CN111754107A - Anchor value evaluation method and device, electronic equipment and readable storage medium - Google Patents
Anchor value evaluation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN111754107A CN111754107A CN202010577138.3A CN202010577138A CN111754107A CN 111754107 A CN111754107 A CN 111754107A CN 202010577138 A CN202010577138 A CN 202010577138A CN 111754107 A CN111754107 A CN 111754107A
- Authority
- CN
- China
- Prior art keywords
- anchor
- value
- evaluation
- user
- platform
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Signal Processing (AREA)
- Strategic Management (AREA)
- Multimedia (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Computer Graphics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a method and a device for evaluating anchor broadcast value, electronic equipment and a readable storage medium, aiming at an anchor broadcast to be evaluated, live broadcast data and behavior data of a user are obtained, and index values corresponding to anchor broadcast characteristic indexes in a plurality of anchor broadcast characteristic indexes established in advance are obtained according to the live broadcast data and the behavior data. And obtaining an evaluation value of the anchor to be evaluated according to the obtained multiple index values and a pre-established evaluation model consisting of multiple anchor characteristic indexes. Therefore, based on the pre-established evaluation model containing a plurality of anchor characteristic indexes, the anchor data of the anchor and the behavior data of the user are combined, the evaluation of the anchor value is realized, the accuracy of the evaluation result is improved, the evaluation times are reduced, and the occupation of the equipment computing resources is reduced.
Description
Technical Field
The invention relates to the technical field of network live broadcast, in particular to a method and a device for evaluating anchor value, electronic equipment and a readable storage medium.
Background
The anchor resource is the key for the development of the live broadcast platform and is one of the main resources of each live broadcast platform. The evaluation of each anchor relative to the live broadcast platform is very important, and the positioning of the anchor by the platform can be evaluated based on the evaluation of the anchor, so that a powerful basis is provided for the adjustment of anchor strategies.
However, most of the current evaluations of the anchor relative to the live broadcast platform are based on the subjective experience guidance to evaluate related data, so that the evaluation result is greatly influenced by subjective factors, and the correlation between the anchor evaluation and network data cannot be accurately reflected, so that the evaluation result is inaccurate, multiple evaluations need to be repeatedly performed in the evaluation process, the waste of computing resources of equipment for performing the evaluation process is caused, and the stability of the equipment is influenced.
Disclosure of Invention
The invention aims to provide a method, a device, an electronic device and a readable storage medium for evaluating the value of a anchor, which can improve the accuracy of the value evaluation of the anchor relative to a platform and reduce the evaluation times so as to reduce the occupation of computing resources of the device.
Embodiments of the invention may be implemented as follows:
in a first aspect, an embodiment of the present invention provides a method for assessing anchor value, where the method includes:
acquiring live broadcast data of a anchor to be evaluated and behavior data of a user;
according to the live broadcast data and the behavior data, obtaining index values corresponding to all anchor characteristic indexes in a plurality of anchor characteristic indexes established in advance;
and obtaining the evaluation value of the anchor to be evaluated according to the obtained index values and a pre-established evaluation model, wherein the evaluation model is composed of the plurality of anchor characteristic indexes.
In an optional embodiment, each of the anchor feature indicators in the evaluation model has a corresponding indicator coefficient, and the method further includes a step of pre-establishing the evaluation model, where the step includes:
acquiring a plurality of anchor samples, live broadcast data of each anchor sample and behavior data of a corresponding user sample;
fitting index coefficients corresponding to the anchor characteristic indexes according to live broadcast data of the anchor samples and behavior data of the user samples to obtain corresponding coefficient values;
and establishing the evaluation model based on each anchor characteristic index and the coefficient value of the corresponding index coefficient.
In an optional implementation manner, the step of fitting the index coefficients corresponding to the anchor characteristic indexes according to the live data of the anchor sample and the behavior data of the user sample to obtain corresponding coefficient values includes:
obtaining platform time length loss according to the behavior data of the user samples, wherein the platform time length loss represents the reduction of platform access time length caused by the loss of the corresponding user samples after the broadcasting of the anchor samples is stopped;
obtaining an index value of each anchor characteristic index according to the live broadcast data of the anchor sample;
and fitting the index coefficients corresponding to the anchor characteristic indexes according to the index values and the platform time length loss to obtain corresponding coefficient values.
In an optional implementation manner, the step of obtaining the platform duration loss according to the behavior data of the user sample includes:
obtaining a characteristic value of each user characteristic in a plurality of pre-established user characteristics according to the behavior data of the user sample;
importing the obtained multiple characteristic values into a pre-established discrimination model to obtain a discrimination result, wherein the discrimination result represents whether the user sample runs off from the platform after the main broadcast sample stops broadcasting;
and when the judgment result shows that the user sample is lost from the platform, acquiring the access time of the user sample to the platform in a historical preset time period as the time loss of the platform.
In an optional embodiment, the method further includes a step of pre-establishing the discriminant model, which includes:
acquiring anchor training samples and user training samples corresponding to the anchor training samples, wherein the anchor training samples are anchors which are stopped on the platform, behavior data of the user training samples comprise stay tags, and the stay tags represent that the user training samples are retained or lost on the platform after the anchor training samples are stopped;
and training according to the behavior data of the user training sample to obtain a discriminant model.
In an optional embodiment, the step of training to obtain a discriminant model according to the behavior data of the user training sample includes:
training the constructed initial model according to the behavior data of the user training sample, and outputting a sample label of the user training sample;
comparing the retention label and the sample label of the user training sample, adjusting the parameters of the initial model and then continuing training, and obtaining the discrimination model when the preset stop condition is met.
In an alternative embodiment, the method further comprises:
obtaining a positioning evaluation value of the anchor to be evaluated according to the evaluation value of the anchor to be evaluated and a positioning value preset for the anchor to be evaluated;
obtaining a positioning evaluation mean value of the anchor on the platform according to the evaluation values of all the anchors on the platform and the positioning values preset for all the anchors;
and judging whether the positioning value of the anchor to be evaluated is reasonable or not according to the positioning evaluation value of the anchor to be evaluated and the positioning evaluation mean value of the anchor on the platform.
