Movatterモバイル変換


[0]ホーム

URL:


CN115146155B - Dynamic user portrayal management system - Google Patents

Dynamic user portrayal management system
Download PDF

Info

Publication number
CN115146155B
CN115146155BCN202210746105.6ACN202210746105ACN115146155BCN 115146155 BCN115146155 BCN 115146155BCN 202210746105 ACN202210746105 ACN 202210746105ACN 115146155 BCN115146155 BCN 115146155B
Authority
CN
China
Prior art keywords
user portrait
user
portrait
preset
central control
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210746105.6A
Other languages
Chinese (zh)
Other versions
CN115146155A (en
Inventor
钟坚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Shenghuo Media Technology Co ltd
Original Assignee
Guangdong Shenghuo Media Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Shenghuo Media Technology Co ltdfiledCriticalGuangdong Shenghuo Media Technology Co ltd
Priority to CN202210746105.6ApriorityCriticalpatent/CN115146155B/en
Publication of CN115146155ApublicationCriticalpatent/CN115146155A/en
Application grantedgrantedCritical
Publication of CN115146155BpublicationCriticalpatent/CN115146155B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

The invention relates to the technical field of data analysis and processing, in particular to a dynamic user portrait management system, which comprises: the portrait acquisition module is used for acquiring dynamic user portrait data; the portrait processing module is used for sending the user portrait with the integrity meeting the requirement to the portrait output module; the storage module is used for receiving user portraits with the integrity not meeting the requirements, user portraits corresponding to the second class of users and user portraits stored in the corresponding label areas; the central control module is connected with the modules and the portrait output module and used for adjusting the operation parameters of the system and the processing parameters of the portrait according to the actual dynamic user portrait data detected by the modules; and the portrait output module is connected with the central control module and is used for outputting the user portrait of the corresponding area to the portrait application interface according to the judging result of the central control module. The invention realizes the accurate identification and storage of the dynamic user portrait and improves the processing efficiency of the user portrait data.

