementation, the first target place includes a first store within a set area, and the generating module 603 is configured to generate items for display in the second target place based on the first number of people and the second number of people When adjusting the information, it includes: determining the store entry rate of the first store within the preset time period based on the number of the first traffic flow and the number of the second traffic flow; Adjustment information for items displayed in the target arena.

In a possible implementation manner, the first store includes at least two, and the generating module 603 is configured to generate adjustment information for items displayed in the second target place based on the store entry rate of the first store within a preset period of time ,include:

Based on the corresponding store entry rate of each store in the first store within the same statistical time period, and the items displayed by each store in the same statistical time period, the adjustment information for the displayed items in the second target place is generated.

In a possible implementation manner, the generating module 603 is used to generate the corresponding store entry rate of each store in the first store in the same statistical period and the items displayed in each store in the same statistical period The adjustment information of the items displayed in the second target place includes: determining the first target store and the second target store from the first store based on the corresponding store entry rate of each store in the same statistical period, and the first target store is the first target store. The store corresponding to the lowest entry rate in one store, the second target store is the store corresponding to the highest entry rate in the first store; taking the first target store as the second target location, based on the items displayed in the second target store, generate Adjustment instruction information for items displayed in the second target place.

In a possible implementation manner, there is one first store, and when the generating module is used to generate adjustment information for the items displayed in the second target place based on the store entry rate of the first store within a preset period of time, the generating module includes: Based on the respective store entry rates of the first store in different statistical periods, and the items displayed by the first store in different statistical periods, adjustment information for items displayed in the second target place is generated.

In a possible implementation, the generating module 603 is used to generate the second target based on the store entry rates corresponding to the first store in different statistical time periods and the items displayed by the first store in different statistical time periods. The adjustment information of the items displayed in the venue includes: in the case that the items displayed by the first store in different statistical time periods are the same, determining the first store based on the corresponding store entry rates of the first store in different statistical time periods. The target display period corresponding to the displayed items; the store entry rate corresponding to the target display period is greater than or equal to the preset store entry rate threshold; based on the target display period, the adjustment information for the items displayed in the second target place during the target display period is generated.

In a possible implementation, the generating module 603 is used to generate the second target based on the store entry rates corresponding to the first store in different statistical time periods and the items displayed by the first store in different statistical time periods. The adjustment information of the items displayed in the venue includes: in the case that the items displayed by the first store in different statistical time periods are different, determining the first store based on the corresponding store entry rates in the different statistical time periods Matching degree between the items displayed by the store in different statistical periods and the corresponding display periods; based on the determined matching degree, the adjustment information for the items displayed in the second target place during the specific display period is generated.

In a possible implementation, when the generating module 603 is used to determine the store entry rate of the first store within a preset time period based on the first number of people and the second number of people, it includes: based on the first number of people and the first number of people The number of two people flows to get the total number of people; the ratio of the first number of people to the total number of people is used as the entry rate of the first store within the preset time period.

In a possible implementation manner, when the acquiring module 601 is used to acquire the track information of pedestrians in the video stream based on the video stream collected from the first target location, it includes: performing pedestrian detection on the target video frame in the video stream, Identify the position information of each pedestrian contained in the target video frame; determine the position information of the target pedestrian in the video stream according to the position information of each pedestrian contained in the target video frame; according to the position information of the target pedestrian in the video stream shown , to determine the trajectory information of the target pedestrian.

In a possible implementation manner, before determining the trajectory information of the target pedestrian according to the position information of the target pedestrian in the video stream, the acquisition module 601 is further configured to: acquire the characteristic information of the pedestrian in the target video frame; based on different targets The feature information of pedestrians contained in the video frames respectively determines the feature similarity between pedestrians contained in different target video frames; the pedestrian corresponding to the maximum similarity higher than the preset similarity threshold in the feature similarity is regarded as the target pedestrian.

In a possible implementation manner, when the determining module 602 is used to determine the number of the first flow of people entering the first target place within a preset time period based on the trajectory information of pedestrians in the video stream, the method includes: based on the trajectory information and the first The determination flag is used to count the number of pedestrians entering the first target place within a preset time period to obtain the first flow of people, and the first determination flag is used to determine whether the pedestrians enter the first target place.

In a possible implementation manner, when the determining module 602 is configured to determine the number of second flows of people passing through the first target place within a preset time period based on the trajectory information of pedestrians in the video stream, the method includes: based on the trajectory information, the first The determination flag and the second determination flag are used to count the number of pedestrians who have passed through the first target place and did not enter the first target place within the preset time period to obtain the second number of pedestrian flows, and the first determination flag is used to determine whether the pedestrian has entered the first target. place, and the second judgment flag is used to judge whether the pedestrian passes through the first target place.

In a possible implementation, the information processing device 600 further includes a first early warning module 604, and the first early warning module 604 is configured to: generate a first early warning prompt when it is determined that the number of the first crowd is greater than a first preset threshold information.

In a possible implementation manner, the information processing apparatus further includes a second early warning module 605, and the determination module 602 is further configured to: determine, based on the trajectory information and the first determination flag, a third person who has left the first target place within a preset time period. The number of people flow, the first judgment flag is used to judge whether the pedestrian enters the first target place; the second early warning module 605 is used to generate the second warning prompt information when it is determined that the third number of people flow is greater than the second preset threshold.

In a possible implementation, the determining module 602 is further configured to: determine the preset duration of the first target place based on the number of people remaining in the history of the first target place within the preset duration, the number of first crowds and the number of third crowds The second warning module 605 is further configured to generate third warning prompt information when it is determined that the net stock of personnel in the first target location within the preset time period is greater than the third preset threshold.

For the description of the processing flow of each module in the apparatus and the interaction flow between the modules, reference may be made to the relevant descriptions in the foregoing method embodiments, which will not be described in detail here.

Corresponding to the information processing method in FIG. 1 , an embodiment of the present disclosure further provides an electronic device 700 . As shown in FIG. 8 , a schematic structural diagram of the electronic device 700 provided by the embodiment of the present disclosure includes: a processor 71 and a memory 72 , and bus 73; memory 72 is used to store execution instructions, including memory 721 and external memory 722; the memory 721 here is also called internal memory, which is used to temporarily store operation data in processor 71 and exchange with external memory 722 such as hard disks The data, the processor 71 exchanges data with the external memory 722 through the memory 721, and when the electronic device 700 is running, the processor 71 and the memory 72 communicate through the bus 73, so that the processor 71 executes the following instructions: based on the first target From the video stream collected by the venue, obtain the trajectory information of pedestrians in the video stream; based on the trajectory information of pedestrians in the video stream, determine the number of first pedestrians entering the first target venue and the second traffic passing through the first target venue within a preset period of time. Quantity; based on the number of the first flow of people and the number of the second flow of people, the adjustment information for the items displayed in the second target place is generated.

Embodiments of the present disclosure also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the information processing method described in the above method embodiments are executed. Wherein, the storage medium may be a volatile or non-volatile computer-readable storage medium.

Embodiments of the present disclosure further provide a computer program or computer program product, where the computer program or computer program product carries a program code, and the instructions included in the program code, when executed by a processor, cause the processor to execute the foregoing method embodiments For the steps of the information processing method described in , refer to the above method embodiments for details, and details are not repeated here.

Wherein, the above-mentioned computer program product can be specifically implemented by means of hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.

Those skilled in the art can clearly understand that, for the convenience and brevity of description, for the specific working process of the system and device described above, reference may be made to the corresponding process in the foregoing method embodiments, which will not be repeated here. In the several embodiments provided by the present disclosure, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. The apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces, indirect coupling or communication connection of devices or units, which may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a processor-executable non-volatile computer-readable storage medium. Based on such understanding, the technical solutions of the present disclosure can be embodied in the form of software products in essence, or the parts that contribute to the prior art or the parts of the technical solutions. The computer software products are stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

The above-mentioned embodiments are only specific implementations of the present disclosure, and are used to illustrate the technical solutions of the present disclosure, but not to limit them. Detailed description, those of ordinary skill in the art should understand: any person skilled in the art is within the technical scope disclosed by the present disclosure, he can still modify the technical solutions described in the foregoing embodiments or can easily think of changes, Or equivalently replace some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

An information processing method, comprising the following operations performed by a computer device:

Obtaining track information of pedestrians in the video stream based on the video stream collected from the first target location;

determining, based on the trajectory information of pedestrians in the video stream, the number of first pedestrians entering the first target place and the number of second pedestrians passing through the first target place within a preset time period;

Based on the first crowd flow quantity and the second crowd flow quantity, adjustment information for the items displayed in the second target place is generated.
The information processing method according to claim 1, wherein the second target place is the same as the first target place, or the second target place is an association with the first target place place.
The information processing method according to claim 1 or 2, wherein the first target location includes a first store within a set range area, and the first target location is based on the first number of people and the second number of people , generating adjustment information for the items displayed in the second target place, including performing the following operations by the computer equipment:

determining the store entry rate of the first store within the preset time period based on the first number of people and the second number of people;

Based on the store entry rate of the first store within the preset time period, adjustment information for the items displayed in the second target field is generated.
The information processing method according to claim 3, wherein the first store includes at least two, and the second target is generated based on a store entry rate of the first store within the preset time period. Adjustment information for items displayed in the premises, including the following operations performed by computer equipment:

Based on the corresponding store entry rate of each store in the first store within the same statistical period, and the items displayed by each store within the same statistical period, generate a list of items displayed in the second target place. Adjust information.
The information processing method according to claim 4, wherein the store entry rate corresponding to each store in the first store in the same statistical period, and the basis of each store in the same statistical period generating the adjustment information for the items displayed in the second target place, including performing the following operations by the computer device:

Based on the store entry rate corresponding to each store in the same statistical period, a first target store and a second target store are determined from the first stores, and the first target store is the lowest entry rate among the first stores. The store corresponding to the store rate, and the second target store is the store corresponding to the highest store entry rate in the first store;

The first target store is used as the second target place, and based on the items displayed in the second target store, adjustment instruction information for items displayed in the second target place is generated.
The information processing method according to claim 3, wherein the number of the first store is one, and the method for generating the first store in the second target place is based on the store entry rate of the first store within the preset time period. Adjustment information for displayed items, including the following actions performed by computer equipment:

The adjustment information for the items displayed in the second target place is generated based on the respective store entry rates of the first store in different statistical time periods and the items displayed by the first store in different statistical time periods.
The information processing method according to claim 6, wherein the store entry rate corresponding to the first store in different statistical time periods and the items displayed by the first store in different statistical time periods , generating adjustment information for the items displayed in the second target place, including performing the following operations by a computer device:

In the case that the items displayed by the first store in different statistical periods are the same, determine the corresponding items of the items displayed in the first shop based on the respective store entry rates corresponding to the first shop in different statistical periods. target display period; the store entry rate corresponding to the target display period is greater than or equal to the preset store entry rate threshold;

Based on the target display period, adjustment information for the items displayed in the second target location during the target display period is generated.
The information processing method according to claim 6, wherein the store entry rate corresponding to the first store in different statistical time periods and the items displayed by the first store in different statistical time periods , generating adjustment information for the items displayed in the second target place, including performing the following operations by a computer device:

In the case where the items displayed by the first store in different statistical time periods are different, determine the first store in different statistical time periods based on the respective store entry rates of the first store in different statistical time periods The degree of matching between the displayed items and the corresponding display period;

Based on the determined degree of matching, adjustment information is generated for the items displayed in the second target venue during a specific display period.
The information processing method according to any one of claims 3 to 8, characterized in that, determining the entry of the first store within the preset time period based on the first flow of people and the second flow of people rate, including by computer equipment:

Based on the first number of people and the second number of people, obtain the total number of people;

The ratio of the first number of people to the total number of people is used as the store entry rate of the first store within the preset time period.
The information processing method according to any one of claims 1 to 9, wherein the acquiring the trajectory information of pedestrians in the video stream based on the video stream collected from the first target site comprises performing the following operations by a computer device :

Perform pedestrian detection on the target video frame in the video stream, and identify the position information of each pedestrian included in the target video frame;

According to the position information of each pedestrian contained in the target video frame, determine the position information of the target pedestrian in the video stream;

According to the position information of the target pedestrian in the video stream, the trajectory information of the target pedestrian is determined.
The information processing method according to claim 10, wherein before determining the position information of the target pedestrian in the video stream according to the position information of each pedestrian included in the target video frame, the information The processing method also includes, by the computer device, performing the following operations:

obtaining the characteristic information of pedestrians in the target video frame;

Determine the feature similarity between the pedestrians contained in the different target video frames based on the feature information of the pedestrians contained in the different target video frames respectively;

The pedestrian corresponding to the maximum similarity higher than the preset similarity threshold in the feature similarity is used as the target pedestrian.
The information processing method according to any one of claims 1 to 11, characterized in that, based on the trajectory information of pedestrians in the video stream, determining the number of the first stream of people entering the first target place within a preset time period, comprising: The following actions are performed by computer equipment:

Based on the trajectory information and the first determination mark, the number of pedestrians entering the first target place within the preset time period is counted to obtain the first number of pedestrian flows, and the first determination mark is used to determine whether the pedestrian is Enter the first target location.
The information processing method according to any one of claims 1 to 12, wherein, based on the trajectory information of pedestrians in the video stream, determining the number of the second stream of people passing through the first target place within a preset time period, comprising: The following actions are performed by computer equipment:

Based on the trajectory information, the first determination flag and the second determination flag, count the number of pedestrians who pass through the first target place and do not enter the first target place within the preset time period to obtain the second The number of people flow, the first judgment mark is used to judge whether the pedestrian enters the first target place, and the second judgment mark is used to judge whether the pedestrian passes through the first target place.
The information processing method according to any one of claims 1 to 13, wherein the information processing method further comprises performing the following operations by a computer device:

In the case that it is determined that the number of the first flow of people is greater than the first preset threshold, first warning prompt information is generated.
The information processing method according to any one of claims 1 to 14, wherein the information processing method further comprises performing the following operations by a computer device:

Based on the trajectory information and the first determination mark, determine the number of third pedestrians leaving the first target place within the preset time period, and the first determination mark is used to determine whether the pedestrian enters the first target place ;

In the case where it is determined that the number of the third crowd is greater than the second preset threshold, second warning prompt information is generated.
The information processing method according to claim 15, wherein the information processing method further comprises performing the following operations by a computer device:

Determine, based on the historical number of people staying at the first target place within the preset time period, the number of the first flow of people and the number of the third flow of people, the net number of people in the first target place within the preset time period stock;

In a case where it is determined that the net personnel stock of the first target place within the preset time period is greater than a third preset threshold, third warning prompt information is generated.
An information processing device, comprising:

an acquisition module, configured to acquire track information of pedestrians in the video stream based on the video stream collected from the first target site;

a determining module, configured to determine, based on the trajectory information of the pedestrians in the video, the number of the first flow of people entering the first target place and the number of the second flow of people passing through the first target place within a preset time period;

The generating module is configured to generate adjustment information for the items displayed in the second target place based on the first number of people and the second number of people.
An electronic device, characterized in that it includes: a processor, a memory, and a bus, the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate with each other. The machine-readable instructions are executed by the processor to perform the steps of the information processing method according to any one of claims 1 to 16.
A computer-readable storage medium, characterized in that, a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the information processing method according to any one of claims 1 to 16 are executed.
A computer program, characterized in that the computer program carries program code, and when the program code includes instructions that are executed by a processor, the processor executes the information processing method according to any one of claims 1 to 16. step.