In an optional implementation manner, the step of obtaining a mean value of the positioning evaluations of the anchor on the platform according to the evaluation values of all the anchors on the platform and the positioning value preset for each anchor includes:
acquiring area information in the attribute information of the anchor to be evaluated;
screening the anchor which has the same area information as the anchor to be evaluated on the platform;
and obtaining a positioning evaluation mean value of the anchor on the platform according to the screened evaluation values of the anchor and positioning values preset for each screened anchor.
In an optional implementation manner, the step of determining whether the positioning value of the anchor to be evaluated is reasonable according to the positioning evaluation value of the anchor to be evaluated and the positioning evaluation mean value of the anchor on the platform includes:
and if the positioning evaluation value of the anchor to be evaluated is smaller than or equal to the positioning evaluation mean value of the anchor on the platform, judging that the positioning value set by the anchor to be evaluated is reasonable, otherwise, judging that the positioning value set by the anchor to be evaluated is unreasonable.
In an optional embodiment, the anchor characteristic indicator at least includes two or more combinations of core user information of the anchor, an anchor broadcasting time length, an access time length of a user of the anchor, an average online number of persons who are broadcasted by the anchor in unit time, a maximum online number of persons who are broadcasted by the anchor in unit time, and virtual gift information acquired by the anchor.
In an optional embodiment, the user characteristics at least include a combination of two or more of a viewing duration of the user to the target anchor, a viewing duration ratio of the user to the target anchor, an average daily viewing duration ratio of the user to the target anchor, subscription information of the user to the target anchor, and subscription information of the user to other users on the platform.
In a second aspect, an embodiment of the present invention provides a device for assessing anchor value, where the device includes:
the data acquisition module is used for acquiring live broadcast data of the anchor to be evaluated and behavior data of a user;
an index value obtaining module, configured to obtain, according to the live data and the behavior data, an index value corresponding to each anchor characteristic index in a plurality of anchor characteristic indexes established in advance;
and the evaluation module is used for obtaining the evaluation value of the anchor to be evaluated according to the obtained index values and a pre-established evaluation model, wherein the evaluation model is composed of the plurality of anchor characteristic indexes.
In a third aspect, embodiments of the present invention provide an electronic device, including one or more storage media and one or more processors in communication with the storage media, where the one or more storage media store machine-executable instructions executable by the processors, and when the electronic device runs, the processors execute the machine-executable instructions to perform the anchor value evaluation method described in any one of the foregoing embodiments.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing machine-executable instructions, which when executed implement the anchor value assessment method according to any one of the foregoing embodiments.
The beneficial effects of the embodiment of the invention include, for example:
the embodiment of the application provides a method and a device for evaluating anchor broadcast value, electronic equipment and a readable storage medium, aiming at an anchor broadcast to be evaluated, live broadcast data and behavior data of a user are obtained, and index values corresponding to anchor broadcast characteristic indexes in a plurality of anchor broadcast characteristic indexes established in advance are obtained according to the live broadcast data and the behavior data. And obtaining an evaluation value of the anchor to be evaluated according to the obtained multiple index values and a pre-established evaluation model consisting of multiple anchor characteristic indexes. Therefore, based on the pre-established evaluation model containing a plurality of anchor characteristic indexes, the anchor value is evaluated by combining the anchor data of the anchor and the behavior data of the user, the accuracy of the evaluation result can be improved, the evaluation times are reduced, and the occupation of equipment computing resources is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic view of an application scenario of a anchor value evaluation method provided in an embodiment of the present application;
FIG. 2 is a flow chart of a method for assessing anchor value provided by an embodiment of the present application;
FIG. 3 is a flow chart of a method for establishing an evaluation model according to an embodiment of the present application;
fig. 4 is a flowchart of an index coefficient fitting method according to an embodiment of the present application;
fig. 5 is a flowchart of a method for obtaining a platform duration loss according to an embodiment of the present application;
FIG. 6 is a flowchart of a discriminant model obtaining method according to an embodiment of the present disclosure;
FIG. 7 is a flowchart of a discriminant model training method according to an embodiment of the present disclosure;
fig. 8 is a flowchart of an anchor location value evaluation method provided in an embodiment of the present application;
fig. 9 is a flowchart of a method for obtaining a mean value of a platform anchor location evaluation provided in an embodiment of the present application;
fig. 10 is a block diagram of an electronic device according to an embodiment of the present application;
fig. 11 is a functional block diagram of a anchor value evaluation device according to an embodiment of the present application.
Icon: 100-live broadcast providing terminal; 200-a live broadcast server; 300-a live broadcast receiving terminal; 110-a storage medium; 120-a processor; 130-anchor value assessment means; 131-a data acquisition module; 132-index value obtaining module; 133-an evaluation module; 140-communication interface.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Referring to fig. 1, a schematic view of a possible application scenario of the anchor value evaluation method according to the embodiment of the present application is shown, where the scenario includes a live broadcast providing terminal 100, a live broadcast server 200, and a live broadcast receiving terminal 300. The live broadcast server 200 is in communication connection with the live broadcast providing terminal 100 and the live broadcast receiving terminal 300, respectively, and is configured to provide live broadcast services for the live broadcast providing terminal 100 and the live broadcast receiving terminal 300. For example, the live broadcast providing terminal 100 may transmit a live video stream to the live broadcast server 200, and the viewer may access the live broadcast server 200 through the live broadcast receiving terminal 300 to view the live video.
The live video stream pushed by the live server 200 may be a video stream currently live in a live platform or a complete video stream formed after the live broadcast is completed.
It is understood that the scenario shown in fig. 1 is only one possible example, and in other possible embodiments, the scenario may include only a part of the components shown in fig. 1 or may also include other components.