Description

Dynamic user portrayal management system
Technical Field
The invention relates to the technical field of data analysis and processing, in particular to a dynamic user portrait management system.
Background
User portraits are an important application of big data technology, and the goal is to establish descriptive tag attributes for users in a plurality of dimensions, so that real personal characteristics of various aspects of the users are outlined by utilizing the tag attributes, further, user requirements can be explored by utilizing the user portraits, user preferences can be analyzed, and the user experience which is more efficient and targeted for information transmission and is more close to personal habits can be provided for the users by matching the user portraits. The data source for creating the user representation is all data related to the user, and all data related to the user are classified according to a closed classification system, wherein the closed classification system means that classification categories in the system are limited and closed. The user data is classified into classification categories in a closed classification system, the statistical rule of the data distributed in the classification categories can be obtained through continuous accumulation and classification of the data, and the statistical rule is correspondingly used as descriptive label attributes, so that the management of dynamic user portraits has a plurality of defects, for example, the accurate management of dynamic portraits with different properties is still insufficient at present.
Chinese patent publication No.: CN105574159a. A user portrait creation method and a user portrait management system based on big data are disclosed, which create a temporary user portrait by using user behavior and/or content within a valid period of time, and make the temporary user portrait inherit descriptive tag attributes matched with the user behavior and/or content within the valid period of time from the user portrait, and when the user behavior and/or content within the valid period of time does not match with the descriptive tag attributes of the user portrait, then newly create descriptive tag attributes in the temporary user portrait. Therefore, the user portrait establishing method and the user portrait management system based on big data have the following problems: the accurate identification processing of the dynamic user portraits and the lack of processing efficiency for the user portraits data.
Disclosure of Invention
Therefore, the invention provides a dynamic user portrait management system, which is used for solving the problems of accurate identification processing of dynamic user portraits and insufficient processing efficiency of user portrait data in the prior art.
In order to achieve the above object, the present invention provides a dynamic user portrait management system comprising: the portrait acquisition module is used for acquiring dynamic user portrait data; the portrait processing module is connected with the portrait acquisition module and is used for carrying out preliminary judgment on the integrity of the dynamic user portrait data acquired by the portrait acquisition module and sending the user portrait with the integrity meeting the requirement to the portrait output module; the storage module is connected with the portrait processing module and is used for receiving user portraits with the integrity not meeting the requirements, user portraits corresponding to the second class of users and user portraits stored in the corresponding tag areas; the central control module is connected with the modules and the portrait output module and is used for adjusting the operation parameters of the system and the processing parameters of the portrait according to the actual dynamic user portrait data detected by the modules, when the initial determination of the integrity of the dynamic user portrait data is completed, the central control module adjusts the value of the user portrait according to the difference value between the dynamic characteristic proportion of the user portrait obtained by analyzing the dynamic user portrait data acquired by the portrait acquisition module and the dynamic characteristic proportion of the preset user portrait, when the adjustment of the value of the user portrait is completed, the central control module determines whether the user portrait is stored in the label area according to the characteristic correlation degree of the actual user portrait and the label area, and when the determination of the user portrait is stored in the corresponding label area, the central control module determines the category of the user corresponding to the user portrait according to the characteristic uniformity of the actual user portrait;
And the portrait output module is connected with the central control module and is used for outputting the user portrait of the corresponding area to the portrait application interface according to the judging result of the central control module.
Further, the central control module is provided with a preset first image integrity D1 and a preset second image integrity D2, wherein D1 is smaller than D2, when the image acquisition module finishes the acquisition of the dynamic user image, the central control module performs preliminary judgment on whether the acquisition is qualified or not according to the comparison result of the actual image integrity and the preset integrity,
if D is less than or equal to D1, the central control module judges that the integrity of the actual user image is lower than the allowable range and does not store the user image;
if D1 is more than D and less than or equal to D2, the central control module judges that the actual user portrait integrity is in an allowable range, calculates a difference DeltaD between the actual portrait integrity and the preset portrait integrity, adjusts the user portrait characteristic acquisition frequency to a corresponding value according to DeltaD, and sets DeltaD=D-D1;
if D is more than D2, the central control module judges that the integrity of the actual user portrait is in the allowable range and sends the user portrait to the portrait processing module to judge the value of the user portrait.
Further, the central control module is provided with a preset first image integrity difference DeltaD 1, a preset second image integrity difference DeltaD 2, a preset first user image feature acquisition frequency adjustment coefficient alpha 1, a preset second user image feature acquisition frequency adjustment coefficient alpha 2 and a preset user image feature acquisition frequency R0, wherein DeltaD 1 < DeltaD2, delta1 < alpha 2, when D1 < D2, the central control module adjusts the user image feature acquisition frequency according to the difference DeltaD of the actual image integrity and the preset image integrity,
If delta D is less than or equal to delta D1, the central control module judges that the difference value between the actual portrait integrity and the preset portrait integrity is lower than the allowable range, and uses alpha 2 to adjust the user portrait characteristic acquisition frequency, the adjusted user portrait characteristic acquisition frequency is recorded as R1, and R1=alpha 2×R0 is set;
if DeltaD 1 < DeltaDis less than or equal to DeltaD 2, the central control module judges that the difference value between the actual image integrity and the preset image integrity is lower than the allowable range, and uses alpha 1 to adjust the user image characteristic acquisition frequency, the adjusted user image characteristic acquisition frequency is recorded as R2, and R2=alpha 1×R0 is set;
and if delta D > -delta D2, the central control module judges that the difference value between the actual portrait integrity and the preset portrait integrity is within an allowable range and does not regulate the user portrait characteristic acquisition frequency.
Further, the central control module is provided with a preset first user portrait dynamic feature ratio S1 and a preset second user portrait dynamic feature ratio S2, wherein S1 is less than S2, when the central control module completes the adjustment of the user portrait feature acquisition frequency and D is more than D2, the central control module carries out preliminary judgment on whether to adjust the value degree of the user portrait according to the actually detected user portrait dynamic feature ratio,
If S is less than or equal to S1, the central control module judges that the dynamic characteristic ratio of the actual user portrait is in the allowable range and sends the user portrait to the portrait output module;
if S1 is more than S and less than or equal to S2, the central control module judges that the actual user portrait dynamic feature ratio is in the allowable range, detects the duration of the user portrait dynamic feature and adjusts the user portrait dynamic feature ratio to a corresponding value according to the duration;
if S is more than S2, the central control module judges that the actual user portrait dynamic feature ratio exceeds the allowable range, calculates a difference DeltaS between the actual user portrait dynamic feature ratio and the preset user portrait dynamic feature ratio, adjusts the user portrait value to a corresponding value according to DeltaS, and sets DeltaS=S-S2.
Further, the central control module is provided with a preset first user portrait dynamic feature duty ratio difference DeltaS 1, a preset second user portrait dynamic feature duty ratio difference DeltaS 2, a preset first user portrait value adjustment coefficient beta 1, a preset second user portrait value adjustment coefficient beta 2 and a preset user portrait value E0, wherein DeltaS 1 < DeltaS2, delta1 < beta 2 < 1, when S > S2, the central control module adjusts the user portrait value according to the difference DeltaS between the actual user portrait dynamic feature duty ratio and the preset user portrait dynamic feature duty ratio,
If DeltaS is less than or equal to DeltaS 1, the central control module judges that the difference value between the actual user portrait dynamic characteristic duty ratio and the preset user portrait dynamic characteristic duty ratio is within an allowable range and does not adjust the user portrait value;
if DeltaS 1 < DeltaSis less than or equal to DeltaS 2, the central control module judges that the difference between the actual user portrait dynamic characteristic proportion and the preset user portrait dynamic characteristic proportion exceeds the allowable range, and uses beta 2 to adjust the user portrait value, the adjusted user portrait value is marked as E1, and E1 = beta 2 multiplied by E0 is set;
and if DeltaS > DeltaS2, the central control module judges that the difference between the actual user portrait dynamic characteristic duty ratio and the preset user portrait dynamic characteristic duty ratio exceeds the allowable range, adjusts the user portrait value by using beta 1, marks the adjusted user portrait value as E2 and sets E2=beta 1×E0.
Further, the central control module is provided with a preset first user portrait dynamic feature duration T1 and a preset second user portrait dynamic feature duration T2, wherein T1 is less than T2, when S1 is less than S and less than S2, the central control module carries out preliminary judgment on whether to adjust the user portrait dynamic feature duty ratio according to the actual user portrait dynamic feature duration,
If T is less than or equal to T1, the central control module judges that the duration of the dynamic characteristics of the actual user portrait is in an allowable range;
if T1 is more than T and less than or equal to T2, the central control module judges that the duration of the dynamic characteristics of the actual user portrait is in the allowable range, and detects the characteristic correlation degree between the user portrait and the tag area;
if T is more than T2, the central control module judges that the actual user portrait dynamic feature duration exceeds the allowable range, calculates the difference DeltaT between the actual user portrait dynamic feature time and the preset user portrait dynamic feature duration, adjusts the user portrait dynamic feature duty ratio to a corresponding value according to DeltaT, and sets DeltaT=T-T2.
Further, the central control module is provided with a preset first user portrait dynamic feature duration difference DeltaT 1, a preset second user portrait dynamic feature duration difference DeltaT 2, a preset first user portrait dynamic feature duty cycle adjustment coefficient gamma 1, a preset second user portrait dynamic feature duty cycle adjustment coefficient gamma 2 and a preset user portrait dynamic feature duty cycle S0, wherein DeltaT 1 < [ DeltaT 2 ], 0 < gamma 1 < gamma 2 < 1, when T > T2, the central control module adjusts the user portrait dynamic feature duty cycle according to the difference between the actual user portrait dynamic feature time and the preset user portrait dynamic feature duration,
If delta T is less than or equal to delta T1, the central control module judges that the difference value between the actual user portrait dynamic feature duration and the preset user portrait dynamic feature duration is within an allowable range and does not adjust the user portrait dynamic feature duty ratio;
if DeltaT 1 < DeltaT2 is less than or equal to DeltaT 2, the central control module judges that the difference value between the actual user portrait dynamic feature duration and the preset user portrait dynamic feature duration exceeds the allowable range, and adjusts the user portrait dynamic feature ratio by using gamma 2, wherein the adjusted user portrait dynamic feature ratio is recorded as S1, and S1=γ2×S0 is set;
if DeltaT > DeltaT2, the central control module judges that the difference value between the actual user portrait dynamic feature duration and the preset user portrait dynamic feature duration exceeds the allowable range, and adjusts the user portrait dynamic feature ratio by using gamma 1, wherein the adjusted user portrait dynamic feature ratio is recorded as S2, and S2=γ1×S0 is set.
Further, the central control module is provided with a preset first tag area characteristic correlation degree B1 and a preset second tag area characteristic correlation degree B2, wherein B1 is smaller than B2, when the central control module finishes the adjustment of the dynamic characteristic ratio of the user portrait or T1 is smaller than T and smaller than T2, the central control module performs preliminary judgment on whether to store the user portrait in the tag area according to the characteristic correlation degree B of the actual user portrait and the tag area,
If B is less than or equal to B1, the central control module judges that the feature correlation degree between the actual user portrait and the tag area is lower than the allowable range and does not store the user portrait in the tag area;
if B1 is more than B and less than or equal to B2, the central control module judges that the feature correlation degree of the actual user portrait and the tag area is in an allowable range, calculates the difference delta B between the actual feature correlation degree and the feature correlation degree of the preset tag area, and further judges whether to store the user portrait in the tag area according to delta B;
if B is more than B2, the central control module judges that the feature correlation degree between the actual user portrait and the tag area is in an allowable range and directly stores the user portrait in the tag area.
Further, the central control module is provided with a preset first label area characteristic correlation difference DeltaB 1, a preset second label area characteristic correlation difference DeltaB 2, a preset first user portrait storage probability adjustment coefficient K1, a preset second user portrait storage probability adjustment coefficient K2 and a preset user portrait storage probability M0, wherein DeltaB 1 < DeltaB2, deltaK 1 < K2, when B1 < B2 is less than or equal to B1, the central control module further judges whether to store the user portrait in the label area according to the difference value of the characteristic correlation of the actual user portrait and the label area and the preset label area characteristic correlation,
If delta B is less than or equal to delta B1, the central control module judges that the difference value between the characteristic correlation degree of the actual user portrait and the tag area and the characteristic correlation degree of the preset tag area is lower than the allowable range and does not adjust the storage probability of the preset user portrait;
if DeltaB 1 < DeltaB2 is less than or equal to DeltaB 2, the central control module judges that the difference value between the characteristic correlation degree of the actual user portrait and the tag area and the characteristic correlation degree of the preset tag area is in an allowable range, and uses K1 to adjust the storage probability of the user portrait, the storage probability of the adjusted user portrait is marked as M1, and M1=K1×M0 is set;
and if delta B > -delta B2, the central control module judges that the difference value between the characteristic correlation degree of the actual user portrait and the tag area and the characteristic correlation degree of the preset tag area is in an allowable range, and uses K2 to adjust the storage probability of the user portrait, the storage probability of the adjusted user portrait is marked as M2, and M2=K2×M0 is set.
Further, the central control module is provided with a preset first user portrait characteristic uniformity C1 and a preset second user portrait uniformity C2, wherein C1 is smaller than C2, when the central control module completes the adjustment of the storage probability of the user portrait and B is smaller than or equal to B1, the central control module judges the category of the user according to the actual user portrait characteristic uniformity,
If C is less than or equal to C1, the central control module judges that the characteristic uniformity of the actual user portrait is less than the allowable range, and judges the user as three types of users, and the user portrait is not stored;
if C1 is more than C and less than or equal to C2, the central control module judges that the image characteristic uniformity of the actual user is in the allowable range, judges the user as a second class of users, and stores the user image into the storage module for standby;
if C is larger than C2, the central control module judges that the characteristic uniformity of the actual user portrait is in the allowable range, judges the user as a user, and connects the user portrait to the portrait output module.
Compared with the prior art, the system has the beneficial effects that the system can adjust the user portrait feature acquisition frequency according to the difference between the actual portrait integrity and the preset portrait integrity, adjust the user portrait value according to the difference between the actual portrait dynamic feature ratio and the preset user portrait dynamic feature ratio, preliminarily judge whether the user portrait is stored in the tag area according to the feature correlation between the actual user portrait and the tag area, further judge whether the user portrait is stored in the tag area according to the difference between the feature correlation between the actual user portrait and the tag area and the feature correlation of the preset tag area, and improve the precision management capability and the portrait processing efficiency of the dynamic user, and realize the precision identification processing of the dynamic user and the improvement of the user data processing efficiency.
Furthermore, the system provided by the invention can be used for preliminarily judging whether the acquisition is qualified according to the comparison result of the actual portrait integrity and the preset integrity by setting the preset first portrait integrity and the preset second portrait integrity, so that the accurate recognition capability of the user portrait integrity is improved, and the accurate recognition processing of the dynamic user portrait and the improvement of the user portrait data processing efficiency are further realized.
Furthermore, the system of the invention can adjust the user portrait characteristic acquisition frequency according to the difference between the actual portrait integrity and the preset portrait integrity by setting the preset first portrait integrity difference, the preset second portrait integrity difference, the preset first user portrait characteristic acquisition frequency adjustment coefficient, the preset second user portrait characteristic acquisition frequency adjustment coefficient and the preset user portrait characteristic acquisition frequency, thereby improving the accurate adjustment capability of the user portrait characteristic acquisition frequency, realizing the accurate management of the user portrait acquired by the portrait acquisition module, and further realizing the accurate identification processing of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
Furthermore, the system can preliminarily judge whether to adjust the value degree and the recommendation probability of the user portrait according to the actually detected user portrait dynamic feature ratio by setting the preset first user portrait dynamic feature ratio and the preset second user portrait dynamic feature ratio, thereby improving the accurate management capability of the user portrait dynamic feature ratio, improving the control capability of the user portrait dynamic feature, and further realizing the accurate identification processing of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
Furthermore, the system of the invention can adjust the user portrait value according to the difference between the actual user portrait dynamic characteristic ratio and the preset user portrait dynamic characteristic ratio by setting the preset first user portrait dynamic characteristic ratio difference, the preset second user portrait dynamic characteristic ratio difference, the preset first user portrait value adjustment coefficient, the preset second user portrait value adjustment coefficient and the preset user portrait value, thereby improving the accurate judgment capability of the portrait value and the accurate management capability of the portrait, and further realizing the accurate identification processing of the dynamic user portrait and the improvement of the processing efficiency of the user portrait data.
Furthermore, the system can preliminarily judge whether to adjust the user portrait dynamic feature ratio according to the actual user portrait dynamic feature duration by setting the preset first user portrait dynamic feature duration and the preset second user portrait dynamic feature duration, thereby realizing the fine monitoring of the user portrait dynamic feature duration and the timely adjustment of the user portrait dynamic feature ratio, and further realizing the accurate identification processing of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
Furthermore, the system of the invention can adjust the user portrait dynamic feature ratio according to the difference value between the actual user portrait dynamic feature time and the preset user portrait dynamic feature duration by setting the preset first user portrait dynamic feature duration difference value, the preset second user portrait dynamic feature duration difference value, the preset first user portrait dynamic feature ratio adjustment coefficient, the preset second user portrait dynamic feature ratio adjustment coefficient and the preset user portrait dynamic feature ratio, thereby reducing the output error rate of the user portrait, and further realizing the accurate identification processing of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
Furthermore, the system provided by the invention can preliminarily judge whether the user portrait is stored in the label area according to the characteristic correlation degree of the actual user portrait and the label area by setting the characteristic correlation degree of the preset first label area and the characteristic correlation degree of the preset second label area, thereby improving the accurate classification of the portrait label area in the system, and further realizing the accurate identification storage of the dynamic user portrait and the improvement of the processing efficiency of the user portrait data.
Further, the system can further judge whether the user portrait is stored in the tag area according to the difference value of the characteristic correlation degree between the actual user portrait and the tag area and the characteristic correlation degree of the preset tag area by setting the preset first tag area characteristic correlation degree difference value, the preset second tag area characteristic correlation degree difference value, the preset first user portrait storage probability adjustment coefficient, the preset second user portrait storage probability adjustment coefficient and the preset user portrait storage probability, so that the accurate classification and determination capability of the user tag area are improved, and the accurate identification processing of the dynamic user portrait and the improvement of the user portrait data processing efficiency are further realized.
Furthermore, the system can judge the category of the user according to the actual user portrait characteristic uniformity by setting the preset first user portrait characteristic uniformity and the preset second user portrait uniformity, thereby realizing the accurate classification and utilization of the user type, and further realizing the accurate identification processing of the dynamic user portrait and the improvement of the processing efficiency of the user portrait data.
Drawings
FIG. 1 is a block diagram illustrating a dynamic user image management system according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1, a dynamic user portrayal management system includes:
the portrait acquisition module is used for acquiring dynamic user portrait data;
the portrait processing module is connected with the portrait acquisition module and is used for carrying out preliminary judgment on the integrity of the dynamic user portrait data acquired by the portrait acquisition module and sending the user portrait with the integrity meeting the requirement to the portrait output module;
the storage module is connected with the portrait processing module and is used for receiving user portraits with the integrity not meeting the requirements, user portraits corresponding to the second class of users and user portraits stored in the corresponding tag areas;
The central control module is connected with the modules and the portrait output module and is used for adjusting the operation parameters of the system and the processing parameters of the portrait according to the actual dynamic user portrait data detected by the modules, when the initial determination of the integrity of the dynamic user portrait data is completed, the central control module adjusts the value of the user portrait according to the difference value between the dynamic characteristic proportion of the user portrait obtained by analyzing the dynamic user portrait data acquired by the portrait acquisition module and the dynamic characteristic proportion of the preset user portrait, when the adjustment of the value of the user portrait is completed, the central control module determines whether the user portrait is stored in the label area according to the characteristic correlation degree of the actual user portrait and the label area, and when the determination of the user portrait is stored in the corresponding label area, the central control module determines the category of the user corresponding to the user portrait according to the characteristic uniformity of the actual user portrait;
and the portrait output module is connected with the central control module and is used for outputting the user portrait of the corresponding area to the portrait application interface according to the judging result of the central control module.
According to the system, the preset portrait integrity difference value, the preset user portrait feature acquisition frequency, the preset user portrait dynamic feature ratio, the preset user portrait dynamic feature duration, the preset user portrait dynamic feature ratio, the preset label area feature correlation degree, the preset user portrait storage probability and the preset user portrait feature uniformity are set, the user portrait feature acquisition frequency can be adjusted according to the difference value of the actual user portrait dynamic feature ratio and the preset user portrait dynamic feature ratio, the user portrait value degree can be adjusted according to the difference value of the actual user portrait dynamic feature ratio and the preset user portrait dynamic feature ratio, the preliminary judgment on whether the user portrait is stored in the label area can be performed according to the feature correlation degree of the actual user portrait and the label area, the further judgment on whether the user portrait is stored in the label area can be performed according to the difference value of the feature correlation degree of the actual user portrait and the label area and the preset label area feature correlation degree, the accurate identification storage capacity of the dynamic user and the portrait processing efficiency are improved, and the user portrait data processing efficiency is improved.
The central control module is provided with a preset first image integrity D1 and a preset second image integrity D2, wherein D1 is smaller than D2, and when the image acquisition module finishes acquisition of the dynamic user image, the central control module performs preliminary judgment on whether acquisition is qualified or not according to the comparison result of the actual image integrity and the preset integrity,
if D is less than or equal to D1, the central control module judges that the integrity of the actual user image is lower than the allowable range and does not store the user image;
if D1 is more than D and less than or equal to D2, the central control module judges that the actual user portrait integrity is in an allowable range, calculates a difference DeltaD between the actual portrait integrity and the preset portrait integrity, adjusts the user portrait characteristic acquisition frequency to a corresponding value according to DeltaD, and sets DeltaD=D-D1;
if D is more than D2, the central control module judges that the integrity of the actual user portrait is in the allowable range and sends the user portrait to the portrait processing module to judge the value of the user portrait.
The system provided by the invention can be used for preliminarily judging whether the acquisition is qualified or not according to the comparison result of the actual portrait integrity and the preset integrity by setting the preset first portrait integrity and the preset second portrait integrity, so that the accurate recognition capability of the user portrait integrity is improved, and the accurate recognition storage of the dynamic user portrait and the improvement of the user portrait data processing efficiency are further realized.
The central control module is provided with a preset first image integrity difference DeltaD 1, a preset second image integrity difference DeltaD 2, a preset first user image characteristic acquisition frequency adjustment coefficient alpha 1, a preset second user image characteristic acquisition frequency adjustment coefficient alpha 2 and a preset user image characteristic acquisition frequency R0, wherein DeltaD 1 < DeltaD2, delta1 < alpha 2, when D1 < D is less than or equal to D2, the central control module adjusts the user image characteristic acquisition frequency according to the difference DeltaD of the actual image integrity and the preset image integrity,
if delta D is less than or equal to delta D1, the central control module judges that the difference value between the actual portrait integrity and the preset portrait integrity is lower than the allowable range, and uses alpha 2 to adjust the user portrait characteristic acquisition frequency, the adjusted user portrait characteristic acquisition frequency is recorded as R1, and R1=alpha 2×R0 is set;
if DeltaD 1 < DeltaDis less than or equal to DeltaD 2, the central control module judges that the difference value between the actual image integrity and the preset image integrity is lower than the allowable range, and uses alpha 1 to adjust the user image characteristic acquisition frequency, the adjusted user image characteristic acquisition frequency is recorded as R2, and R2=alpha 1×R0 is set;
and if delta D > -delta D2, the central control module judges that the difference value between the actual portrait integrity and the preset portrait integrity is within an allowable range and does not regulate the user portrait characteristic acquisition frequency.
According to the system, the preset first portrait integrity difference value, the preset second portrait integrity difference value, the preset first portrait characteristic acquisition frequency adjustment coefficient, the preset second portrait characteristic acquisition frequency adjustment coefficient and the preset user portrait characteristic acquisition frequency are set, so that the user portrait characteristic acquisition frequency can be adjusted according to the difference value between the actual portrait integrity and the preset portrait integrity, the accurate adjustment capability of the user portrait characteristic acquisition frequency is improved, the accurate management of the user portraits acquired by the portrait acquisition module is realized, and the accurate identification storage of the dynamic user portraits and the improvement of the user portrait data processing efficiency are further realized.
The central control module is provided with a preset first user portrait dynamic feature ratio S1 and a preset second user portrait dynamic feature ratio S2, wherein S1 is less than S2, when the central control module completes the adjustment of the user portrait feature acquisition frequency and D is more than D2, the central control module carries out preliminary judgment on whether to adjust the value degree of the user portrait according to the actually detected user portrait dynamic feature ratio,
if S is less than or equal to S1, the central control module judges that the dynamic characteristic ratio of the actual user portrait is in the allowable range and sends the user portrait to the portrait output module;
If S1 is more than S and less than or equal to S2, the central control module judges that the actual user portrait dynamic feature ratio is in the allowable range, detects the duration of the user portrait dynamic feature and adjusts the user portrait dynamic feature ratio to a corresponding value according to the duration;
if S is more than S2, the central control module judges that the actual user portrait dynamic feature ratio exceeds the allowable range, calculates a difference DeltaS between the actual user portrait dynamic feature ratio and the preset user portrait dynamic feature ratio, adjusts the user portrait value to a corresponding value according to DeltaS, and sets DeltaS=S-S2.
The system can preliminarily judge whether to adjust the value degree and the recommendation probability of the user portrait according to the actually detected user portrait dynamic characteristic proportion by setting the preset first user portrait dynamic characteristic proportion and the preset second user portrait dynamic characteristic proportion, improves the accurate management capability of the user portrait dynamic characteristic proportion, improves the control capability of the dynamic characteristic of the user portrait characteristic, and further realizes the accurate identification and storage of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
The central control module is provided with a preset first user portrait dynamic feature duty ratio difference DeltaS 1, a preset second user portrait dynamic feature duty ratio difference DeltaS 2, a preset first user portrait value degree adjustment coefficient beta 1, a preset second user portrait value degree adjustment coefficient beta 2 and a preset user portrait value degree E0, wherein DeltaS 1 < DeltaS2, delta1 < beta 2 < 1, and when S is more than S2, the central control module adjusts the user portrait value degree according to the difference DeltaS between the actual user portrait dynamic feature duty ratio and the preset user portrait dynamic feature duty ratio,
If DeltaS is less than or equal to DeltaS 1, the central control module judges that the difference value between the actual user portrait dynamic characteristic duty ratio and the preset user portrait dynamic characteristic duty ratio is within an allowable range and does not adjust the user portrait value;
if DeltaS 1 < DeltaSis less than or equal to DeltaS 2, the central control module judges that the difference between the actual user portrait dynamic characteristic proportion and the preset user portrait dynamic characteristic proportion exceeds the allowable range, and uses beta 2 to adjust the user portrait value, the adjusted user portrait value is marked as E1, and E1 = beta 2 multiplied by E0 is set;
and if DeltaS > DeltaS2, the central control module judges that the difference between the actual user portrait dynamic characteristic duty ratio and the preset user portrait dynamic characteristic duty ratio exceeds the allowable range, adjusts the user portrait value by using beta 1, marks the adjusted user portrait value as E2 and sets E2=beta 1×E0.
The system can adjust the user portrait value according to the difference between the actual user portrait dynamic characteristic ratio and the preset user portrait dynamic characteristic ratio by setting the preset first user portrait dynamic characteristic ratio difference, the preset second user portrait dynamic characteristic ratio difference, the preset first user portrait value adjustment coefficient, the preset second user portrait value adjustment coefficient and the preset user portrait value, thereby improving the accurate judgment capability of the portrait value and the accurate management capability of the portrait, and further realizing the accurate identification and storage of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
The central control module is provided with a preset first user portrait dynamic feature duration T1 and a preset second user portrait dynamic feature duration T2, wherein T1 is less than T2, when S1 is less than S and less than or equal to S2, the central control module carries out preliminary judgment on whether to adjust the user portrait dynamic feature duty ratio according to the actual user portrait dynamic feature duration,
if T is less than or equal to T1, the central control module judges that the duration of the dynamic characteristics of the actual user portrait is in an allowable range;
if T1 is more than T and less than or equal to T2, the central control module judges that the duration of the dynamic characteristics of the actual user portrait is in the allowable range, and detects the characteristic correlation degree between the user portrait and the tag area;
if T is more than T2, the central control module judges that the actual user portrait dynamic feature duration exceeds the allowable range, calculates the difference DeltaT between the actual user portrait dynamic feature time and the preset user portrait dynamic feature duration, adjusts the user portrait dynamic feature duty ratio to a corresponding value according to DeltaT, and sets DeltaT=T-T2.
The system can preliminarily judge whether to adjust the user portrait dynamic feature ratio according to the actual user portrait dynamic feature duration by setting the preset first user portrait dynamic feature duration and the preset second user portrait dynamic feature duration, thereby realizing the fine monitoring of the user portrait dynamic feature duration and the timely adjustment of the user portrait dynamic feature ratio, and further realizing the accurate identification and storage of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
The central control module is provided with a preset first user portrait dynamic feature duration difference DeltaT 1, a preset second user portrait dynamic feature duration difference DeltaT 2, a preset first user portrait dynamic feature duty cycle adjustment coefficient gamma 1, a preset second user portrait dynamic feature duty cycle adjustment coefficient gamma 2 and a preset user portrait dynamic feature duty cycle S0, wherein DeltaT 1 < DeltaT2, delta1 < gamma 2 < 1, when T > T2, the central control module adjusts the user portrait dynamic feature duty cycle according to the difference between the actual user portrait dynamic feature time and the preset user portrait dynamic feature duration,
if delta T is less than or equal to delta T1, the central control module judges that the difference value between the actual user portrait dynamic feature duration and the preset user portrait dynamic feature duration is within an allowable range and does not adjust the user portrait dynamic feature duty ratio;
if DeltaT 1 < DeltaT2 is less than or equal to DeltaT 2, the central control module judges that the difference value between the actual user portrait dynamic feature duration and the preset user portrait dynamic feature duration exceeds the allowable range, and adjusts the user portrait dynamic feature ratio by using gamma 2, wherein the adjusted user portrait dynamic feature ratio is recorded as S1, and S1=γ2×S0 is set;
If DeltaT > DeltaT2, the central control module judges that the difference value between the actual user portrait dynamic feature duration and the preset user portrait dynamic feature duration exceeds the allowable range, and adjusts the user portrait dynamic feature ratio by using gamma 1, wherein the adjusted user portrait dynamic feature ratio is recorded as S2, and S2=γ1×S0 is set.
The system of the invention can adjust the user portrait dynamic characteristic ratio according to the difference value between the actual user portrait dynamic characteristic time and the preset user portrait dynamic characteristic duration time by setting the preset first user portrait dynamic characteristic duration time difference value, the preset second user portrait dynamic characteristic duration time difference value, the preset first user portrait dynamic characteristic ratio adjustment coefficient, the preset second user portrait dynamic characteristic ratio adjustment coefficient and the preset user portrait dynamic characteristic ratio, thereby reducing the output error rate of the user portrait, and further realizing the accurate identification and storage of the dynamic user portrait and the improvement of the user portrait data processing efficiency.
The central control module is provided with a preset first tag area characteristic correlation degree B1 and a preset second tag area characteristic correlation degree B2, wherein B1 is smaller than B2, when the central control module finishes the adjustment of the dynamic characteristic ratio of the user portrait or T1 is smaller than or equal to T2, the central control module performs preliminary judgment on whether to store the user portrait in the tag area according to the characteristic correlation degree B of the actual user portrait and the tag area,
If B is less than or equal to B1, the central control module judges that the feature correlation degree between the actual user portrait and the tag area is lower than the allowable range and does not store the user portrait in the tag area;
if B1 is more than B and less than or equal to B2, the central control module judges that the feature correlation degree of the actual user portrait and the tag area is in an allowable range, calculates the difference delta B between the actual feature correlation degree and the feature correlation degree of the preset tag area, and further judges whether to store the user portrait in the tag area according to delta B;
if B is more than B2, the central control module judges that the feature correlation degree between the actual user portrait and the tag area is in an allowable range and directly stores the user portrait in the tag area.
According to the system, by setting the preset first label area feature correlation degree and the preset second label area feature correlation degree, whether the user portrait is stored in the label area or not can be primarily judged according to the feature correlation degree of the actual user portrait and the label area, the accurate classification of the portrait label area in the system is improved, and the accurate identification storage of the dynamic user portrait and the improvement of the processing efficiency of the user portrait data are further realized.
The central control module is provided with a preset first tag area characteristic correlation difference DeltaB 1, a preset second tag area characteristic correlation difference DeltaB 2, a preset first user image storage probability adjustment coefficient K1, a preset second user image storage probability adjustment coefficient K2 and a preset user image storage probability M0, wherein DeltaB 1 < DeltaB2, K1 < K2, when B1 < B2 is less than or equal to B2, the central control module further judges whether to store the user image in the tag area according to the difference value of the characteristic correlation of the actual user image and the tag area and the characteristic correlation of the preset tag area,
if delta B is less than or equal to delta B1, the central control module judges that the difference value between the characteristic correlation degree of the actual user portrait and the tag area and the characteristic correlation degree of the preset tag area is lower than the allowable range and does not adjust the storage probability of the preset user portrait;
if DeltaB 1 < DeltaB2 is less than or equal to DeltaB 2, the central control module judges that the difference value between the characteristic correlation degree of the actual user portrait and the tag area and the characteristic correlation degree of the preset tag area is in an allowable range, and uses K1 to adjust the storage probability of the user portrait, the storage probability of the adjusted user portrait is marked as M1, and M1=K1×M0 is set;
And if delta B > -delta B2, the central control module judges that the difference value between the characteristic correlation degree of the actual user portrait and the tag area and the characteristic correlation degree of the preset tag area is in an allowable range, and uses K2 to adjust the storage probability of the user portrait, the storage probability of the adjusted user portrait is marked as M2, and M2=K2×M0 is set.
According to the system, whether the user portrait is stored in the tag area or not can be further judged according to the difference value between the characteristic correlation of the actual user portrait and the tag area and the characteristic correlation of the preset tag area by setting the preset first tag area characteristic correlation difference value, the preset second tag area characteristic correlation difference value, the preset first user portrait storage probability adjustment coefficient, the preset second user portrait storage probability adjustment coefficient and the preset user portrait storage probability, so that the accurate classification and determination capability of the user tag area are improved, and the accurate identification processing of the dynamic user portrait and the improvement of the user portrait data processing efficiency are further realized.
The central control module is provided with a preset first user portrait characteristic uniformity C1 and a preset second user portrait uniformity C2, wherein C1 is smaller than C2, when the central control module completes the adjustment of the storage probability of the user portrait and B is smaller than or equal to B1, the central control module judges the category of the user according to the actual user portrait characteristic uniformity,
If C is less than or equal to C1, the central control module judges that the characteristic uniformity of the actual user portrait is less than the allowable range, and judges the user as three types of users, and the user portrait is not stored;
if C1 is more than C and less than or equal to C2, the central control module judges that the image characteristic uniformity of the actual user is in the allowable range, judges the user as a second class of users, and stores the user image into the storage module for standby;
if C is larger than C2, the central control module judges that the characteristic uniformity of the actual user portrait is in the allowable range, judges the user as a user, and connects the user portrait to the portrait output module.
The system can judge the category of the user according to the actual user portrait characteristic uniformity by setting the preset first user portrait characteristic uniformity and the preset second user portrait uniformity, thereby realizing the accurate classification and utilization of the user type, and further realizing the accurate identification processing of the dynamic user portrait and the improvement of the processing efficiency of the user portrait data.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (9)

the central control module is connected with the modules and the portrait output module and is used for adjusting the operation parameters of the system and the processing parameters of the portrait according to the actual dynamic user portrait data detected by the modules, when the initial determination of the integrity of the dynamic user portrait data is completed, the central control module adjusts the value of the user portrait according to the difference value between the dynamic characteristic proportion of the user portrait obtained by analyzing the dynamic user portrait data acquired by the portrait acquisition module and the dynamic characteristic proportion of the preset user portrait, when the adjustment of the value of the user portrait is completed, the central control module determines whether the user portrait is stored in the label area according to the characteristic correlation degree of the actual user portrait and the label area, and when the determination of the user portrait is stored in the corresponding label area, the central control module determines the category of the user corresponding to the user portrait according to the characteristic uniformity of the actual user portrait;
CN202210746105.6A2022-06-282022-06-28Dynamic user portrayal management systemActiveCN115146155B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202210746105.6ACN115146155B (en)2022-06-282022-06-28Dynamic user portrayal management system

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202210746105.6ACN115146155B (en)2022-06-282022-06-28Dynamic user portrayal management system

Publications (2)

Publication NumberPublication Date
CN115146155A CN115146155A (en)2022-10-04
CN115146155Btrue CN115146155B (en)2023-08-25

Family

ID=83409389

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202210746105.6AActiveCN115146155B (en)2022-06-282022-06-28Dynamic user portrayal management system

Country Status (1)

CountryLink
CN (1)CN115146155B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN105184375A (en)*2015-10-092015-12-23中国传媒大学Full industry chain film evaluation method and system based on big data
CN112131106A (en)*2020-09-162020-12-25电信科学技术第十研究所有限公司Test data construction method and device based on small probability data
CN112270596A (en)*2020-10-232021-01-26杭州伍暨通信设备有限公司Risk control system and method based on user portrait construction
CN112700271A (en)*2020-12-292021-04-23长威信息科技发展股份有限公司Big data image drawing method and system based on label model
CN113157752A (en)*2021-03-122021-07-23北京航空航天大学Scientific and technological resource recommendation method and system based on user portrait and situation
CN113312531A (en)*2021-04-222021-08-27广州丰石科技有限公司User portrait identification method based on DPI analysis and decision tree model

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110839129A (en)*2018-08-172020-02-25Oppo广东移动通信有限公司 Image processing method, device and mobile terminal

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN105184375A (en)*2015-10-092015-12-23中国传媒大学Full industry chain film evaluation method and system based on big data
CN112131106A (en)*2020-09-162020-12-25电信科学技术第十研究所有限公司Test data construction method and device based on small probability data
CN112270596A (en)*2020-10-232021-01-26杭州伍暨通信设备有限公司Risk control system and method based on user portrait construction
CN112700271A (en)*2020-12-292021-04-23长威信息科技发展股份有限公司Big data image drawing method and system based on label model
CN113157752A (en)*2021-03-122021-07-23北京航空航天大学Scientific and technological resource recommendation method and system based on user portrait and situation
CN113312531A (en)*2021-04-222021-08-27广州丰石科技有限公司User portrait identification method based on DPI analysis and decision tree model

Also Published As

Publication numberPublication date
CN115146155A (en)2022-10-04

Similar Documents

PublicationPublication DateTitle
CN110245213B (en)Questionnaire generation method, device, equipment and storage medium
Myung et al.Adaptive binary splitting for efficient RFID tag anti-collision
US6128398A (en)System, method and application for the recognition, verification and similarity ranking of facial or other object patterns
US6430306B2 (en)Systems and methods for identifying images
US7046829B2 (en)Fingerprint verification
CA2549092A1 (en)System and method for providing improved claimant authentication
CN106921942B (en)Equipment control method and device
CN115146155B (en)Dynamic user portrayal management system
CN113162986B (en)Automatic multi-type Internet of things parallel access protocol adaptation method and system
CN120278454A (en)Digital intelligent service system for enterprise service
CN112788280A (en)Intelligent conference media management cloud platform based on cloud computing and voice feature analysis
CN116383421B (en)Artificial intelligence data aggregation system based on big data
CN117811935B (en)Smart city Internet of things system based on wireless communication and operation method
CA2588078C (en)Multimodal biometric platform
CN116432469A (en)Data channel management system and method based on big data
CN109165601A (en)Face identification method and device neural network based
CN110502346A (en)Resource information management system and method under a kind of cluster environment
CN113609465B (en)OFD document authority control system and method based on face recognition
CN113435842B (en) Business process processing method and computer equipment
CN112187814B (en)Intelligent double-recording method, system and server
CN210895444U (en)Data processing device suitable for financial big data analysis
CN111818044A (en)Security event reporting system based on multi-level mode
CN120108076B (en)Campus ID card multi-scene identity authentication system based on edge calculation
CN114040484B (en)Control system for dynamically adjusting wireless AP transmitting power and energy consumption
CN119316451B (en)Safe communication method of electric power Internet of things system

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp