CN110414424A

CN110414424A - Data processing system, method, platform, machine readable media and equipment

Info

Publication number: CN110414424A
Application number: CN201910680353.3A
Authority: CN
Inventors: 周曦; 姚志强; 万珺; 谢科; 陈江豪
Original assignee: Guangzhou Yuncong Information Technology Co Ltd
Current assignee: Guangzhou Yuncong Information Technology Co Ltd
Priority date: 2019-07-26
Filing date: 2019-07-26
Publication date: 2019-11-05

Abstract

The present invention provides a kind of data processing system, method, platform, machine readable media and equipment, including equipment access layer, network layer, data Layer, podium level；Equipment access layer, for obtaining corresponding physical characteristic data in one or more object space regions；Data Layer, it is connect by network layer with equipment access layer, whether the one or more physical characteristic datas acquired in object space region for judging equipment access layer meet preset physical characteristic data screening rule, and the physical characteristic data for meeting physical characteristic data screening rule is transmitted to podium level；Podium level, the physical characteristic data for being transmitted according to data Layer determine that one or more dimensions corresponding with physical characteristic data analyzes result.The present invention can complete the identification of line Xiamen customer's stream statistics, the consumption propensity of user analysis and user, to solve the problems, such as to obtain user data hardly possible under line；And deployment is simple, at low cost, stability is good.

Description

Data processing system, method, platform, machine readable media and equipment

Technical field

The present invention relates to data processing technique, more particularly to a kind of data processing system, method, platform, machine readable Medium and equipment.

Background technique

Xian Xia entity shops compares concern and is concentrated mainly on passenger flow statistics, consumption propensity, user identity identification etc. These aspects, and the difficulty that user data is obtained under line is very big.

Existing passenger flow statistics mainly using artificial statistics, checkout statistics, wifi counting, infrared counting, computer vision, The modes such as gravity sensing；It has the following disadvantages:

(1) using artificial statistics there are leakiness number, can not long-term stable work, it is at high cost the disadvantages of；

(2) using checkout statistics, to will lead to data not comprehensive；

(3) using wifi count because range reason cause it is not statistical uncertainty really；

(4) easily disturbed using infrared counting；

(5) high using gravity sensing equipment input cost, it is unstable；

(6) common Computer Vision Recognition is not statistical uncertainty really at present, can will be including the demographics such as employee.

Existing consumption propensity, which differentiates, mainly uses artificial judgment, research company, self-operation data, big data analysis；In the presence of Following disadvantage:

(1) lead to poor user experience because salesman's quality is irregular using artificial judgment；

(2) there is high the defects of relying on, is at high cost, non real-time in research company；

(3) there is the problems such as not comprehensive, fragmentation, at high cost in self-operation data；

(4) big data analysis there are data deficiency under line, it is at high cost the defects of.

Existing user identity identification almost relies on artificial judgment entirely, and salesman's Quality ability is irregular, can not accomplish pair Effective identification of all users.

Summary of the invention

In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide a kind of data processing system, method, Platform, machine readable media and equipment, for solving the problems, such as that acquisition user data difficulty is big under prior art middle line.

In order to achieve the above objects and other related objects, the present invention provides a kind of data processing system, includes that equipment connects Enter layer, network layer, data Layer, podium level；

The equipment access layer, for obtaining corresponding physical characteristic data in one or more object space regions；

The data Layer is connect by network layer with equipment access layer, for judging the equipment access layer in the mesh Whether the one or more physical characteristic datas acquired in mark area of space meet preset physical characteristic data screening rule, and The physical characteristic data for meeting the physical characteristic data screening rule is transmitted to podium level；

The podium level, the physical characteristic data for being transmitted according to the data Layer, determining and characteristics of human body's number Result is analyzed according to corresponding one or more dimensions.

Optionally, the physical characteristic data includes face characteristic data, human body load characteristic data.

Optionally, if the physical characteristic data is face characteristic, the face characteristic data include below extremely One of few: face picture clarity, face picture intensity of illumination, face picture are bowed angle, face picture new line angle, face Picture side face angle, face picture face characteristic point mass point.

Optionally, if the face characteristic data meet at least one the following conditions: face picture clarity, which is greater than, to be corresponded to Preset value, face picture intensity of illumination are greater than corresponding preset value, face picture is bowed, and angle is less than corresponding preset value, face picture New line angle is less than corresponding preset value, face picture side face angle is less than corresponding preset value, face picture face characteristic point mass Divide and be greater than corresponding preset value, then meets preset physical characteristic data screening rule.

Optionally, analysis result includes at least one of: consumption propensity analyzes result, consumption habit analyzes result.

It optionally, further include application layer；Wherein, the application layer, for showing the consumption propensity analysis result or institute State consumption habit analysis result.

Optionally, if the physical characteristic data is human body load characteristic data, the human body load characteristic data packet Include at least one of: human body wears characteristic, human body picks and places product features data.

Optionally, if one or more face characteristic numbers that the equipment access layer acquires in the object space region According to preset physical characteristic data screening rule is not met, then the podium level is in face characteristic data basis, in conjunction with human body It wears characteristic or human body picks and places product features data, determine one or more dimensions point corresponding with the face characteristic data Analyse result.

Optionally, it includes at least one of that the human body, which picks and places product features data: the action data of hand pick-and-place commodity, Product features data；Wherein, the product features data include at least one of: product name, commodity price, commodity bundle Dress.

Optionally, it includes at least one of that the human body, which wears characteristic: human body garment features data, body decorations Object characteristic.

Optionally, the body decorations object characteristic includes at least one of: the ring characteristic of human body wearing, The earrings data of bracelet data, human body wearing that human body is worn.

Optionally, the podium level is also preset with the presetting database for carrying out identification；

The podium level is by human face data in presetting database and the equipment access layer in the area of space The human face data of the personnel for meeting physical characteristic data screening rule of acquisition compares, and judges present count according to comparison result According in library with the presence or absence of meeting the human face data of physical characteristic data screening rule；If it exists, then it matches and the face number According to corresponding identity information；If it does not exist, then creation is this time collected in the area of space in application layer meets The human face data and identity information of physical characteristic data screening rule.

Optionally, the application layer also counts the podium level in certain time period and adopts in the object space region The number of the human face data successful match that meets physical characteristic data screening rule of collection, and statistics create in application layer What is acquired in the area of space meets the human face data of physical characteristic data screening rule.

It optionally, include for detecting and identifying equipment access layer in the object space region in the podium level The face recognition engine unit of the human face data of acquisition acquires in the object space region for counting equipment access layer Crowd's accounting engine unit of human face data in face picture, for analyze acquired in the object space region meet human body The attributive analysis engine unit of the human face data of characteristic screening rule；For storing pre-set database, storage is answered With the database server of layer newly created human face data and identity information.

The present invention also provides a kind of data processing methods, the method comprises the following steps:

Obtain corresponding physical characteristic data in one or more object spaces region；

If the one or more physical characteristic datas acquired in the object space region meet preset characteristics of human body Data screening rule, it is determined that one or more dimensions corresponding with the physical characteristic data analyzes result.

Optionally, if the one or more face characteristic data acquired in the object space region do not meet it is preset Physical characteristic data screening rule wears characteristic in conjunction with human body or human body picks and places quotient then in face characteristic data basis Product characteristic determines that one or more dimensions corresponding with the face characteristic data analyzes result.

Optionally, the consumption propensity analysis result or consumption habit analysis result are shown.

Optionally, the face characteristic data basis acquired in certain time period and in the object space region is counted On, in conjunction with human body wear characteristic or human body pick and place product features data, the number of successful match, and statistics from At least one of the following data acquired in the area of space: face characteristic data, human body wear characteristic, human body picks and places quotient Product characteristic.

The present invention also provides a kind of data processing cloud platforms, include data processing system described above.

The present invention also provides a kind of data processing equipments, comprising:

The one or more physical characteristic datas for judging that the equipment access layer acquires in the object space region are It is no to meet preset physical characteristic data screening rule, if meeting, according to the physical characteristic data that the data Layer transmits, really Fixed one or more dimensions corresponding with the physical characteristic data analyzes result.

The present invention also provides a kind of equipment, comprising:

One or more processors；With

One or more machine readable medias of instruction are stored thereon with, when one or more of processors execute, So that the equipment executes said one or multiple data processing methods.

The present invention also provides one or more machine readable medias, are stored thereon with instruction, handle when by one or more When device executes, so that equipment executes said one or multiple data processing methods.

As described above, a kind of data processing system based on human face data provided by the invention, method, platform, machine can Medium and equipment are read, line Xiamen customer's stream statistics, the analysis of the consumption propensity of user can be completed and use by having the advantages that The identification at family, to solve the problems, such as to obtain user data hardly possible under line；And deployment is simple, at low cost, stability is good.

Detailed description of the invention

Fig. 1 is data processing system principle connection schematic diagram.

Fig. 2 is the internal frame diagram of podium level.

Fig. 3 is the internal frame diagram of application layer.

Fig. 4 is data processing method flow diagram.

Fig. 5 is the hardware structural diagram for the terminal device that an embodiment provides.

Fig. 6 is the hardware structural diagram for the terminal device that another embodiment provides.

Component label instructions

1100 input equipments

1101 first processors

1102 output equipments

1103 first memories

1104 communication bus

1200 processing components

1201 second processors

1202 second memories

1203 communication components

1204 power supply modules

1205 multimedia components

1206 voice components

1207 input/output interfaces

1208 sensor modules

Specific embodiment

Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation Feature in example can be combined with each other.

It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel It is likely more complexity.

It please refers to Fig.1 to Fig.3, the present invention provides a kind of data collection system, includes equipment access layer, network layer, number According to layer, podium level and application layer；

Equipment access layer is for acquiring corresponding physical characteristic data in some or multiple object space regions.As showing Example, object space region for example may include at least one of: in Xian Xia entity shops, Xian Xia entity shops where a certain commodity Certain commodity regions in region, Xian Xia entity shops.

The data Layer is connect by network layer with equipment access layer, for judging the equipment access layer in the mesh Whether the one or more physical characteristic datas acquired in mark area of space meet preset physical characteristic data screening rule, and The physical characteristic data for meeting the physical characteristic data screening rule is transmitted to podium level.

In one exemplary embodiment, physical characteristic data includes at least face characteristic data.Wherein, face characteristic data Including at least one of: face picture clarity, face picture intensity of illumination, face picture bow angle, face picture lift Brilliance degree, face picture side face angle, face picture face characteristic point mass point.

According to an exemplary embodiment, the face characteristic data screening rule in physical characteristic data screening rule for example may be used To be provided that

Clarity: the standard of self-defining clarity point, setting clarity divide range in A1 between B1, will be when filtering The clarity point of the human face data acquired in area of space is filtered out less than the face picture of the first preset value；

Wherein, the value of A1, B1 can flexibly be set according to the actual situation, such as: A1 0, B1 1；First is default Value can also flexibly be set according to the actual situation, such as: the first preset value is 0.3.

Intensity of illumination: the standard of customized intensity of illumination point, such as: setting intensity of illumination divides range in A2 between B2, Face picture when filtering by the intensity of illumination of the human face data acquired in area of space point less than the second preset value filters out；

Wherein, the value of A2, B2 can flexibly be set according to the actual situation, such as: A2 0, B2 1；Second is default Value can also flexibly be set according to the actual situation, such as: the second preset value is 0.2.

Shooting angle: it is divided into angle of bowing, new line angle, side face angle；

Bow angle: the angle that can will bow when filtering is filtered out greater than the face picture of third preset value；Wherein, third is pre- If value can flexibly be set according to the actual situation, such as: third preset value is 35 °；

New line angle: the face picture that new line angle is greater than the 4th preset value can be filtered out when filtering；Wherein, the 4th is pre- If value can flexibly be set according to the actual situation, such as: the 4th preset value is 35 °；

Side face angle can filter out the face picture that deflection angle is greater than the 5th preset value when filtering；Wherein, In, the 5th preset value can flexibly be set according to the actual situation, such as: the 5th preset value is 40 °

Face characteristic point mass point: the standard of self-defining face characteristic point mass point, face characteristic point mass point is full Set up separately and be set to A3, face picture when filtering by face characteristic point mass point less than the 6th preset value filters out.

Wherein, the value of A3 can flexibly be set according to the actual situation, such as: A3 1；6th preset value can also root It is flexibly set according to actual conditions, such as: the 6th preset value is 0.5.

Further, if the human face data in face picture to be filtered meets at least one of the following conditions: clarity is small It is greater than third preset value less than the second preset value, angle of bowing in the first preset value, intensity of illumination, new line angle is greater than the 4th in advance If value, side face angle are greater than the 5th preset value, face characteristic point mass is divided less than the 6th preset value, then by corresponding face picture It filters out.

Further, podium level is connect with data Layer, the face characteristic data for being transmitted according to data Layer, determining and people The corresponding one or more dimensions of face characteristic analyzes result.Specifically, podium level meets respectively according to reaching of transmitting of data Layer The human face data information of preset value, analysis are located at the consumption that human face data information in area of space reaches the personnel of preset value condition Tendency or consumption habit；By equipment access layer acquire user descend shops region online, a certain particular commodity area in Xian Xia shops The human face data in certain particular commodity regions, analyzes human face data in domain or Xian Xia shops, in a certain period of time, The human face data of one or many acquisition users in above-mentioned zone, the then consumption propensity or consumption that can be used for analyzing user are practised It is used.

In a further exemplary embodiment, physical characteristic data further includes human body load characteristic data.Wherein, human body carries Characteristic includes at least one of: human body wears characteristic, human body picks and places product features data.

In one exemplary embodiment, if acquired in the object space region one or more of the equipment access layer A face characteristic does not meet preset physical characteristic data screening rule, then the podium level is in face characteristic data basis On, characteristic is worn in conjunction with human body or human body picks and places product features data, is determined and the face characteristic data corresponding one Dimension or multidimensional analysis result.

According to the above exemplary embodiments, it includes at least one of that the human body, which picks and places product features data: hand picks and places The action data of commodity, product features data.

Specifically, hand pick and place commodity action data for example including removed in object space region/do not remove shelf quotient The movement of product；The movement that will be removed commodity and put back to shelf after commodity on shelf is removed, commodity will be removed and be put into the dynamic of shopping cart Make etc..

Wherein, the product features data include at least one of: product name, commodity price, commodity packaging.Commodity The text of title is for example whether the text comprising the every country in the world such as Chinese, Russian, English, Japanese, Korean, French, German Word.Commodity price is currently sold price, discounted cost and discount original cost lattice etc. for example including there is it.Commodity packaging is for example including having Commodity packaging color, commodity packaging size, commodity packaging pattern, commodity packaging shape and commodity packaging material etc..

According to the above exemplary embodiments, it includes at least one of that the human body, which wears characteristic: human body clothes is special Levy data, body decorations object characteristic.

Specifically, human body garment features data are for example including having clothes material, clothes brand, suit length, clothes pattern With garment shape etc..

According to the above exemplary embodiments, body decorations object characteristic includes at least one of: the ring that human body is worn Refer to bracelet data, the earrings data of human body wearing that characteristic, human body are worn.

Wherein, the ring characteristic that human body is worn is for example including having ring brand, ring material, ring quantity, ring Position, ring shape and ring finger size etc..The bracelet data that human body is worn are for example including having bracelet brand, bracelet material, bracelet Quantity, bracelet position, bracelet shape and bracelet size etc..The earrings data that human body is worn are for example including having earrings brand, earrings Material, earrings quantity, earrings position, earrings shape and earrings size etc..

In some exemplary embodiments, if acquired in the object space region one of the equipment access layer or Multiple face characteristic data do not meet preset physical characteristic data screening rule, then the podium level is in face characteristic data base On plinth, characteristic is worn in conjunction with above-mentioned human body or human body picks and places product features data, the determining and face characteristic data Corresponding consumption propensity or consumption habit.

Further, podium level is connect with data Layer, the human body load characteristic data for being transmitted according to data Layer, is determined One or more dimensions corresponding with face characteristic data analyzes result.Specifically, the online Xiamen of user is acquired by equipment access layer In shop region, Xian Xia shops in a certain particular commodity region or Xian Xia shops certain particular commodity regions human body load characteristic Data analyze human body load characteristic data.In a certain period of time, one or many acquisitions in above-mentioned zone are incorporated in The human face data of user analyzes the consumption propensity or consumption habit of user.

Application layer is connect with podium level, for the consumption propensity or consumption habit after display platform layer analysis.

In one exemplary embodiment, podium level is also preset with the presetting database for carrying out identification.Present count It for example may include line Xiamen trade name Cheng Huoxianxia shops number, person number, personnel's surname according to data information pre-stored in library Name, cell-phone number, the date of birth, human face photo, arrives shop time and personnel identity etc. at gender for the first time；Personnel identity for example may include Member or VIP personnel, blacklist, employee, keep a public place clean and ensure public security at frequent visitor.

The symbol that podium level is acquired in object space region by the human face data in presetting database with equipment access layer The human face data for closing the personnel of preset value condition compares, and matches personnel identity or creator's body according to comparison result Part；As an example, meeting preset value condition with what is acquired in object space region if in the preset database not finding The corresponding human face data of personnel then creates a new demographic data in application layer, assigns new number.As an example, Creation process for example may include using the collected human face photo for meeting preset value condition as bottom library photo, and bottom library photo is available In the human face data as judgement next time, and input line Xiamen trade name Cheng Huoxianxia shops number and bottom in application layer The corresponding person number of library photo, personnel's name corresponding with bottom library photo, personnel's gender corresponding with bottom library photo, Personnel's cell-phone number corresponding with bottom library photo, personnel's date of birth corresponding with bottom library photo and opposite with bottom library photo Personnel identity information answered etc..

The human face data and identity information of these personnel are preset in presetting database, will be adopted in object space region The human face data for meeting preset value condition of collection is compared with the human face data in presetting database, is carried out according to comparison result Judgement, if the similarity of comparison result meeting of in preset section, judging to acquire in object space region is default Human face data in the human face data and presetting database of value condition is the human face data from same people, then completes specific personnel Matching of personnel identity information is completed at the same time according to the corresponding identity information of personnel matched in presetting database Match.As an example, the pre-set interval range of similarity in C1 between C2, the section of similarity can be according to the reality of Xian Xia shops Border situation is configured, for example, C1, which is set as 78%, C2, is set as 98%.

Application layer shows matched personnel identity or creator's identity also according to the comparison result in podium level, completes Passenger flow statistics.After collecting the human face data for meeting preset value condition in object space region, with the present count in podium level It is compared according to library, passenger flow statistics is carried out according to the comparison result of podium level, even a certain personnel carried out within a period Personnel identity information matches or the identity information for creating the personnel, then to carry out in the period to customer's fluxion "+ 1 ", conversely, then without "+1 ".As an example, certain time period for example may include have 10 minutes, 30 minutes, 1 hour, it is 24 small When, a week or one month etc..

It in one exemplary embodiment, include crowd's accounting engine unit in podium level, for counting equipment access layer The number in face picture acquired in object space region；Attributive analysis engine unit, for analyzing object space region The age of the human face data for meeting physical characteristic data screening rule of interior acquisition and gender；Face recognition engine unit, is used for The detection and identification of face；And database server, it (include human face data, body for storing pre-set personal information Part information etc.) and the newly created personal information of storage and storage personnel to shop these data such as record.

In one exemplary embodiment, application layer is classified by the data that service logic transmits podium level, business Logic includes service management module and business application module；

Service management module includes: user management, and the additions and deletions for personnel such as member and frequent visitors, which change, looks into；Equipment management, Additions and deletions for capturing the hardware devices such as camera, shop heat treasured, which change, looks into and condition monitoring；Equipment access, for equipment authentication and with The communication of equipment；And log management, for recording and checking System Operation Log；

Business application module includes: passenger flow statistics, for count and check per hour, daily, weekly, monthly to shop Number；Attributive analysis, for counting and viewing the sex ratio and age bracket ratio of shop personnel；Frequent visitor's analysis, for counting With check frequent visitor to shop quantity and gender and age bracket accounting；Intensity of passenger flow thermodynamic chart, for real-time with heating power diagram form Crowds Distribute, density and variation tendency are described；Trajectory track, for checking and being recorded track of the shop personnel in shop；And VIP User identification, for identification into shop personnel whether be this shops VIP.

It in one exemplary embodiment, further include having client layer, client layer includes browser/user terminal (B/C), user End/server (C/S) and mobile client；Client layer is connect with application layer, passes through web terminal, the end IOS, Android in client layer Data are showed user by end.

This system working principle is as follows: by installing face snap camera in entrance, the face captured is uploaded to podium level Picture, podium level carry out face alignment, after face filtering, duplicate removal these processes, finally obtain accurate passenger flow statistics；It is flat Platform layer will record user every time to shop, by analysis user arrive every time the concern commodity in shop, stay time, dwell regions and The data such as the human body load characteristic in conjunction with user obtain the consumption propensity of user；By the way that member, employee are added in system in advance Etc. primary datas, and frequent visitor's data are generated according to customized rule, next time, corresponding user just can be carried out user's to shop Identification and classification.

This system has the advantage that including (1) recognition of face uses machine recognition, and artificial origin is avoided to leak number, can whole day 24 hours steady operations, the same set of applicable multiple shops of system are at low cost；(2) recognition of face can be collected and not settled accounts User, avoid with closing entries count passenger flow caused by counting loss；(3) the candid photograph camera of recognition of face is mounted on shops and enters Mouthful, it can precisely acquire and avoid wifi counting false statistic shops periphery into shop user not into the passenger flow in shop；(4) recognition of face meter Number is hardly interfered by other factors, avoids infrared counting easily disturbed the case where leading to error count；(5) recognition of face counts, Cloud platform is connected by capturing camera, shops need to only dispose a candid photograph camera, and deployment is simple, and at low cost, stability is good； (6) common Computer Vision Recognition counts, and indiscriminate owner can be carried out counting statistics, not in full conformity with practical trade company The statistical rules needed, and this platform can be automatically removed capturing to employee, only counted real passenger flow, kept passenger flow more smart It is quasi-.

It is had the advantage that in terms of judging consumption propensity including (1) recognition of face to user and is compared by machine recognition Historical data obtains the analysis of consumption propensity, and it is accurate to stablize, and avoids erroneous judgement caused by the subjective factor being manually likely to occur； (2) recognition of face passes through machine recognition and analyzes user's history data, needs not rely on other third company, set of system can Multiple shops are applicable in, at low cost, the real-time discriminance analysis of system returns the result, and has high real-time；(3) this system is known by face Other network analysis consumption propensity is all managed collectively in a system to storing data again from acquisition data to analysis data, ensure that The integrality of data also largely reduces the waste of resource；(4) this system acquires human face data analysis by Xian Xia shops Consumption propensity, data rich under line, human face data are used as data acquisition and passenger flow statistics simultaneously, reduce use cost.

As shown in figure 4, method and step is as follows the present invention also provides a kind of data processing method:

S1 obtains corresponding physical characteristic data in one or more object spaces region；

S2, if the one or more physical characteristic datas acquired in the object space region meet preset human body spy Levy data screening rule, it is determined that one or more dimensions corresponding with the physical characteristic data analyzes result.

Further, equipment access layer obtains corresponding physical characteristic data in one or more object spaces region；Make For example, object space region for example may include at least one of: a certain commodity in Xian Xia entity shops, Xian Xia entity shops Certain commodity regions in region, Xian Xia entity shops.

Data Layer judges whether the equipment access layer has acquired physical characteristic data in object space region, and judges Whether the physical characteristic data that the equipment access layer acquisition acquires in object space region meets preset characteristics of human body's number Podium level is transmitted to according to screening rule, and by the physical characteristic data for meeting screening rule.

In one exemplary embodiment, physical characteristic data includes face characteristic data, the face characteristic data packet Include at least one of: face picture clarity, face picture intensity of illumination, face picture bow angle, face picture come back Angle, face picture side face angle, face picture face characteristic point mass point.

According to the above exemplary embodiments, equipment access layer obtains corresponding face in one or more object spaces region Characteristic；

Data Layer judges whether the equipment access layer has acquired face data information in object space region, and sentences Clarity, intensity of illumination, shooting angle in the human face data information that the equipment access layer acquires in the area of space of breaking Whether degree and face characteristic point mass meet corresponding screening rule, and the human face data information for meeting screening rule is passed Transport to podium level；

As an example, the screening rule of human face data characteristic can be set it is as follows:

Side face angle can filter out the face picture that deflection angle is greater than the 5th preset value when filtering；Wherein, Five preset values can flexibly be set according to the actual situation, such as: the 5th preset value is 40 °

The human face data information for meeting corresponding screening rule that podium level is transmitted according to data Layer, analysis are located at the sky Between in region human face data information meet corresponding screening rule personnel consumption propensity or consumption habit；It is accessed by equipment Layer acquisition user descend shops region online, certain particular commodities in a certain particular commodity region or Xian Xia shops in Xian Xia shops The human face data in region, analyzes human face data, and in a certain period of time, one or many acquisitions are used in above-mentioned zone The human face data at family then can be used for analyzing the consumption propensity or consumption habit of user.

According to the above exemplary embodiments, the face acquired in certain time period and in the object space region is counted On the basis of characteristic, characteristic or human body are worn in conjunction with human body and picks and places product features data, the number of successful match, with And at least one of following data that statistics acquires in the area of space: face characteristic data, human body wear characteristic Product features data are picked and placed according to, human body.

Consumption propensity or consumption habit after application layer display platform layer analysis.

According to the above exemplary embodiments, podium level is by the human face data in presetting database with equipment access layer in sky Between the human face data of the personnel for meeting corresponding screening rule that acquires in region compare, personnel are matched according to comparison result Identity or creator's identity；As an example, if the symbol for not finding and being acquired in area of space in the preset database The corresponding human face data of the personnel for closing corresponding screening rule then creates a new demographic data in application layer, assigns New number.As an example, creation process for example may include making the collected human face photo for meeting corresponding screening rule For bottom library photo, bottom library photo is used as the human face data of judgement next time, and the shops under input line in application layer Title or Xian Xia shops number, person number corresponding with bottom library photo, personnel's name corresponding with bottom library photo and bottom The corresponding personnel's gender of library photo, personnel's cell-phone number corresponding with bottom library photo, personnel corresponding with bottom library photo go out Phase birthday and personnel identity information corresponding with bottom library photo etc..

According to the above exemplary embodiments, the human face data and identity letter of these personnel are preset in presetting database Breath, by the human face data in the human face data and presetting database for meeting corresponding screening rule acquired in area of space into Row compares, and is judged according to comparison result, if the similarity of comparison result judges in preset section in space region The human face data in the human face data and presetting database for meeting corresponding screening rule acquired in domain is from same people's Human face data then completes the matching of specific personnel, according to the corresponding identity information of personnel matched in presetting database, together When complete personnel identity information matching.As an example, the pre-set interval range of similarity in C1 between C2, the area of similarity Between can be configured according to the actual conditions of Xian Xia shops, for example, C1, which is set as 78%, C2, is set as 98%.

According to the above exemplary embodiments, application layer shows matched personnel identity also according to the comparison result in podium level Or creator's identity, complete passenger flow statistics.The human face data for meeting corresponding screening rule is collected in area of space Afterwards, it is compared with the presetting database in podium level, passenger flow statistics, even a certain people is carried out according to the comparison result of podium level Member carried out the matching of personnel's identity information within a period or created the identity information of the personnel, then in the period To customer's fluxion carry out "+1 ", conversely, then without "+1 ".As an example, certain time period for example may include have 10 minutes, 30 minutes, 1 hour, 24 hours, a week or one month etc..

It include crowd's accounting engine unit in a specific implementation process, in podium level, for counting equipment access layer The number in human face photo acquired in area of space；Attributive analysis engine unit, for analyzing target object space region The age of the human face data for meeting physical characteristic data screening rule of interior acquisition and gender；Face recognition engine unit, is used for The detection and identification of face；And database server, it (include human face data, body for storing pre-set personal information Part information etc.) and the newly created personal information of storage and storage personnel to shop these data such as record.

This method working principle is as follows: by installing face snap camera in entrance, the face captured is uploaded to podium level Photo, podium level carry out face alignment, after face filtering, duplicate removal these processes, finally obtain accurate passenger flow statistics；It is flat Platform layer will record user every time to shop, by analysis user arrive every time the concern commodity in shop, stay time, dwell regions and The data such as the human body load characteristic in conjunction with user obtain the consumption propensity of user；By the way that member, employee are added in system in advance Etc. primary datas, and frequent visitor's data are generated according to customized rule, next time, corresponding user just can be carried out user's to shop Identification and classification.

This method has the advantage that including (1) recognition of face uses machine recognition, and artificial origin is avoided to leak number, can whole day 24 hours steady operations, the same set of applicable multiple shops of system are at low cost；(2) recognition of face can be collected and not settled accounts User, avoid with closing entries count passenger flow caused by counting loss；(3) the candid photograph camera of recognition of face is mounted on shops and enters Mouthful, it can precisely acquire and avoid wifi counting false statistic shops periphery into shop user not into the passenger flow in shop；(4) recognition of face meter Number is hardly interfered by other factors, avoids infrared counting easily disturbed the case where leading to error count；(5) recognition of face counts, Cloud platform is connected by capturing camera, shops need to only dispose a candid photograph camera, and deployment is simple, and at low cost, stability is good； (6) common Computer Vision Recognition counts, and indiscriminate owner can be carried out counting statistics, not in full conformity with practical trade company The statistical rules needed, and this platform can be automatically removed capturing to employee, only counted real passenger flow, kept passenger flow more smart It is quasi-.

It is had the advantage that in terms of judging consumption propensity including (1) recognition of face to user and is compared by machine recognition Historical data obtains the analysis of consumption propensity, and it is accurate to stablize, and avoids erroneous judgement caused by the subjective factor being manually likely to occur； (2) recognition of face passes through machine recognition and analyzes user's history data, needs not rely on other third company, set of system can Multiple shops are applicable in, at low cost, the real-time discriminance analysis of system returns the result, and has high real-time；(3) this method is known by face Other network analysis consumption propensity is all managed collectively in a system to storing data again from acquisition data to analysis data, ensure that The integrality of data also largely reduces the waste of resource；(4) this method acquires human face data analysis by Xian Xia shops Consumption propensity, data rich under line, human face data are used as data acquisition and passenger flow statistics simultaneously, reduce use cost.

The present invention also provides a kind of data processing cloud platforms, include above-mentioned data processing system.Cloud platform includes upper The features and benefits of system are stated, details are not described herein again.

In conclusion the present invention provides a kind of data processing system, method and cloud platform, including equipment access layer, network Layer, data Layer, podium level and application layer；The equipment access layer is used to acquire the face number of all personnel in a certain area of space It is believed that breath；The data Layer is connect by network layer with equipment access layer, for judging the equipment access layer in the space Whether face data information has been acquired in region, and for judging what the equipment access layer acquired in the area of space Whether clarity, intensity of illumination and shooting angle in human face data information meet corresponding screening rule, and by judging result It is transmitted to podium level；The podium level is connect with the data Layer, and podium level is according to the judging result of data Layer, and analysis is positioned at institute State the consumption propensity or consumption habit of all personnel in area of space；The application layer is connect with the podium level, for showing Consumption propensity or consumption habit after platform layer analysis；It can complete line Xiamen customer's stream statistics, the analysis of the consumption propensity of user With the identification of user, thus solve the problems, such as to obtain user data under line it is difficult；And deployment is simple, at low cost, stability It is good.So the present invention effectively overcomes various shortcoming in the prior art and has high industrial utilization value.

The embodiment of the present application also provides a kind of data processing equipments, obtain corresponding in one or more object spaces region Physical characteristic data；

In the present embodiment, which executes above system or method, concrete function and technical effect reference Above-described embodiment, details are not described herein again.

The embodiment of the present application also provides a kind of equipment, which may include: one or more processors；It deposits thereon The one or more machine readable medias for containing instruction, when being executed by one or more of processors, so that the equipment Execute method described in Fig. 1.In practical applications, which can be used as terminal device, can also be used as server, and terminal is set Standby example may include: smart phone, tablet computer, E-book reader, MP3 (dynamic image expert's compression standard voice Level 3, Moving Picture Experts Group Audio Layer III) player, MP4 (dynamic image expert pressure Contracting received pronunciation level 4, Moving Picture Experts Group Audio Layer IV) it is player, on knee portable Computer, vehicle-mounted computer, desktop computer, set-top box, intelligent TV set, wearable device etc., the embodiment of the present application for Specific equipment is without restriction.

The embodiment of the present application also provides a kind of non-volatile readable storage medium, be stored in the storage medium one or Multiple modules (programs) when the one or more module is used in equipment, can make the equipment execute the application reality Apply the instruction (instructions) of the included step of data processing method in Fig. 4 of example.

Fig. 5 is the hardware structural diagram for the terminal device that one embodiment of the application provides.As shown, the terminal device It may include: input equipment 1100, first processor 1101, output equipment 1102, first memory 1103 and at least one is logical Believe bus 1104.Communication bus 1104 is for realizing the communication connection between element.First memory 1103 may include high speed RAM memory, it is also possible to it further include non-volatile memories NVM, a for example, at least magnetic disk storage, in first memory 1103 It can store various programs, for completing various processing functions and realizing the method and step of the present embodiment.

Optionally, above-mentioned first processor 1101 for example can be central processing unit (Central Processing Unit, abbreviation CPU), application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or Other electronic components realize that the first processor 1101 is coupled to above-mentioned input equipment 1100 and defeated by wired or wireless connection Equipment 1102 out.

Optionally, above-mentioned input equipment 1100 may include a variety of input equipments, such as may include user oriented use At least one of family interface, device oriented equipment interface, the programmable interface of software, camera, sensor.Optionally, should Device oriented equipment interface can be wireline interface for carrying out data transmission between equipment and equipment, can also be and is used for Hardware insertion interface (such as USB interface, serial ports etc.) carried out data transmission between equipment and equipment；Optionally, should towards with The user interface at family for example can be user oriented control button, voice-input device and use for receiving voice input The touch awareness apparatus (such as touch screen, Trackpad with touch sensing function etc.) of family reception user's touch input；It is optional , the programmable interface of above-mentioned software for example can be the entrance for editing or modifying program for user, such as the input of chip Pin interface or input interface etc.；Output equipment 1102 may include the output equipments such as display, sound equipment.

In the present embodiment, the processor of the terminal device includes for executing each module of speech recognition equipment in each equipment Function, concrete function and technical effect are referring to above-described embodiment, and details are not described herein again.

Fig. 6 is the hardware structural diagram for the terminal device that one embodiment of the application provides.Fig. 6 is to Fig. 5 in reality A specific embodiment during now.As shown, the terminal device of the present embodiment may include second processor 1201 And second memory 1202.

Second processor 1201 executes the computer program code that second memory 1202 is stored, and realizes above-described embodiment Middle Fig. 4 the method.

Second memory 1202 is configured as storing various types of data to support the operation in terminal device.These numbers According to example include any application or method for operating on the terminal device instruction, such as message, picture, video Deng.Second memory 1202 may include random access memory (random access memory, abbreviation RAM), it is also possible to It further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.

Optionally, second processor 1201 is arranged in processing component 1200.The terminal device can also include: communication set Part 1203, power supply module 1204, multimedia component 1205, voice component 1206, input/output interface 1207 and/or sensor Component 1208.Component that terminal device is specifically included etc. is set according to actual demand, and the present embodiment is not construed as limiting this.

The integrated operation of the usual controlling terminal equipment of processing component 1200.Processing component 1200 may include one or more Second processor 1201 executes instruction, to complete all or part of the steps in above-mentioned data processing method.In addition, processing group Part 1200 may include one or more modules, convenient for the interaction between processing component 1200 and other assemblies.For example, processing group Part 1200 may include multi-media module, to facilitate the interaction between multimedia component 1205 and processing component 1200.

Power supply module 1204 provides electric power for the various assemblies of terminal device.Power supply module 1204 may include power management System, one or more power supplys and other with for terminal device generate, manage, and distribute the associated component of electric power.

Multimedia component 1205 includes the display screen of one output interface of offer between terminal device and user.One In a little embodiments, display screen may include liquid crystal display (LCD) and touch panel (TP).If display screen includes touch surface Plate, display screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touchings Sensor is touched to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or cunning The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.

Voice component 1206 is configured as output and/or input speech signal.For example, voice component 1206 includes a wheat Gram wind (MIC), when terminal device is in operation mode, when such as speech recognition mode, microphone is configured as receiving external voice Signal.The received voice signal of institute can be further stored in second memory 1202 or send via communication component 1203. In some embodiments, voice component 1206 further includes a loudspeaker, for exporting voice signal.

Input/output interface 1207 provides interface between processing component 1200 and peripheral interface module, and above-mentioned periphery connects Mouth mold block can be click wheel, button etc..These buttons may include, but are not limited to: volume button, start button and locking press button.

Sensor module 1208 includes one or more sensors, and the state for providing various aspects for terminal device is commented Estimate.For example, sensor module 1208 can detecte the state that opens/closes of terminal device, the relative positioning of component, Yong Huyu The existence or non-existence of terminal device contact.Sensor module 1208 may include proximity sensor, be configured to do not having Detected the presence of nearby objects when any physical contact, including detection user between terminal device at a distance from.In some implementations In example, which can also be including camera etc..

Communication component 1203 is configured to facilitate the communication of wired or wireless way between terminal device and other equipment.Eventually End equipment can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In one embodiment In, it may include SIM card slot in the terminal device, which step on terminal device for being inserted into SIM card GPRS network is recorded, is communicated by internet with server foundation.

From the foregoing, it will be observed that communication component 1203, voice component 1206 involved in Fig. 6 embodiment and input/output Interface 1207, sensor module 1208 can be used as the implementation of the input equipment in Fig. 5 embodiment.

The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as At all equivalent modifications or change, should be covered by the claims of the present invention.

Claims

1. a kind of data processing system, which is characterized in that include: equipment access layer, network layer, data Layer, podium level；

The data Layer is connect by network layer with equipment access layer, for judging the equipment access layer in the target empty Between one or more physical characteristic datas for acquiring in region whether meet preset physical characteristic data screening rule, and will symbol The physical characteristic data for closing the physical characteristic data screening rule is transmitted to podium level；

The podium level, the physical characteristic data for being transmitted according to the data Layer, the determining and physical characteristic data pair The one or more dimensions analysis result answered.

2. data processing system according to claim 1, which is characterized in that the physical characteristic data includes face characteristic Data, human body load characteristic data.

3. data processing system according to claim 2, which is characterized in that if the physical characteristic data is face characteristic Data, then the face characteristic data include at least one of: face picture clarity, face picture intensity of illumination, face Picture is bowed angle, face picture new line angle, face picture side face angle, face picture face characteristic point mass point.

4. data processing system according to claim 3, which is characterized in that if the face characteristic data meet following item At least one part: face picture clarity is greater than corresponding preset value, face picture intensity of illumination is greater than corresponding preset value, face figure Piece is bowed, and angle is less than corresponding preset value, face picture new line angle is less than corresponding preset value, face picture side face angle is less than Corresponding preset value, face picture face characteristic point mass point are greater than corresponding preset value, then meet preset physical characteristic data sieve Choosing rule.

5. data processing system according to claim 1, which is characterized in that analysis result includes at least one of: being disappeared Take trend analysis result, consumption habit analysis result.

6. data processing system according to claim 5, which is characterized in that further include application layer；Wherein, the application Layer, for showing the consumption propensity analysis result or consumption habit analysis result.

7. data processing system according to claim 2, which is characterized in that if the physical characteristic data is human body carrying Characteristic, then the human body load characteristic data include at least one of: human body wears characteristic, human body picks and places commodity Characteristic.

8. data processing system according to claim 7, which is characterized in that if the equipment access layer is in the target empty Between one or more face characteristic data for acquiring in region do not meet preset physical characteristic data screening rule, then it is described flat Platform layer wears characteristic in conjunction with human body or human body picks and places product features data, determining and institute in face characteristic data basis State the corresponding one or more dimensions analysis result of face characteristic data.

9. data processing system according to claim 7, which is characterized in that the human body picks and places product features data and includes At least one of: hand picks and places the action data of commodity, product features data；Wherein, the product features data include following At least one: product name, commodity price, commodity packaging.

10. data processing system according to claim 7, which is characterized in that the human body wear characteristic include with It is at least one lower: human body garment features data, body decorations object characteristic.

11. data processing system according to claim 10, which is characterized in that the body decorations object characteristic includes At least one of: bracelet data, the earrings data of human body wearing of ring characteristic, human body wearing that human body is worn.

12. data processing system according to claim 6, which is characterized in that the podium level is also preset with for carrying out The presetting database of identification；

The podium level is acquired in the area of space by the human face data in presetting database with the equipment access layer The human face data of the personnel for meeting physical characteristic data screening rule compare, presetting database is judged according to comparison result In with the presence or absence of meeting the human face data of physical characteristic data screening rule；If it exists, then it matches and the human face data phase Corresponding identity information；If it does not exist, then creation is this time collected in the area of space in application layer meets human body The human face data and identity information of characteristic screening rule.

13. data processing system according to claim 12, which is characterized in that the application layer also counts certain time period The interior podium level and the human face data for meeting physical characteristic data screening rule acquired in the object space region With successful number, and statistics acquiring in the area of space of creating in application layer meets characteristics of human body's number According to the human face data of screening rule.

14. human face data acquisition analysis system according to claim 1, which is characterized in that include in the podium level For detect and identify human face data that equipment access layer acquires in the object space region face recognition engine unit, For counting crowd's accounting engine of human face data in the face picture that equipment access layer acquires in the object space region Unit, the attribute for analyzing the human face data for meeting physical characteristic data screening rule acquired in the object space region Analysis engine unit；For storing pre-set database, the newly created human face data of storage application layer and identity information Database server.

15. a kind of data processing method, which is characterized in that the method comprises the following steps:

If the one or more physical characteristic datas acquired in the object space region meet preset physical characteristic data Screening rule, it is determined that one or more dimensions corresponding with the physical characteristic data analyzes result.

16. data processing method according to claim 15, which is characterized in that the physical characteristic data includes face spy Levy data, human body load characteristic data.

17. data processing method according to claim 16, which is characterized in that if the physical characteristic data is that face is special Data are levied, then the face characteristic data include at least one of: face picture clarity, face picture intensity of illumination, people Face picture is bowed angle, face picture new line angle, face picture side face angle, face picture face characteristic point mass point.

18. data processing method according to claim 17, which is characterized in that if face characteristic data satisfaction is following At least one condition: face picture clarity is greater than corresponding preset value, face picture intensity of illumination is greater than corresponding preset value, face It is small that picture bows that angle is less than corresponding preset value, face picture new line angle is less than corresponding preset value, face picture side face angle It is greater than corresponding preset value in corresponding preset value, face picture face characteristic point mass point, then meets preset physical characteristic data Screening rule.

19. data processing method according to claim 15, which is characterized in that analysis result includes at least one of: Consumption propensity analyzes result, consumption habit analyzes result.

20. data processing method according to claim 16, which is characterized in that if the physical characteristic data is held for human body Carry characteristic, then the human body load characteristic data include at least one of: human body wears characteristic, human body picks and places quotient Product characteristic.

21. data processing method according to claim 20, which is characterized in that if being acquired in the object space region One or more face characteristic data do not meet preset physical characteristic data screening rule, then in face characteristic data basis On, characteristic is worn in conjunction with human body or human body picks and places product features data, is determined and the face characteristic data corresponding one Dimension or multidimensional analysis result.

22. data processing method according to claim 20, which is characterized in that the human body picks and places product features data packet Include at least one of: hand picks and places the action data of commodity, product features data；Wherein, the product features data include with It is at least one lower: product name, commodity price, commodity packaging.

23. data processing method according to claim 20, which is characterized in that the human body wear characteristic include with It is at least one lower: human body garment features data, body decorations object characteristic.

24. data processing method according to claim 23, which is characterized in that the body decorations object characteristic includes At least one of: bracelet data, the earrings data of human body wearing of ring characteristic, human body wearing that human body is worn.

25. data processing method according to claim 23, which is characterized in that show consumption propensity analysis result or The consumption habit analyzes result.

26. data processing method according to claim 25, which is characterized in that in statistics certain time period and in the mesh It marks in the face characteristic data basis acquired in area of space, wears characteristic in conjunction with human body or human body picks and places product features Data, the number of successful match, and at least one of following data that statistics acquires in the area of space: face is special Sign data, human body wear characteristic, human body picks and places product features data.

27. a kind of data processing cloud platform, which is characterized in that include in claim 1 to 14 described in any claim Data processing system.

28. a kind of data processing equipment, which is characterized in that

Whether the one or more physical characteristic datas for judging that the equipment access layer acquires in the object space region accord with Close preset physical characteristic data screening rule, if meeting, according to the data Layer transmit physical characteristic data, determine with The corresponding one or more dimensions of the physical characteristic data analyzes result.

29. a kind of equipment characterized by comprising

One or more processors；With

One or more machine readable medias of instruction are stored thereon with, when one or more of processors execute, so that The equipment executes the method as described in one or more in claim 15-26.

30. one or more machine readable medias, which is characterized in that instruction is stored thereon with, when by one or more processors When execution, so that equipment executes the method as described in one or more in claim 15-26.