In this embodiment, the live broadcast providing terminal 100 and the live broadcast receiving terminal 300 may be, but are not limited to, a smart phone, a personal digital assistant, a tablet computer, a personal computer, a notebook computer, a virtual reality terminal device, an augmented reality terminal device, and the like.
The live broadcast providing terminal 100 and the live broadcast receiving terminal 300 may have internet products installed therein for providing live broadcast services of the internet, for example, the internet products may be applications APP, Web pages, applets, etc. related to live broadcast services of the internet used in a computer or a smart phone.
In this embodiment, a video capture device for capturing the anchor video frame may be further included in the scene, and the video capture device may be, but is not limited to, a camera, a lens of a digital camera, a monitoring camera, a webcam, or the like.
The video capture device may be directly installed or integrated in the live broadcast providing terminal 100. For example, the video capture device may be a camera configured on the live broadcast providing terminal 100, and other modules or components in the live broadcast providing terminal 100 may receive videos and images transmitted from the video capture device via the internal bus. Alternatively, the video capture device may be independent of the live broadcast providing terminal 100, and the two may communicate with each other in a wired or wireless manner.
Fig. 2 is a flowchart illustrating a anchor value evaluation method provided in an embodiment of the present application, which can be executed by the live broadcast server 200 shown in fig. 1. It should be understood that, in other embodiments, the order of some steps in the anchor value evaluation method of this embodiment may be interchanged according to actual needs, or some steps may be omitted or deleted. The detailed steps of the anchor value assessment method are described below.
Step S210, acquiring the live broadcast data of the anchor to be evaluated and the behavior data of the user.
Step S220, obtaining index values corresponding to each anchor characteristic index in a plurality of anchor characteristic indexes established in advance according to the live broadcast data and the behavior data.
Step S230, obtaining an evaluation value of the anchor to be evaluated according to the obtained index values and a pre-established evaluation model, where the evaluation model is composed of the plurality of anchor characteristic indexes.
In this embodiment, the user refers to a user who watches live webcasting of the anchor through the live broadcast platform by using the live broadcast receiving terminal 300. When the value of the anchor is evaluated, the obtained behavior data of the user mainly refers to the behavior data of the user who has viewed the anchor within a period of time, namely the behavior data of the user who has a correlation with the anchor.
The live broadcast data of the anchor to be evaluated may include, for example, a duration of the broadcast, a number of days, a situation of a core user, a situation of a viewing user of the broadcast, and the like, which may reflect a degree of attention paid to the live broadcast of the anchor, a quality of the live broadcast, a frequency of the live broadcast, and the like from multiple aspects. The behavior data of the user mainly includes the watching condition of the user on a specific anchor, the watching condition of the user on a plurality of anchors on the platform, and the like, and can embody the attention degree of the user on the platform and the attention degree of a certain specific anchor.
In this embodiment, a plurality of anchor characteristic indicators are pre-constructed, and the live broadcast state of the anchor can be reflected from a plurality of aspects through the plurality of anchor characteristic indicators, wherein each constructed anchor characteristic indicator can be indicator information acquired by the operator based on the daily live broadcast condition of the platform, so that the operator can conveniently evaluate the value of the anchor based on the acquirable information.
An evaluation model can be constructed in advance based on the established multiple anchor characteristic indexes, and the evaluation model can synthesize the multiple anchor characteristic indexes to evaluate the value of the anchor. The evaluation model can be understood as that each anchor characteristic index is obtained after being integrated by different weights. When a specific evaluation value is obtained based on the evaluation model, index values corresponding to the anchor characteristic indexes need to be obtained first. And the index value of each anchor characteristic index can be obtained according to the actually obtained live broadcast data and the behavior data of the user. On the basis, the obtained index values are substituted into the evaluation model, and the evaluation value capable of comprehensively evaluating the comprehensive value of the anchor can be obtained.
In this embodiment, an evaluation model formed by a plurality of anchor characteristic indexes is established in advance, and an evaluation value of the anchor is obtained according to the evaluation model based on the acquired live broadcast data and behavior data. The evaluation on the anchor value can be realized, and the accuracy of the evaluation result is improved. Thereby reducing the use of computing resources of the live broadcast server 200. In a live application scenario, the performance stability of the live server 200 will affect the live effect, such as whether a delay occurs, whether the quality of the live picture is low, and whether a jam occurs. Therefore, it is important to maintain performance stability of the live server 200.
The evaluation scheme provided by the embodiment has high evaluation accuracy, reduces the evaluation times, can reduce the occupation of the calculation resources of the live broadcast server 200 in the evaluation process, and avoids the problems that the evaluation accuracy is low in the prior art, and the performance stability of the live broadcast server 200 is influenced due to the waste of the calculation resources of the live broadcast server 200 caused by repeated evaluation for many times.
In this embodiment, to achieve accurate assessment of the anchor value, a reasonable assessment model needs to be established, and as can be seen from the above, the assessment model is composed of a plurality of anchor characteristic indexes, and each anchor characteristic index has a corresponding index coefficient. Therefore, each index coefficient needs to be accurately determined, so that value evaluation based on the evaluation model can be realized. Referring to fig. 3, in the present embodiment, the evaluation model can be pre-established in the following manner:
step S310, a plurality of anchor samples, live broadcast data of each anchor sample, and behavior data of a corresponding user sample are obtained.
Step S320, fitting the index coefficients corresponding to the anchor characteristic indexes according to the live data of the anchor sample and the behavior data of the user sample to obtain corresponding coefficient values.
Step S330, establishing the evaluation model based on each anchor characteristic index and the coefficient value of the corresponding index coefficient.
In this embodiment, when the evaluation model is pre-established, a plurality of anchor samples on the platform may be collected, where the anchor samples may be users whose corresponding number of users reaches a certain value, for example, 100, 200, and the like. And combining the live broadcast data of the anchor sample and the behavior data of the user sample to obtain the index values corresponding to the anchor characteristic indexes. In this embodiment, live broadcast data of each anchor sample in a preset period of history may be collected, for example, within 30 days of history or within 40 days of history. Correspondingly, behavior data of the corresponding user sample in a historical preset period of time are collected.
The value of the anchor on the platform relative to the platform can be reflected in the situation of user loss caused by the user who stops playing the anchor after the anchor stops playing the anchor, namely after the platform stops playing the anchor. The more users that are lost in this portion, the greater the user precipitation effect of the anchor on the platform, and the greater the loss of the anchor on the platform after the platform is stopped. And the content provider taking the anchor as a platform needs to improve the watching duration of the user for the core behavior stimulation of the user. Therefore, the main broadcasting stop may cause the loss of the user, and further, the access duration of the platform is reduced.
Based on the analysis, when matching is performed on index coefficients of the anchor characteristic indexes by using live broadcast data of the anchor sample and behavior data of the user sample, the duration loss of the platform can be used as a basis for the matching. Alternatively, referring to fig. 4, when fitting the index coefficients, the following steps may be performed:
and step S410, obtaining the time length loss of the platform according to the behavior data of the user sample. The platform duration loss represents a reduction in platform access duration caused by a corresponding user sample loss after the anchor sample is stopped.
Step S420, obtaining an index value of each anchor characteristic index according to the live broadcast data of the anchor sample.
Step S430, according to the index values and the platform time length loss, fitting the index coefficients corresponding to the anchor characteristic indexes to obtain corresponding coefficient values.
In this embodiment, the behavior data of the user sample may reflect the viewing condition of the user sample on the platform, the viewing condition of the user sample on the specific anchor, and the like. And obtaining the platform duration loss according to the behavior data of the user sample, wherein the platform duration loss is the reduction of the access duration of the platform caused by the assumption that the user sample runs off the platform.
The platform duration loss may be a total duration of viewing, i.e., total duration of access, of the platform by the user sample within a historical preset period of time. The total watching duration of the user samples represents the contribution of the corresponding anchor samples to the platform, and the longer the total watching duration of the user samples is, the larger the contribution of the anchor samples is.
And obtaining the index value of each live broadcast characteristic index according to the live broadcast data of the anchor sample, and taking the obtained platform time length loss as a fitting dependent variable and the index value of each anchor characteristic index as a fitting independent variable. In the case of multiple anchor samples and multiple user samples, multiple sets of index values and multiple sets of platform duration losses can be obtained. In this case, a linear fitting method may be used to fit a plurality of unknown index coefficients, and obtain coefficient values.
In this embodiment, the established anchor characteristic indicator at least includes two or more combinations of core user information of the anchor, an anchor broadcasting time, an access time of a user of the anchor, an average online number of people in unit time of the anchor broadcasting, a highest online number of people in unit time of the anchor broadcasting, and virtual gift information obtained by the anchor.
Optionally, the anchor characteristic indicator may specifically include, but is not limited to, a plurality of indicators as listed in table 1.
In the calculation of the index value in table 1, the live broadcast data and the behavior data of the anchor sample and the user sample in the history of 30 days are used for measurement, but it should be understood that the present embodiment is not limited thereto, and the index value may be adjusted according to actual requirements during implementation.
TABLE 1 Anchor characteristic indicators
As can be seen from the above, when evaluating the contribution of a certain anchor to the platform, it is assumed that the anchor stops playing, and then the loss of the platform duration caused by the lost user is taken as the criterion. Therefore, for the anchor to be evaluated, it is first necessary to determine whether each user corresponding to the anchor will be lost after the anchor is stopped. Alternatively, referring to fig. 5, the above-mentioned time loss in performing the platform may be performed by:
step S510, obtaining a feature value of each of the user features in the pre-established plurality of user features according to the behavior data of the user sample.
Step S520, the obtained characteristic values are imported into a pre-established discrimination model to obtain a discrimination result, and the discrimination result represents whether the user sample runs off from the platform after the main broadcast sample stops broadcasting.
Step S530, when the judgment result shows that the user sample is lost from the platform, acquiring the access time of the user sample to the platform in a historical preset time period as the time loss of the platform.
In this embodiment, the behavior data of the user represents the viewing condition of the user on the platform and the viewing condition of the user on the specific anchor, so that the relative attention tendency of the user on the specific anchor can be reflected to a certain extent. Optionally, a plurality of user characteristics are pre-established, and the user characteristics are used as a basis for measuring whether the user is lost.
In this embodiment, the user characteristics at least include a combination of two or more of the viewing duration of the user on the target anchor, the viewing duration ratio of the user on the target anchor, the average daily viewing duration ratio of the user on the target anchor, subscription information of the user on the target anchor, and subscription information of the user on other users on the platform.
In particular, the user characteristics may include, but are not limited to, a plurality of characteristic items listed in table 2.
In the calculation of the feature value of each user feature in table 2, the user viewing condition within 30 days of the history is used for calculation, and it should be noted that this embodiment is not limited to this, and the calculation may be performed according to actual needs.
After the characteristic values of the user characteristics are obtained, the characteristic values are led into the established discrimination model, the discrimination model is a binary model, and whether the corresponding user sample can run off from the platform after a certain anchor sample stops playing can be discriminated based on the characteristic values of the user characteristics, namely, the platform is not accessed any more or rarely in the following process. If it is determined that a certain user sample is lost, it is firstly indicated that the anchor sample has a certain contribution to the platform, and then platform duration loss brought by the lost user to the platform is obtained, and the platform duration loss can embody the contribution of the anchor sample to the platform in a quantitative manner.
TABLE 2 subscriber characteristics
In this embodiment, the above used discriminant model is pre-constructed, and optionally, referring to fig. 6, the process of constructing the discriminant model can be as follows.
Step S610, anchor training samples and user training samples corresponding to each anchor training sample are obtained. The anchor training sample is an anchor that has been stopped on the platform, the behavior data of the user training sample includes a stay tag, and the stay tag represents that the user training sample remains or runs off on the platform after the anchor training sample is stopped.
And S620, training according to the behavior data of the user training sample to obtain a discriminant model.
In this embodiment, the obtained anchor training sample is an anchor that has been stopped playing on the platform for a certain period of time, for example, two months, three months, and the like. In this way, whether the corresponding user training sample runs off from the platform can be determined by counting the access condition of the corresponding user training sample to the platform after the anchor training sample stops playing. For example, if the user training sample is visited on the platform for more than a certain number of days or more than a certain length of time within 30 days after the anchor training sample is stopped, the user training sample may be considered not to be lost, otherwise, the user training sample may be considered to be lost from the platform.
Based on the statistical situation, a stay label setting may be performed on each user training sample, for example, a stay label of 0 indicates that the user training sample is lost on the platform, and if the stay label is 1, indicates that the user training sample is not lost on the platform.
On the basis, the model can be trained according to the behavior data of the user training sample to obtain the discriminant model. Alternatively, referring to fig. 7, the specific process may include the following steps:
step S710, training the constructed initial model according to the behavior data of the user training sample, and outputting a sample label of the user training sample.
And S720, comparing the retention label and the sample label of the user training sample, adjusting the parameters of the initial model and then continuing training, and obtaining the judgment model when the preset stopping condition is met.
Alternatively, an initial model may be established, which may be a gradient lifting tree model, a decision tree model, a random forest algorithm model, or the like. For the behavior data of the user training sample, feature values of a plurality of user features are obtained based on the behavior data, and specifically, feature values of a plurality of user features listed in table 2 may be obtained. And importing the processed characteristic values into the initial model to train the initial model. The output of the initial model is a sample label of a user training sample, namely whether the user is left on the platform or lost from the platform is judged by the model. And adjusting the parameters of the initial model by comparing the retention label of the user training sample with the sample label obtained by model judgment. And obtaining the discrimination model under the condition that the iteration times reach the preset times or the discrimination accuracy of the model reaches the preset accuracy.
In this embodiment, through the above process, model training is performed based on the anchor training sample and the user training sample to obtain a discriminant model. The discriminant model can be used to discriminate whether a corresponding user is retained on or lost from the platform after an anchor is stopped. If the user runs off from the platform, the time length loss of the platform can be obtained according to the historical watching time length of the user on the platform, and the time length loss of the platform can embody the contribution of the anchor to the platform.
In order to quantify the contribution value of the anchor to the platform through various anchor core data indexes of the anchor and further realize anchor play guidance and interference of an actual control layer, the method is embodied by constructing an evaluation model comprising a plurality of anchor characteristic indexes. The method comprises the steps of collecting a anchor sample and a user sample, obtaining platform duration loss based on the anchor sample and the user sample and by using the discrimination model, and fitting index coefficients of all anchor characteristic indexes in an evaluation model by combining the platform duration loss with live broadcast data and behavior data so as to establish the evaluation model.
And when the value of the anchor is formally evaluated, acquiring the live broadcast data of the anchor to be evaluated and the corresponding behavior data of the user, and evaluating by using an evaluation model to obtain the evaluation value of the anchor.
In the evaluation scheme provided by this embodiment, a discrimination model is established to discriminate whether a user corresponding to a certain anchor runs away after the anchor is stopped. And under the condition of loss, obtaining the platform time length loss, fitting each index coefficient of the evaluation model based on the platform time length loss, and finally evaluating the value of the anchor by using the evaluation model.
Under the condition of obtaining the evaluation value of the anchor, the method can provide a basis for the operation to interfere with the anchor for broadcasting, the anchor pay expenditure and the user culture in advance. For example, the loss of users can be predicted based on the discriminant model, and some valuable content guidance can be performed for predicting lost users to increase the cost of losing from the platform. For the anchor with a high evaluation value obtained by evaluation based on the evaluation model, in order to avoid the influence of the anchor stop on the platform, manual intervention is performed in advance, so that the loss is avoided. In addition, the evaluation of platform cost can be carried out based on the evaluation of each anchor, and the reasonability of compensation of the anchor can be judged.
Optionally, referring to fig. 8, on the basis, the anchor value evaluation method provided in this embodiment further includes the following steps:
step S810, obtaining a positioning evaluation value of the anchor to be evaluated according to the evaluation value of the anchor to be evaluated and a positioning value preset for the anchor to be evaluated.
Step S820, obtaining a positioning evaluation mean value of the anchor on the platform according to the evaluation values of all the anchors on the platform and the positioning values preset for each of the anchors.
And step S830, judging whether the positioning value of the anchor to be evaluated is reasonable or not according to the positioning evaluation value of the anchor to be evaluated and the positioning evaluation mean value of the anchor on the platform.
In this embodiment, a positioning value is set in advance for each anchor on the platform, where the positioning value may be, for example, compensation, a grade, and the like, and a positioning evaluation value may be obtained by using an evaluation value of an anchor to be evaluated and a positioning value of the anchor to be evaluated, and may be calculated according to the following formula, for example:
positioning evaluation value of anchor to be evaluated (positioning value of anchor to be evaluated/evaluation value of anchor to be evaluated)
The rationality judgment of the positioning value of the anchor to be evaluated cannot be carried out only by a simply set numerical value, and needs to be carried out by combining the relative conditions of other anchors on the platform. Therefore, a positioning evaluation mean value can be obtained based on the evaluation values of all the anchor on the platform and the positioning value of each anchor. And judging whether the positioning value of the anchor to be evaluated is reasonable or not by comparing the positioning evaluation mean values.
It should be understood that the larger the evaluation value of the anchor to be evaluated, the smaller the positioning evaluation value will be. And the larger the positioning value of the anchor to be evaluated is, the larger the positioning evaluation value is. And the larger the evaluation value of the anchor is, the larger the contribution to the platform is, and the larger the positioning value of the anchor is, the higher the investment cost of the platform is. Therefore, the anchor's location rating should be relatively low to keep the investment of the platform for that anchor within reasonable bounds with respect to its contribution.
Therefore, in this embodiment, if the positioning evaluation value of the anchor to be evaluated is less than or equal to the positioning evaluation mean value of the anchor on the platform, it is determined that the positioning value set by the anchor to be evaluated is reasonable. Otherwise, if the positioning evaluation value of the anchor to be evaluated is larger than the positioning evaluation mean value of the anchor on the platform, the positioning value set by the anchor to be evaluated is judged to be unreasonable.
In this embodiment, considering that the difference between possible values of the evaluation values of each anchor on the platform is large, and the subsequent processing and comparison may be complicated, the evaluation values of each anchor may be normalized first, for example, to be normalized to a range of 1-100. And processing by using the normalized evaluation value.
In addition, considering that some live broadcast platforms may involve the anchor and operation management of multiple regions and multiple countries, and each region has its own anchor market condition and development stage, the overall anchor positioning evaluation is an evaluation system which can be commonly used in multiple region ranges on the basis of considering the condition of each region. And the evaluation of the positioning value cannot be performed on the anchor of different areas with the same criteria. Therefore, referring to fig. 9, when evaluating the rationality of the positioning value of the anchor to be evaluated, the above-mentioned evaluation can be implemented by the following steps based on the consideration of the locality:
step S910, obtaining area information in the attribute information of the anchor to be evaluated.
And step S920, screening the anchor on the platform with the same area information as the anchor to be evaluated.
And step S930, obtaining a positioning evaluation mean value of the anchor on the platform according to the screened evaluation value of the anchor and a positioning value preset for each screened anchor.
In this embodiment, the rationality of the positioning value of the anchor to be evaluated is judged by screening out a plurality of anchors belonging to the same area as the anchor to be evaluated and comparing the anchor to be evaluated based on the positioning evaluation mean value of the screened anchors. Therefore, the specific conditions of different areas can be distinguished, and the method is suitable for the local anchor market condition and the platform development condition.
In this embodiment, the area information to which the anchor belongs on the platform is taken into consideration, and the positioning value of the local anchor is evaluated based on the positioning evaluation mean value of each area, so that whether the positioning value of the anchor is reasonable or not in the same market environment of the local anchor can be measured.
In order to facilitate those skilled in the art to have a more detailed understanding of the anchor value evaluation scheme provided in the present application, the overall flow of the evaluation scheme will be described below.
The anchor value evaluation scheme mainly comprises a pre-model establishing stage and a formal evaluation stage.
In the model building stage, firstly, the anchor training sample which is stopped playing for a period of time on the platform is obtained, and the corresponding user training sample is obtained. The behavior data of the user training sample comprises a stay tag which indicates whether the user training sample is retained or lost on the platform after the main training sample stops broadcasting. Based on live broadcast data of the anchor training sample and behavior data of the user training sample, the established initial model can be trained, and based on comparison between a sample label output by the model and a lost label of the user, the initial model is adjusted, and finally a discrimination model meeting conditions is obtained. The discriminant model can be used for determining whether a corresponding user runs off from the platform after a certain anchor is stopped.
On the basis, in order to convert the contribution value of the anchor to the platform into a quantifiable anchor broadcasting core index, the anchor sample and the user sample are collected, and whether the user sample runs off from the platform after the anchor sample stops broadcasting is judged by using a discrimination model based on the behavior data of the user sample. And if the user sample runs off from the platform, acquiring the access condition of the user sample to the platform within a period of history as the long-time loss of the platform.
And fitting the index coefficients of the anchor characteristic indexes based on the obtained platform duration, the live broadcast data of the anchor sample and the behavior data of the user sample. Therefore, an evaluation model containing a plurality of anchor characteristic indexes can be successfully established.
In the formal evaluation stage, for the anchor to be evaluated, index values of the anchor characteristic indexes in the evaluation model can be obtained based on the live broadcast data of the anchor to be evaluated and the behavior data of the user corresponding to the live broadcast data. And then, obtaining the evaluation value of the anchor to be evaluated by using the evaluation model.
On the basis, the rationality judgment can be carried out on the preset positioning value of the anchor to be evaluated by utilizing the evaluation value of the anchor to be evaluated and the evaluation values of other anchors on the platform. In this step, the regional information of the anchor can be taken into account to determine whether the local anchor is in the same market environment and the anchor's location value is reasonable.
Referring to fig. 10, a schematic diagram of exemplary components of an electronic device according to an embodiment of the present application is provided, where the electronic device may be the live broadcast server 200 shown in fig. 1. The electronic device may include a storage medium 110, a processor 120, a anchorperson value evaluation device 130, and a communication interface 140. In this embodiment, the storage medium 110 and the processor 120 are both located in the electronic device and are separately disposed. However, it should be understood that the storage medium 110 may be separate from the electronic device and may be accessed by the processor 120 through a bus interface. Alternatively, the storage medium 110 may be integrated into the processor 120, for example, may be a cache and/or general purpose registers.
The anchor value evaluation device 130 may be understood as the electronic device, or the processor 120 of the electronic device, or may be understood as a software functional module that is independent of the electronic device or the processor 120 and implements the anchor value evaluation method under the control of the electronic device.
As shown in fig. 11, the anchor value evaluation device 130 may include a data acquisition module 131, an index value acquisition module 132, and an evaluation module 133. The functions of the respective functional modules of the anchor value evaluation device 130 are explained in detail below.
And the data acquisition module 131 is configured to acquire live data of the anchor to be evaluated and behavior data of the user.
It is understood that the data obtaining module 131 can be used to execute the step S210, and for the detailed implementation of the data obtaining module 131, reference can be made to the contents related to the step S210.
An index value obtaining module 132, configured to obtain, according to the live data and the behavior data, an index value corresponding to each anchor characteristic index in a plurality of anchor characteristic indexes established in advance.
It is understood that the metric value obtaining module 132 can be used to execute the above step S220, and for the detailed implementation of the metric value obtaining module 132, reference can be made to the above contents related to the step S220.
The evaluation module 133 is configured to obtain an evaluation value of the anchor to be evaluated according to the obtained multiple index values and a pre-established evaluation model, where the evaluation model is formed by the multiple anchor characteristic indexes.
It is understood that the evaluation module 133 can be used to execute the step S210, and for the detailed implementation of the evaluation module 133, reference can be made to the above-mentioned contents related to the step S210.
The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.
Further, an embodiment of the present application also provides a computer-readable storage medium, where machine-executable instructions are stored in the computer-readable storage medium, and when the machine-executable instructions are executed, the anchor value assessment method provided by the foregoing embodiment is implemented.
In particular, the computer readable storage medium can be a general storage medium, such as a removable disk, a hard disk, etc., and the computer program on the computer readable storage medium can be executed to execute the above-mentioned anchor value evaluation method when the computer program is executed. With regard to the processes involved when the executable instructions in the computer-readable storage medium are executed, reference may be made to the related descriptions in the above method embodiments, which are not described in detail herein.
To sum up, the embodiments of the present application provide a anchor value evaluation method, apparatus, electronic device, and readable storage medium, where, for an anchor to be evaluated, live broadcast data of the anchor and behavior data of a user are obtained, and according to the live broadcast data and the behavior data, index values corresponding to anchor characteristic indexes in a plurality of anchor characteristic indexes established in advance are obtained. And obtaining an evaluation value of the anchor to be evaluated according to the obtained multiple index values and a pre-established evaluation model consisting of multiple anchor characteristic indexes. Therefore, based on the pre-established evaluation model containing a plurality of anchor characteristic indexes, the anchor data of the anchor and the behavior data of the user are combined, the evaluation of the anchor value is realized, and the accuracy of the evaluation result is improved. Therefore, the purpose of reducing the evaluation times and reducing the occupation of the computing resources of the equipment is achieved.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (14)
1. A method for anchor value assessment, the method comprising:
acquiring live broadcast data of a anchor to be evaluated and behavior data of a user;
according to the live broadcast data and the behavior data, obtaining index values corresponding to all anchor characteristic indexes in a plurality of anchor characteristic indexes established in advance;
and obtaining the evaluation value of the anchor to be evaluated according to the obtained index values and a pre-established evaluation model, wherein the evaluation model is composed of the plurality of anchor characteristic indexes.
2. The anchor value evaluation method according to claim 1, wherein each of the anchor feature indicators in the evaluation model has a corresponding indicator coefficient, the method further comprising a step of pre-establishing the evaluation model, the step comprising:
acquiring a plurality of anchor samples, live broadcast data of each anchor sample and behavior data of a corresponding user sample;
fitting index coefficients corresponding to the anchor characteristic indexes according to live broadcast data of the anchor samples and behavior data of the user samples to obtain corresponding coefficient values;
and establishing the evaluation model based on each anchor characteristic index and the coefficient value of the corresponding index coefficient.
3. The anchor value evaluation method according to claim 2, wherein the step of fitting the index coefficients corresponding to each anchor feature index according to the live broadcast data of the anchor sample and the behavior data of the user sample to obtain corresponding coefficient values comprises:
obtaining platform time length loss according to the behavior data of the user samples, wherein the platform time length loss represents the reduction of platform access time length caused by the loss of the corresponding user samples after the broadcasting of the anchor samples is stopped;
obtaining an index value of each anchor characteristic index according to the live broadcast data of the anchor sample;
and fitting the index coefficients corresponding to the anchor characteristic indexes according to the index values and the platform time length loss to obtain corresponding coefficient values.
4. The anchor value assessment method of claim 3, wherein said step of deriving a platform duration loss from said user sample behavior data comprises:
obtaining a characteristic value of each user characteristic in a plurality of pre-established user characteristics according to the behavior data of the user sample;
importing the obtained multiple characteristic values into a pre-established discrimination model to obtain a discrimination result, wherein the discrimination result represents whether the user sample runs off from the platform after the main broadcast sample stops broadcasting;
and when the judgment result shows that the user sample is lost from the platform, acquiring the access time of the user sample to the platform in a historical preset time period as the time loss of the platform.
5. The anchor value assessment method according to claim 4, further comprising the step of pre-establishing said discriminant model, comprising:
acquiring anchor training samples and user training samples corresponding to the anchor training samples, wherein the anchor training samples are anchors which are stopped on the platform, behavior data of the user training samples comprise stay tags, and the stay tags represent that the user training samples are retained or lost on the platform after the anchor training samples are stopped;
and training according to the behavior data of the user training sample to obtain a discriminant model.
6. The anchor value assessment method according to claim 5, wherein said step of training to obtain a discriminant model according to the behavior data of the user training samples comprises:
training the constructed initial model according to the behavior data of the user training sample, and outputting a sample label of the user training sample;
comparing the retention label and the sample label of the user training sample, adjusting the parameters of the initial model and then continuing training, and obtaining the discrimination model when the preset stop condition is met.
7. The anchor value assessment method of claim 1, further comprising:
obtaining a positioning evaluation value of the anchor to be evaluated according to the evaluation value of the anchor to be evaluated and a positioning value preset for the anchor to be evaluated;
obtaining a positioning evaluation mean value of the anchor on the platform according to the evaluation values of all the anchors on the platform and the positioning values preset for all the anchors;
and judging whether the positioning value of the anchor to be evaluated is reasonable or not according to the positioning evaluation value of the anchor to be evaluated and the positioning evaluation mean value of the anchor on the platform.
8. The anchor value evaluation method according to claim 7, wherein the step of obtaining a mean value of the positioning evaluations of the anchors on the platform based on the evaluation values of all the anchors on the platform and the positioning values preset for each of the anchors comprises:
acquiring area information in the attribute information of the anchor to be evaluated;
screening the anchor which has the same area information as the anchor to be evaluated on the platform;
and obtaining a positioning evaluation mean value of the anchor on the platform according to the screened evaluation values of the anchor and positioning values preset for each screened anchor.
9. The anchor value evaluation method according to claim 7, wherein the step of judging whether the location value of the anchor to be evaluated is reasonable or not according to the location evaluation value of the anchor to be evaluated and the location evaluation mean value of the anchor on the platform includes:
and if the positioning evaluation value of the anchor to be evaluated is smaller than or equal to the positioning evaluation mean value of the anchor on the platform, judging that the positioning value set by the anchor to be evaluated is reasonable, otherwise, judging that the positioning value set by the anchor to be evaluated is unreasonable.
10. The anchor value evaluation method of claim 1, wherein the anchor characteristic indicators comprise at least two or more combinations of anchor core user information, anchor broadcasting duration, anchor user access duration, anchor broadcasting average online population per unit time, anchor broadcasting maximum online population per unit time, and anchor acquired virtual gift information.
11. The anchor value evaluation method according to claim 4, wherein the user characteristics include at least a combination of two or more of a user's viewing duration of the target anchor, a user's average daily viewing duration of the target anchor, a user's subscription information to the target anchor, and a user's subscription information to other users on the platform.
12. An anchor value evaluation apparatus, the apparatus comprising:
the data acquisition module is used for acquiring live broadcast data of the anchor to be evaluated and behavior data of a user;
an index value obtaining module, configured to obtain, according to the live data and the behavior data, an index value corresponding to each anchor characteristic index in a plurality of anchor characteristic indexes established in advance;
and the evaluation module is used for obtaining the evaluation value of the anchor to be evaluated according to the obtained index values and a pre-established evaluation model, wherein the evaluation model is composed of the plurality of anchor characteristic indexes.
13. An electronic device comprising one or more storage media and one or more processors in communication with the storage media, the one or more storage media storing processor-executable machine-executable instructions that, when executed by the electronic device, are executed by the processor to perform the anchor value assessment method of any one of claims 1-11.
14. A computer-readable storage medium having stored thereon machine-executable instructions that, when executed, implement the anchor value assessment method of any one of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010577138.3A CN111754107A (en) | 2020-06-22 | 2020-06-22 | Anchor value evaluation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010577138.3A CN111754107A (en) | 2020-06-22 | 2020-06-22 | Anchor value evaluation method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111754107A true CN111754107A (en) | 2020-10-09 |
Family
ID=72676433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010577138.3A Pending CN111754107A (en) | 2020-06-22 | 2020-06-22 | Anchor value evaluation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754107A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561268A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | Behavior evaluation method and related equipment |
| CN112580887A (en) * | 2020-12-25 | 2021-03-30 | 百果园技术(新加坡)有限公司 | Weight determination method, device and equipment for multi-target fusion evaluation and storage medium |
| WO2023131326A1 (en) * | 2022-01-07 | 2023-07-13 | 北京有竹居网络技术有限公司 | Live broadcast processing method and apparatus, and electronic device, storage medium and program product |
| CN116502944A (en) * | 2023-04-10 | 2023-07-28 | 好易购家庭购物有限公司 | Live broadcast cargo quality evaluation method based on big data analysis |
-
2020
- 2020-06-22 CN CN202010577138.3A patent/CN111754107A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561268A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | Behavior evaluation method and related equipment |
| CN112561268B (en) * | 2020-12-07 | 2023-12-15 | 深圳市思为软件技术有限公司 | Behavior evaluation method and related equipment |
| CN112580887A (en) * | 2020-12-25 | 2021-03-30 | 百果园技术(新加坡)有限公司 | Weight determination method, device and equipment for multi-target fusion evaluation and storage medium |
| CN112580887B (en) * | 2020-12-25 | 2023-12-01 | 百果园技术(新加坡)有限公司 | Weight determination method, device, equipment and storage medium for multi-target fusion evaluation |
| WO2023131326A1 (en) * | 2022-01-07 | 2023-07-13 | 北京有竹居网络技术有限公司 | Live broadcast processing method and apparatus, and electronic device, storage medium and program product |
| CN116502944A (en) * | 2023-04-10 | 2023-07-28 | 好易购家庭购物有限公司 | Live broadcast cargo quality evaluation method based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111754107A (en) | Anchor value evaluation method and device, electronic equipment and readable storage medium | |
| CN108337563B (en) | Video evaluation method, device, equipment and storage medium | |
| Lin et al. | Identifying the determinants of broadband adoption by diffusion stage in OECD countries | |
| CN104205158B (en) | Measure the system, method and product of online spectators | |
| CN110475155B (en) | Live video hot state identification method, device, equipment and readable medium | |
| CN109033408B (en) | Information pushing method and device, computer readable storage medium and electronic equipment | |
| CN105163142B (en) | A kind of user preference determines method, video recommendation method and system | |
| CN109768888B (en) | Network service quality evaluation method, device, equipment and readable storage medium | |
| Kang et al. | Eva: An explainable visual aesthetics dataset | |
| Lee | On designing paired comparison experiments for subjective multimedia quality assessment | |
| Menkovski et al. | Adaptive psychometric scaling for video quality assessment | |
| CN111522724B (en) | Method and device for determining abnormal account number, server and storage medium | |
| TW201735654A (en) | Multimedia resource quality assessment method and apparatus | |
| CN113099475A (en) | Network quality detection method and device, electronic equipment and readable storage medium | |
| CN112702631A (en) | Operation management system and method for network training | |
| CN103609069B (en) | Subscriber terminal equipment, server apparatus, system and method for assessing media data quality | |
| CN114245185B (en) | Video recommendation method, model training method, device, electronic equipment and medium | |
| CN110121088B (en) | User attribute information determination method and device and electronic equipment | |
| CN109688217B (en) | Message pushing method and device and electronic equipment | |
| CN112215509A (en) | Resource parameter determination method, device and equipment | |
| CN115909166A (en) | Video evaluation method and device, electronic equipment and storage medium | |
| JPWO2021048902A1 (en) | Learning model application system, learning model application method, and program | |
| US10674045B2 (en) | Mutual noise estimation for videos | |
| CN111107439B (en) | Content distribution method, content distribution device, server and storage medium | |
| CN111143688B (en) | Evaluation method and system based on mobile news client |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |