CN114819747A - Message traffic quality evaluation method, electronic device, medium, and program product - Google Patents

Message traffic quality evaluation method, electronic device, medium, and program product Download PDF

Info

Publication number
CN114819747A
CN114819747A CN202210627672.XA CN202210627672A CN114819747A CN 114819747 A CN114819747 A CN 114819747A CN 202210627672 A CN202210627672 A CN 202210627672A CN 114819747 A CN114819747 A CN 114819747A
Authority
CN
China
Prior art keywords
conversion
user
link
node
traffic
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
Application number
CN202210627672.XA
Other languages
Chinese (zh)
Inventor
郑楚涛
罗夏雨
张晓军
邹少馨
郑文琛
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.)
WeBank Co Ltd
Original Assignee
WeBank 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 WeBank Co Ltd filed Critical WeBank Co Ltd
Priority to CN202210627672.XA priority Critical patent/CN114819747A/en
Publication of CN114819747A publication Critical patent/CN114819747A/en
Pending legal-status Critical Current

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
    • G06Q10/06395—Quality analysis or management
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06—Asset management; Financial planning or analysis

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Educational Administration (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Technology Law (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a message traffic quality evaluation method, an electronic device, a medium, and a program product, the message traffic quality evaluation method including: acquiring user traffic data corresponding to a target conversion node in a user conversion link, and determining a traffic quality prediction model corresponding to the target conversion node, wherein the traffic quality prediction model is obtained by optimizing based on a link conversion degree label; and evaluating the user traffic quality of the target conversion node according to the user traffic data and the traffic quality prediction model to obtain a traffic quality evaluation result. The method and the device solve the technical problem that in the prior art, the evaluation accuracy of the flow quality of the single node in the user conversion link is low.

Description

Message traffic quality evaluation method, electronic device, medium, and program product
Technical Field
The present application relates to the field of artificial intelligence technology for financial technology (Fintech), and in particular, to a method, an electronic device, a medium, and a program product for evaluating message traffic quality.
Background
With the continuous development of financial science and technology, especially internet science and technology, more and more technologies (such as distributed technology, artificial intelligence and the like) are applied to the financial field, but the financial industry also puts higher requirements on the technologies, for example, higher requirements on the distribution of backlog in the financial industry are also put forward.
With the continuous development of artificial intelligence, the application of artificial intelligence is more and more extensive, and currently in the field of message recommendation, the quality of user traffic of a current user Conversion node is generally evaluated Through indexes of the current user Conversion node, such as an exposure Click Rate (CTR) and a Click Conversion Rate (CVR), and the higher the CTR and the CVR, the higher the single node retention in the user Conversion link is, the better the traffic quality is, but a single index may attract a large number of clicks relatively to a flat, for example, some popular or odd advertisements, although the retention of the Click node in the user Conversion link may be higher, the actual user Conversion effect may be poor for the whole user Conversion link, and therefore, the accuracy of evaluating the traffic quality of the single node in the user Conversion link is currently low.
Disclosure of Invention
The present application mainly aims to provide a method, an electronic device, a medium, and a program product for evaluating message traffic quality, and aims to solve the technical problem in the prior art that the evaluation accuracy of single-node traffic quality in a user conversion link is low.
In order to achieve the above object, the present application provides a method for evaluating message traffic quality, where the method for evaluating message traffic quality includes:
acquiring user traffic data corresponding to a target conversion node in a user conversion link, and determining a traffic quality prediction model corresponding to the target conversion node, wherein the traffic quality prediction model is obtained by optimizing based on a link conversion degree label;
and evaluating the user traffic quality of the target conversion node according to the user traffic data and the traffic quality prediction model to obtain a traffic quality evaluation result.
The present application further provides a message traffic quality assessment apparatus, the apparatus is a virtual apparatus, the message traffic quality assessment apparatus includes:
the system comprises an acquisition module, a traffic quality prediction module and a traffic quality prediction module, wherein the acquisition module is used for acquiring user traffic data corresponding to a target conversion node in a user conversion link and determining a traffic quality prediction model corresponding to the target conversion node, and the traffic quality prediction model is obtained by optimizing the traffic quality prediction model based on a link conversion degree label;
and the flow quality prediction module is used for evaluating the user flow quality of the target conversion node according to the user flow data and the flow quality prediction model to obtain a flow quality evaluation result.
The present application further provides an electronic device, the electronic device including: a memory, a processor and a program of the message traffic quality assessment method stored on the memory and executable on the processor, which program, when executed by the processor, may implement the steps of the message traffic quality assessment method as described above.
The present application also provides a computer-readable storage medium having stored thereon a program for implementing a message traffic quality assessment method, which when executed by a processor implements the steps of the message traffic quality assessment method as described above.
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the message traffic quality assessment method as described above.
Compared with the technical means of evaluating the quality of the user traffic of a current user conversion node through the index of the current user conversion node adopted in the prior art, the method comprises the steps of firstly obtaining user traffic data corresponding to a target conversion node in a user conversion link and determining a traffic quality prediction model corresponding to the target conversion node; evaluating the user traffic quality of the target conversion node according to the user traffic data and the traffic quality prediction model to obtain a traffic quality evaluation result, wherein the traffic quality prediction model is obtained by optimizing based on a link conversion degree label, so that the purpose of evaluating the traffic quality of a single node in a user conversion link by taking a rear-end index of the user conversion link as a scale is achieved, and the rear-end index is associated with the whole user conversion link instead of only being associated with the single node, so that the traffic quality prediction model optimized according to the rear-end index can comprehensively evaluate the conversion effect of the user traffic of the single node relative to the whole user conversion link, and the existing single index is relatively simple, although the retention of the single node in the user conversion link is higher, the actual user conversion effect is poor for the whole user conversion link, therefore, the technical defect that the accuracy of single-node flow quality evaluation in the user conversion link is low at present is overcome, and the accuracy of the single-node flow quality evaluation in the user conversion link is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a first embodiment of a message traffic quality assessment method according to the present application;
fig. 2 is a schematic flow chart of a second embodiment of the message traffic quality assessment method according to the present application;
fig. 3 is a schematic device structure diagram of a hardware operating environment related to a message traffic quality evaluation method in an embodiment of the present application.
The objectives, features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments of the present application are described in detail below with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. 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 application.
Example one
In a first embodiment of the message traffic quality assessment method according to the present application, referring to fig. 1, the message traffic quality assessment method includes:
step S10, obtaining user traffic data corresponding to a target conversion node in a user conversion link, and determining a traffic quality prediction model corresponding to the target conversion node, wherein the traffic quality prediction model is obtained by optimizing based on a link conversion degree label;
and step S20, evaluating the user traffic quality of the target conversion node according to the user traffic data and the traffic quality prediction model to obtain a traffic quality evaluation result.
In this embodiment, the message may be an advertisement, the user conversion link is a whole process from an exposure node that starts to expose the message to the user to completion of user conversion, the user conversion link may have a plurality of conversion nodes, loss and retention of the user may exist in each conversion node, and the retained user may continue to flow to the next conversion node until conversion on the user conversion link is completed or lost. The link conversion degree label is a label which is used for representing the conversion degree of the user relative to the whole user conversion link. In one implementable manner, the user traffic data may be user portrait data.
As an example, in the financial loan field, the user conversion link may be "expose-click-reserve-enter-credit (credit) -withdraw", in which a message may be first exposed to the user, the user may select to click or not click the message, if the user clicks the message, the user may select to perform enterprise authentication, leave enterprise user data (reserve), if the user performs enterprise authentication, the user may select to register an account, after the account is successfully registered, the loan amount is optionally approved, and after the loan amount is approved, the loan may be selected to be extracted, thereby completing the normal amount loan process.
As one example, steps S10 to S20 include: determining a target conversion node in a user conversion link, and acquiring user traffic data corresponding to a user to be predicted, which enters the target conversion node; determining a flow quality prediction model corresponding to a target conversion node in a preset model set according to a node identification corresponding to the target user node, wherein the preset model set at least comprises a flow quality prediction model corresponding to the conversion node in a user conversion link, the flow quality prediction model corresponds to the conversion node one by one, the flow quality prediction model is obtained by performing iterative optimization according to flow data of a historical user entering the corresponding conversion node and a link conversion degree label corresponding to the historical user, and different conversion nodes can be subjected to iterative optimization to obtain different flow quality prediction models; inputting the user traffic data into the traffic quality prediction model, and performing traffic quality scoring on the user traffic data to obtain a traffic quality scoring value; and determining the flow quality evaluation result according to the flow quality score value.
As an example, the step of determining the traffic quality assessment result according to a traffic quality score value comprises:
and determining a corresponding flow quality label according to the flow quality scoring value, and taking the flow quality label as the flow quality evaluation result. For example, if the flow quality score is set to be greater than 80 points, the corresponding flow quality label is determined to be 1, the flow quality is identified as the head flow, the flow quality score is set to be not greater than 80 points and not less than 50 points, the flow quality label is set to be 0.5, the flow quality is identified as the middle flow, the flow quality score is set to be less than 50 points, the flow quality label is set to be 0, and the flow quality is identified as the tail flow. The flow quality label is an identifier representing the quality of user flow data, and the flow quality label can be used for segmenting user flow, so that different message pushing strategies can be adopted for message pushing according to different user flows.
As an example, the step of determining the traffic quality assessment result according to a traffic quality score value comprises:
acquiring different flow quality score values corresponding to target conversion nodes in a preset time period; and according to the flow quality grading values, carrying out flow segmentation on the user flow data entering the target conversion node in the time dimension to obtain a flow quality evaluation result corresponding to the target conversion node.
The obtaining of the user traffic data corresponding to the target conversion node in the user conversion link includes:
step S11, user portrait characteristics and node user conversion time corresponding to each conversion node before the target conversion node are obtained;
step S12, generating the user feature data according to the node user transformation time feature and the user portrait feature constructed by each user transformation time.
In this embodiment, it should be noted that, when evaluating the quality of the user traffic, for a user with a relatively strong willingness to convert, the user usually has a relatively strong willingness to complete the user conversion process corresponding to the whole user conversion link, so that the user traffic corresponding to the user is usually relatively good, so the willingness to convert is an important factor for evaluating the user traffic, and the willingness to convert can be reflected from the side by the conversion time consumed by the user at each conversion node. The user portrait characteristic can be a characteristic vector generated according to the user portrait and is composed of at least one user portrait characteristic value, for an individual user, the user portrait characteristic value can be characteristic information such as age, hobby type and gender, and for an enterprise user, the user portrait characteristic value can be characteristic information such as enterprise scale, enterprise region and enterprise industry type.
As one example, steps S11 to S12 include: acquiring user portrait characteristics and node user conversion time corresponding to each conversion node before the target conversion node; splicing the conversion time of each node user into a feature vector to obtain the conversion time feature of the node user, for example, the conversion time of each node user can be spliced into the feature vector according to the arrangement position of the corresponding conversion node; and splicing the user portrait characteristics and the node user conversion time characteristics to obtain user characteristic data.
According to the embodiment of the application, the user characteristic data is constructed according to the conversion consumption time distribution condition of the user on the whole user conversion link and the basic portrait information of the user, so that the conversion intention information related to the whole user conversion link is carried in the user characteristic data, more decision-making bases are provided for flow quality evaluation of flow information entering a single node on the basis of the whole user conversion link, and the accuracy of the flow quality evaluation can be improved.
Wherein, the generating the user characteristic data according to the user portrait characteristic and the node user transformation time characteristic comprises:
step S121, acquiring flow channel information corresponding to each conversion node before the target conversion node and corresponding message product forms;
step S122, constructing flow channel characteristics according to the information of each flow channel, and constructing message product form characteristics according to the form of each message product;
and S123, splicing the user portrait characteristics, the node user conversion time characteristics, the traffic channel characteristics and the message product form characteristics to obtain the user characteristic data.
In this embodiment, as for the influencing factors of the conversion will, in addition to the conversion time consumed by the user at each conversion node, the traffic channel and the message product form of each conversion node also generally influence the conversion will of the user, for example, for a bank loan, compared with a user who enters a conversion node by video recommendation pop-up, a user who enters a conversion node from a bank APP would be more willing to complete the user conversion process of the whole user conversion link, so that the conversion will of the user can be reflected from the side by collecting the traffic channel information and the change condition of the traffic channel information of each conversion node; different users have different acceptance degrees for different product forms, some users are willing to accept text type messages, and some users are willing to accept video type messages, so that the product form of the messages can also influence the conversion willingness of the users for the whole user conversion link. The traffic channel information may be a traffic channel type tag characterizing a traffic channel.
As an example, steps S121 to S123 include: determining flow channels and message product forms when a user enters each conversion node before entering a target conversion node, and acquiring flow channel type labels corresponding to the flow channels and message product form type labels corresponding to the message product forms; splicing the flow channel type labels corresponding to the conversion nodes into a feature vector to obtain flow channel features; splicing the message product form type labels corresponding to the conversion nodes into feature vectors to obtain message product form features; and splicing the user portrait characteristics, the node user conversion time characteristics, the flow channel characteristics and the message product form characteristics to obtain the user characteristic data.
According to the embodiment of the application, the user characteristic data is constructed by combining the information channel information and the information product form on the basis of the conversion consumption time distribution condition of the whole user conversion link and the user basic portrait information, so that more conversion intention information related to the whole user conversion link is carried in the user characteristic data, more decision bases are provided for flow quality evaluation of flow information entering a single node on the basis of the whole user conversion link, and therefore the accuracy of the flow quality evaluation can be improved.
As an example, the user traffic data at least includes one user characteristic data, and the obtaining user traffic data corresponding to a target conversion node in the user conversion link further includes:
acquiring flow channel information corresponding to each conversion node before the target conversion node and corresponding message product forms; constructing flow channel characteristics according to the information of each flow channel, and constructing message product form characteristics according to the form of each message product; and splicing the user portrait characteristics, the flow channel characteristics and the message product form characteristics to obtain the user characteristic data. The specific implementation of the construction of the traffic channel characteristics and the message product morphological characteristics may refer to the contents of steps S121 to S123, and will not be described herein again.
According to the embodiment of the application, the user characteristic data is constructed according to the traffic channel information and the message product form of each conversion node of the whole user conversion link and the basic portrait information of the user, so that the conversion intention information related to the whole user conversion link is carried in the user characteristic data, more decision bases are provided for the traffic quality evaluation of the traffic information entering a single node on the basis of the whole user conversion link, and the accuracy of the traffic quality evaluation can be improved.
Before the step of determining the traffic quality prediction model corresponding to the target conversion node, the message traffic quality assessment method further includes:
a10, acquiring a traffic quality prediction model to be trained and historical user characteristic data corresponding to a historical user;
step A20, according to the conversion intention association information of the historical user on the user conversion link, performing label calibration on the historical user characteristic data to obtain the link conversion degree label;
step A30, determining a real traffic quality label corresponding to the historical user characteristic data according to the link conversion degree label;
step A40, performing iterative training and updating on the traffic quality prediction model to be trained according to the real traffic quality label and the historical user characteristic data to obtain the traffic quality prediction model.
In this embodiment, it should be noted that a traffic quality prediction model is correspondingly arranged in each user transformation node on the user transformation link, and is used for predicting the traffic quality of the user traffic entering the corresponding transformation node on the user transformation link. The link conversion degree label is a label which characterizes the conversion degree of the user relative to the whole user conversion link, may be determined by one or more of the user's willingness to convert the link and conversion qualification, the conversion qualification is the adaptation qualification for representing the business process corresponding to the user conversion link, the better the conversion qualification, the better the traffic quality corresponding to the user, the conversion qualification being determined by the conversion qualification correlation data, for example, assuming that the user conversion process corresponding to the user conversion link is a loan process, the conversion qualification related data can be the deposit amount of the user, the credit score of the user and the overdue repayment times of the user, therefore, the higher the deposit amount of the user, the higher the credit score of the user and the fewer the overdue repayment times of the user, the more the user is adapted to the business process corresponding to the user conversion link, and the better the conversion quality is. The conversion intention related information is data related to a conversion intention of a user for user conversion through a user conversion link, and may be one or more of time consumed by the user on the user conversion link, conversion depth of the user on the user conversion link, and feature information of the user, where for an enterprise user, the feature information of the user may be information of an industry type where the enterprise is located, or a region where the enterprise is located. The historical user characteristic data can be user characteristic data of historical users, and can be one or more of user portrait characteristics, node user conversion time characteristics, flow channel characteristics and message product form characteristics.
As an example, the steps a10 to a40 include: acquiring a traffic quality prediction model to be trained and historical user characteristic data generated when a historical user enters each conversion node; according to the conversion intention related information of the historical user on the user conversion link, performing label calibration on historical user characteristic data to obtain a link conversion degree label; and respectively carrying out iterative training optimization on the flow quality prediction model to be trained according to the historical user characteristic data corresponding to each conversion node and the real flow quality label determined by the link conversion degree label to obtain the flow quality prediction model to be trained corresponding to each conversion node. It should be noted that, because there are differences in the number of conversion nodes that a historical user passes before entering each conversion node of a user conversion link, there are differences in the node user conversion time characteristics, the traffic channel characteristics, and the message product morphological characteristics, there may be differences in the historical user characteristic data corresponding to each conversion node, but the historical user characteristic data corresponding to each conversion node may correspond to a same link conversion degree label, so that a traffic quality prediction model corresponding to each conversion node is obtained through iterative training.
The step of performing iterative training and updating on the to-be-trained traffic quality prediction model according to the real traffic quality label and the historical user characteristic data to obtain the traffic quality prediction model comprises the following steps:
inputting historical user characteristic data corresponding to the conversion node into a to-be-trained flow quality prediction model, and evaluating the flow quality of the historical user characteristic data at the conversion node to obtain a training output flow quality label; determining a real flow quality label corresponding to the historical user characteristic data according to the link conversion degree label; calculating model loss corresponding to the to-be-trained flow quality prediction model according to the difference between the training output flow quality label and the real flow quality label; judging whether the model loss is converged, if so, taking the to-be-trained flow quality prediction model as the flow quality prediction model, if not, updating the to-be-trained flow quality prediction model according to the model gradient calculated by the model loss, and returning to the execution step: and acquiring historical user characteristic data corresponding to the historical users until the calculated model loss is converged.
Wherein, the step of determining the real traffic quality label corresponding to the historical user characteristic data according to the link conversion degree label comprises:
step A31, determining a traffic category corresponding to the historical user characteristic data according to the value size of the link conversion degree label and a preset conversion degree range;
step A32, assigning a real traffic quality label corresponding to the traffic category to the historical user characteristic data.
As an example, step a31 through step a32 include: if the value of the link conversion degree label is larger than the upper limit value of the preset conversion degree range, judging that the traffic class corresponding to the historical user characteristic data is a first traffic class, and endowing the historical user characteristic data with a head traffic label corresponding to the first traffic class as a real traffic quality label; if the value of the link conversion degree label is not smaller than the lower limit value of the preset conversion degree range and not larger than the upper limit value of the preset conversion degree range, judging that the traffic class corresponding to the historical user characteristic data is a second traffic class, and giving the intermediate traffic label corresponding to the second traffic class to the historical user characteristic data as a real traffic quality label; and if the value of the link conversion degree label is smaller than the lower limit value of the preset conversion degree range, judging that the flow category corresponding to the historical user characteristic data is a third flow category, and endowing the tail flow label corresponding to the third flow category to the historical user characteristic data as a real flow quality label. For example, assuming that the preset conversion degree range is 0.4 to 0.8, it may be set that when the value of the link conversion degree tag is greater than 0.8, the historical user characteristic data belongs to the first traffic class, so that the head traffic tag a is used as a real traffic quality tag corresponding to the historical user characteristic data, and the historical user characteristic data is identified as the head traffic; setting that when the value of the link conversion degree label is not more than 0.8 and not less than 0.4, the historical user characteristic data belongs to a second traffic class, so that an intermediate traffic label b is used as a real traffic quality label corresponding to the historical user characteristic data to identify the historical user characteristic data as intermediate traffic; and when the value of the link conversion degree label is less than 0.4, the historical user characteristic data belongs to a third flow category, so that a tail flow label c is used as a real flow quality label corresponding to the historical user characteristic data to identify the historical user characteristic data as tail flow.
Compared with the technical means of evaluating the quality of the user traffic of a current user conversion node through indexes of the current user conversion node in the prior art, the method for evaluating the quality of the user traffic of the current user conversion node comprises the steps of firstly obtaining user traffic data corresponding to a target conversion node in a user conversion link and determining a traffic quality prediction model corresponding to the target conversion node; evaluating the user traffic quality of the target conversion node according to the user traffic data and the traffic quality prediction model to obtain a traffic quality evaluation result, wherein the traffic quality prediction model is obtained by optimizing based on a link conversion degree label, so that the purpose of evaluating the traffic quality of a single node in a user conversion link by taking a rear-end index of the user conversion link as a scale is achieved, and the rear-end index is associated with the whole user conversion link instead of only being associated with the single node, so that the traffic quality prediction model optimized according to the rear-end index can comprehensively evaluate the conversion effect of the user traffic of the single node relative to the whole user conversion link, and the existing single index is relatively simple, although the retention of the single node in the user conversion link is higher, the actual user conversion effect is poor for the whole user conversion link, therefore, the technical defect that the accuracy of single-node flow quality evaluation in the user conversion link is low at present is overcome, and the accuracy of the single-node flow quality evaluation in the user conversion link is improved.
Example two
Further, referring to fig. 2, based on the first embodiment, in another embodiment of the message traffic quality assessment method of the present application, the conversion intention association information includes information of conversion depth and conversion consumption time of the historical user on the user conversion link, and the step of performing label calibration on the historical user characteristic data according to the conversion intention association information of the historical user on the user conversion link to obtain the link conversion degree label includes:
step A21, evaluating the conversion will of the historical user on the user conversion link according to the conversion depth and the conversion consumption time information to obtain a conversion will score;
step A22, according to the conversion will score, label calibration is carried out on the historical user characteristic data, and the link conversion degree label is obtained.
In this embodiment, it should be noted that the conversion depth is a depth of a final arrival node of a user on a user conversion link on the user conversion link, for example, assuming that there are 6 conversion nodes in the user conversion link, if the final arrival node of the user on the user conversion link is a 5 th node, the conversion depth may be set to 5, if the user completes a conversion process of the entire user conversion link, the conversion depth may be set to 10, and the specific identification is performed by increasing a weight value of the conversion depth, where in a case that information of other users is the same, the conversion will of the user is considered to be stronger as the conversion depth is deeper. The conversion consumption time information may be the total time spent by the user on the conversion link, may also be distribution information of the conversion time spent by the user on each conversion node, or may also be a combination of the two, which is not limited herein.
As an example, the steps a21 to a22 include: splicing the conversion depth and the conversion consumption time information to obtain a conversion wish representation characteristic; inputting the conversion intention characterization feature into a preset conversion intention grading model for grading, and evaluating the conversion intention of the historical user on the user conversion link to obtain a conversion intention grade, wherein the conversion intention grade is used for characterizing the strength of the intention of the user for completing the user conversion through the user conversion link; and according to the conversion wish score, performing label calibration on the historical user characteristic data to obtain the link conversion degree label.
According to the method and the device, the purpose of label calibration on historical user characteristic data is achieved according to conversion depth and conversion consumption time information associated with the whole user conversion link, so that the link conversion degree label is strongly related to the whole user conversion link, the correspondingly constructed flow quality prediction model is strongly related to the whole user conversion link, the prediction result of the flow quality prediction model is strongly related to the whole user conversion link, and therefore the accuracy of single-node flow quality prediction can be improved.
As an example, the tag calibration of the historical user characteristic data according to the conversion willingness score to obtain the link conversion degree tag includes:
normalizing the conversion wish score to a preset value range to obtain a normalized score, and taking the normalized score as the link conversion degree label; and/or
And determining a preset target value size range in which the value size of the conversion will score is located, and searching an index label corresponding to the preset target value size range as the link conversion degree label according to the corresponding relation between the preset value size range and the index label.
As an example, the conversion consumption time information may be a conversion consumption time feature, for example, a conversion consumption time feature vector, and the splicing the conversion depth and the conversion consumption time information to obtain a conversion intention characterizing feature includes:
acquiring node consumption time of each conversion node passed by a historical user in a user conversion link; constructing a conversion consumption time characteristic according to the consumption time of each node; and splicing the conversion depth and the conversion consumption time characteristic to obtain a conversion intention characteristic.
As an example, the constructing of the conversion consumption time feature according to the consumption time of each node includes:
splicing the consumption time of each node into a feature vector to obtain a conversion consumption time feature; and/or
And calculating the sum of the consumption time of each node to obtain the total consumption time corresponding to the user conversion link, and splicing the consumption time of each node and the total consumption time into a feature vector to obtain the conversion consumption time feature.
The historical users comprise enterprise users, and the step of evaluating conversion willingness of the historical users on the user conversion links according to the conversion depth and the conversion consumption time information to obtain conversion willingness scores comprises the following steps:
step A211, acquiring an industry type and corresponding region information corresponding to the enterprise user;
step A212, evaluating the conversion will of the historical user on the user conversion link according to the industry type, the region information, the conversion depth and the conversion consumption time information, and obtaining the conversion will score.
In this embodiment, it should be noted that the region information may be a geographic position coordinate, or may be a specific place name, which is not limited herein. For enterprise users, different industries often have different conversion willingness, for example, loan willingness for emerging industries is obviously higher than that of the traditional industry; the loan will usually be different for enterprises in different regions, for example, the loan will be more wished for enterprises in the first developed city than for enterprises in the second and third cities.
As an example, the steps a211 to a212 include: determining an industry type and corresponding region information corresponding to the enterprise user; acquiring an industry type label corresponding to the industry type, and splicing the industry type label, the region information, the conversion depth and the conversion consumption time information into a feature vector to obtain a conversion wish representation feature; and inputting the conversion intention characterization features into a preset conversion intention grading model for grading, and evaluating the conversion intention of the historical user on the user conversion link to obtain a conversion intention grade.
According to the embodiment of the application, on the basis of the conversion depth and the conversion consumption time information associated with the whole user conversion link, the industry type and the region information of enterprise users are further added for label calibration, so that the link conversion degree label is also associated with the industry type and the region information on the basis of strong correlation with the whole user conversion link, more decision bases are provided for generating a high-accuracy link conversion degree label, the link conversion degree label is more matched with historical user characteristic data, the accuracy of a correspondingly constructed flow quality prediction model is higher, and a foundation is laid for improving the flow quality prediction accuracy of a single node.
As an example, it should be noted that the general conversion willingness of enterprises in different industries at different time periods may also be different, for example, if an industry is in the whole industry stocking period, such as seasonal seafood processing enterprises, etc., the loan willingness may be obviously increased. The step of splicing the industry type label, the region information, the conversion depth and the conversion consumption time information into a feature vector to obtain a conversion intention characterization feature comprises the following steps:
acquiring an industry hot spot time point where the enterprise user is located and an entry time point of a historical user entering a user conversion link; calculating the difference between the entry time point and the industry hot point time point to obtain industry hot point time characteristics; and splicing the industry type label, the region information, the conversion depth, the conversion consumption time information and the industry hotspot time characteristic into a characteristic vector to obtain a conversion wish characteristic. Correspondingly, when the flow quality is predicted, the industry hotspot time characteristics can be collected and added into the user characteristic data, and the flow quality prediction is already carried out. The embodiment of the application adds the conversion intention characterization feature constructed by the industry hotspot time feature together on the basis of the industry type tag, the region information, the conversion depth and the conversion consumption time information, so that the conversion intention characterization feature is more matched with an enterprise user, more decision-making bases are provided for generating a high-accuracy link conversion degree tag, the link conversion degree tag is more matched with historical user feature data of the enterprise user, the accuracy of a corresponding constructed flow quality prediction model is higher, and a foundation is laid for improving the flow quality prediction accuracy of a single node.
The step of performing label calibration on the historical user characteristic data according to the conversion will score to obtain the link conversion degree label comprises the following steps:
step A221, evaluating the conversion qualification corresponding to the historical user according to the historical user characteristic data to obtain a conversion qualification score;
step A222, according to the conversion qualification score and the conversion willingness score, performing label calibration on the historical user characteristic data to obtain the link conversion degree label.
In this embodiment, it should be noted that, when performing label calibration, in addition to the conversion will of the user, the conversion qualification of the user needs to be considered, and the better the conversion qualification is, the better the traffic quality corresponding to the user is.
As an example, the steps a221 to a222 include: acquiring conversion qualification related data in the historical user characteristic data, wherein the conversion qualification related data is data related to the conversion qualification of the user, and for example, if the user conversion process corresponding to the user conversion link is a loan process, the conversion qualification related data can be information such as user deposit amount, user credit score, user overdue repayment times and the like; if the user conversion process corresponding to the user conversion link is a movie recommendation process, the conversion qualification related data may be information such as the frequency of watching movies by the user or the type of movies preferred by the user. The conversion qualification corresponding to the historical user is estimated by inputting the conversion qualification associated data into a preset conversion qualification scoring model, so that a conversion qualification score is obtained; aggregating the conversion qualification scores and the conversion wish scores to obtain comprehensive conversion scores corresponding to the historical users; and according to the comprehensive conversion score, performing label calibration on the historical user characteristic data to obtain the link conversion degree label. According to the method and the device, the purpose of label calibration of the historical user characteristic data of the historical user is achieved according to the conversion willingness and the conversion qualification of the historical user, sufficient decision-making basis is provided for label calibration, the link conversion degree label obtained by label calibration is matched with the historical user characteristic data, the label calibration accuracy is improved, and therefore a foundation is laid for improving the accuracy of flow quality prediction.
As an example, the tag calibration of the historical user feature data according to the comprehensive conversion score to obtain the link conversion degree tag includes:
normalizing the comprehensive conversion score to a preset value range to obtain a normalized score, and taking the normalized score as the link conversion degree label; and/or
And determining a preset target value size range in which the value size of the comprehensive conversion score is located, and searching an index label corresponding to the preset target value size range as the link conversion degree label according to the corresponding relation between the preset value size range and the index label.
The embodiment of the application provides a method for constructing a flow quality prediction model, namely, according to the conversion depth and the conversion consumption time information, evaluating the conversion intention of the historical user on the user conversion link to obtain a conversion intention score; according to the conversion intention grading, label calibration is carried out on the historical user characteristic data to obtain the link conversion degree label, the purpose of constructing an index label which is strongly related to a user conversion link is achieved, instead of constructing an index label which is strongly related to a single node in the user conversion link, iterative training and updating are carried out on the to-be-trained traffic quality prediction model according to the real traffic quality label determined by the link conversion degree label and the historical user characteristic data to obtain the traffic quality prediction model, the adaptability of the traffic quality prediction model and the whole user conversion link can be improved, the traffic quality prediction model is not only adapted to the single node in the user conversion link any more, the single index in the prior art is relatively flat, although the retention of the single node in the user conversion link is higher, for the whole user conversion link, the actual user transformation effect is poor, so that a foundation is laid for overcoming the technical defect that the accuracy of single-node flow quality evaluation in the user transformation link is low at present.
EXAMPLE III
An embodiment of the present application further provides a device for evaluating message traffic quality, where the device for evaluating message traffic quality includes:
the system comprises an acquisition module, a traffic quality prediction module and a traffic quality prediction module, wherein the acquisition module is used for acquiring user traffic data corresponding to a target conversion node in a user conversion link and determining a traffic quality prediction model corresponding to the target conversion node, and the traffic quality prediction model is obtained by optimizing the traffic quality prediction model based on a link conversion degree label;
and the flow quality prediction module is used for evaluating the user flow quality of the target conversion node according to the user flow data and the flow quality prediction model to obtain a flow quality evaluation result.
Optionally, the message traffic quality assessment apparatus is further configured to:
acquiring a traffic quality prediction model to be trained and historical user characteristic data corresponding to a historical user;
according to conversion intention related information of the historical user on the user conversion link, performing label calibration on the historical user characteristic data to obtain a link conversion degree label;
determining a real flow quality label corresponding to the historical user characteristic data according to the link conversion degree label;
and performing iterative training and updating on the to-be-trained flow quality prediction model according to the real flow quality label and the historical user characteristic data to obtain the flow quality prediction model.
Optionally, the conversion intention association information includes conversion depth and conversion consumption time information of the historical user on the user conversion link, and the message traffic quality assessment apparatus is further configured to:
according to the conversion depth and the conversion consumption time information, evaluating the conversion willingness of the historical user on the user conversion link to obtain a conversion willingness score;
and according to the conversion wish score, performing label calibration on the historical user characteristic data to obtain the link conversion degree label.
Optionally, the message traffic quality assessment apparatus is further configured to:
determining the traffic category corresponding to the historical user characteristic data according to the value size of the link conversion degree label and a preset conversion degree range;
and endowing the historical user characteristic data with a real flow quality label corresponding to the flow category.
Optionally, the message traffic quality assessment apparatus is further configured to:
evaluating the conversion qualification corresponding to the historical user according to the historical user characteristic data to obtain a conversion qualification score;
and according to the conversion qualification grade and the conversion willingness grade, performing label calibration on the historical user characteristic data to obtain the link conversion degree label.
Optionally, the user traffic data at least includes a user feature data, and the obtaining module is further configured to:
acquiring user portrait characteristics and node user conversion time corresponding to each conversion node before the target conversion node;
and generating the user characteristic data according to the node user transformation time characteristics and the user portrait characteristics constructed according to the user transformation time.
Optionally, the obtaining module is further configured to:
acquiring flow channel information corresponding to each conversion node before the target conversion node and corresponding message product forms;
constructing flow channel characteristics according to the information of each flow channel, and constructing message product form characteristics according to the form of each message product;
and splicing the user portrait characteristics, the node user conversion time characteristics, the flow channel characteristics and the message product form characteristics to obtain the user characteristic data.
By adopting the message traffic quality evaluation device provided by the application, the technical problem of low evaluation accuracy of the single-node traffic quality in the user conversion link is solved. Compared with the prior art, the beneficial effects of the message traffic quality assessment device provided by the embodiment of the present application are the same as those of the message traffic quality assessment method provided by the above embodiment, and other technical features of the message traffic quality assessment device are the same as those disclosed in the above embodiment method, which are not described herein again.
Example four
An embodiment of the present application provides an electronic device, and the electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the message traffic quality assessment method in the first embodiment.
Referring now to FIG. 3, shown is a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device may include a processing apparatus (e.g., a central processing unit, a graphic processor, etc.) that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage apparatus into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device, ROM and RAM are trained on each other via the bus. An input/output (I/O) interface is also connected to the bus.
Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, Liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, etc.; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device with various systems, it is to be understood that not all illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
By adopting the message traffic quality assessment method in the embodiment, the electronic device provided by the application solves the technical problem of low accuracy of single-node traffic quality assessment in a user conversion link. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiment of the present application are the same as the beneficial effects of the message traffic quality assessment method provided by the above embodiment, and other technical features in the electronic device are the same as those disclosed in the above embodiment method, which are not described herein again.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
EXAMPLE five
The present embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon for performing the method for message traffic quality assessment in the first embodiment.
The computer readable storage medium provided by the embodiments of the present application may be, for example, a usb disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or a combination of any of the above. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer-readable storage medium may be embodied in an electronic device; or may be present alone without being incorporated into the electronic device.
The computer readable storage medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring user traffic data corresponding to a target conversion node in a user conversion link, and determining a traffic quality prediction model corresponding to the target conversion node, wherein the traffic quality prediction model is obtained by optimizing based on a link conversion degree label; and evaluating the user traffic quality of the target conversion node according to the user traffic data and the traffic quality prediction model to obtain a traffic quality evaluation result.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the names of the modules do not in some cases constitute a limitation of the unit itself.
The computer-readable storage medium provided by the application stores computer-readable program instructions for executing the message traffic quality assessment method, and solves the technical problem of low single-node traffic quality assessment accuracy in a user conversion link. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiment of the present application are the same as the beneficial effects of the message traffic quality assessment method provided by the above embodiment, and are not described herein again.
EXAMPLE six
The present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the message traffic quality assessment method as described above.
The computer program product provided by the application solves the technical problem of low accuracy of single-node flow quality evaluation in a user conversion link. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as the beneficial effects of the message traffic quality assessment method provided by the above embodiment, and are not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.

Claims (10)

1. A message traffic quality assessment method is characterized by comprising the following steps:
acquiring user traffic data corresponding to a target conversion node in a user conversion link, and determining a traffic quality prediction model corresponding to the target conversion node, wherein the traffic quality prediction model is obtained by optimizing based on a link conversion degree label;
and evaluating the user traffic quality of the target conversion node according to the user traffic data and the traffic quality prediction model to obtain a traffic quality evaluation result.
2. The message traffic quality assessment method according to claim 1, wherein prior to the step of determining the traffic quality prediction model corresponding to the target translation node, the message traffic quality assessment method further comprises:
acquiring a traffic quality prediction model to be trained and historical user characteristic data corresponding to a historical user;
according to conversion intention related information of the historical user on the user conversion link, performing label calibration on the historical user characteristic data to obtain a link conversion degree label;
determining a real flow quality label corresponding to the historical user characteristic data according to the link conversion degree label;
and performing iterative training and updating on the to-be-trained flow quality prediction model according to the real flow quality label and the historical user characteristic data to obtain the flow quality prediction model.
3. The message traffic quality assessment method according to claim 2, wherein the conversion intention association information includes conversion depth and conversion consumption time information of the historical user on the user conversion link, and the step of performing label calibration on the historical user characteristic data according to the conversion intention association information of the historical user on the user conversion link to obtain the link conversion degree label includes:
according to the conversion depth and the conversion consumption time information, evaluating the conversion willingness of the historical user on the user conversion link to obtain a conversion willingness score;
and according to the conversion wish score, performing label calibration on the historical user characteristic data to obtain the link conversion degree label.
4. The message traffic quality assessment method according to claim 2, wherein said step of determining a true traffic quality label based on said link translation level label comprises:
determining the traffic category corresponding to the historical user characteristic data according to the value size of the link conversion degree label and a preset conversion degree range;
and endowing the historical user characteristic data with a real flow quality label corresponding to the flow category.
5. The method according to claim 3, wherein the step of performing label calibration on the historical user characteristic data according to the conversion willingness score to obtain the link conversion degree label comprises:
evaluating the conversion qualification corresponding to the historical user according to the historical user characteristic data to obtain a conversion qualification score;
and according to the conversion qualification grade and the conversion willingness grade, performing label calibration on the historical user characteristic data to obtain the link conversion degree label.
6. The method for evaluating message traffic quality according to claim 1, wherein the user traffic data at least includes a user characteristic data, and the obtaining user traffic data corresponding to a target conversion node in the user conversion link includes:
acquiring user portrait characteristics and node user conversion time corresponding to each conversion node before the target conversion node;
and generating the user characteristic data according to the node user transformation time characteristics and the user portrait characteristics constructed according to the user transformation time.
7. The method for message traffic quality assessment according to claim 6, wherein said generating said user profile data based on said user profile characteristics and said node user transition time characteristics comprises:
acquiring flow channel information corresponding to each conversion node before the target conversion node and corresponding message product forms;
constructing flow channel characteristics according to the information of each flow channel, and constructing message product form characteristics according to the form of each message product;
and splicing the user portrait characteristics, the node user conversion time characteristics, the flow channel characteristics and the message product form characteristics to obtain the user characteristic data.
8. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the message traffic quality assessment method of any one of claims 1 to 7.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program for implementing a message traffic quality assessment method, the program being executed by a processor to implement the steps of the message traffic quality assessment method according to any one of claims 1 to 7.
10. A computer program product comprising a computer program, wherein the computer program when executed by a processor implements the steps of the message traffic quality assessment method according to any one of claims 1 to 7.
CN202210627672.XA 2022-06-06 2022-06-06 Message traffic quality evaluation method, electronic device, medium, and program product Pending CN114819747A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210627672.XA CN114819747A (en) 2022-06-06 2022-06-06 Message traffic quality evaluation method, electronic device, medium, and program product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210627672.XA CN114819747A (en) 2022-06-06 2022-06-06 Message traffic quality evaluation method, electronic device, medium, and program product

Publications (1)

Publication Number Publication Date
CN114819747A true CN114819747A (en) 2022-07-29

Family

ID=82522048

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210627672.XA Pending CN114819747A (en) 2022-06-06 2022-06-06 Message traffic quality evaluation method, electronic device, medium, and program product

Country Status (1)

Country Link
CN (1) CN114819747A (en)

Similar Documents

Publication Publication Date Title
CN111381909B (en) Page display method and device, terminal equipment and storage medium
CN111199459B (en) Commodity recommendation method, commodity recommendation device, electronic equipment and storage medium
CN113592535B (en) Advertisement recommendation method and device, electronic equipment and storage medium
CN111738316B (en) Zero sample learning image classification method and device and electronic equipment
US20180075765A1 (en) System and method for transmission of market-ready education curricula
US20200412682A1 (en) Feedback enabled network curation of relevant content thread
CN111191894A (en) Method and device for processing resource demand based on user classification and electronic equipment
CN116894188A (en) Service tag set updating method and device, medium and electronic equipment
CN115018552A (en) Method for determining click rate of product
CN112836128A (en) Information recommendation method, device, equipment and storage medium
CN115601088A (en) Object delivery method and device, storage medium and electronic equipment
CN115953234A (en) Risk assessment method and device, electronic equipment and storage medium
CN114819747A (en) Message traffic quality evaluation method, electronic device, medium, and program product
CN113177176A (en) Feature construction method, content display method and related device
CN113255819A (en) Method and apparatus for identifying information
CN108984680B (en) Information recommendation method and device, server and storage medium
CN112416989A (en) Management method and device of Internet performance broker platform and electronic equipment
US20200169588A1 (en) Methods and systems for managing distribution of online content based on content maturity
CN111738311A (en) Multitask-oriented feature extraction method and device and electronic equipment
US20180225728A1 (en) System and method for facilitating non-parametric weighted correlation analysis
CN115470292B (en) Block chain consensus method, device, electronic equipment and readable storage medium
CN110390291B (en) Data processing method and device and electronic equipment
CN109492695B (en) Sample processing method and device for data modeling, electronic equipment and readable medium
CN116245202A (en) Longitudinal federal learning model training method, device, storage medium and program product
CN116975580A (en) Information evaluation method, device and equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication