CN106503907B - Service evaluation information determination method and server - Google Patents
Service evaluation information determination method and server Download PDFInfo
- Publication number
- CN106503907B CN106503907B CN201610946369.0A CN201610946369A CN106503907B CN 106503907 B CN106503907 B CN 106503907B CN 201610946369 A CN201610946369 A CN 201610946369A CN 106503907 B CN106503907 B CN 106503907B
- Authority
- CN
- China
- Prior art keywords
- service
- user perception
- user
- target service
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
Abstract
The embodiment of the invention discloses a method for determining service evaluation information, which comprises the following steps: acquiring user perception quantity of the target service, wherein the user perception quantity is a degree parameter of the target service perceived by a user; obtaining comment attribute information of a user on a target service through a preset feature extraction rule, wherein the comment attribute information comprises at least one of positive comment information, negative comment information and neutral comment information; and determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information. The invention also provides a server. The embodiment of the invention can fully consider the demand of the user on the target service when evaluating the target service, and improves the influence of social behaviors on the target service, thereby enhancing the popularization efficiency and efficiency of the target service. Meanwhile, the comment attribute information is acquired by combining deep learning and neuro-linguistic programmers, so that the emotional surface of the user can be identified and judged more accurately, and the accuracy and reliability of the scheme are facilitated.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a service evaluation information determining method and a server.
Background
With the rapid iteration of the mobile internet era, the medium environment has changed qualitatively. As information propagators, more and more interactive content cases are generated, the investment cost of the interactive content cases is gradually increased, and the popularization efficiency and the efficiency of the interactive content cases are widely concerned in the industry.
Currently, in order to better promote interactive content cases, related evaluation systems have been adopted in the industry. In a user behavior consumption model issued by a Chinese Internet Data Center (Data Center Of China Internet, English abbreviation: DCCI), user movement behaviors can be divided into mutual perception, interest is generated, connection interaction communication is established, action and post experience sharing are determined, the user behavior consumption model is established through the five parts, and a reasonable interactive content popularization scheme can be planned through the model.
In the user action consumption model published by DCCI, the core lies in the influence of purchasing action on promotion of the interactive content, and the influence of social behavior on promotion of the interactive content is weakened. For the internet era, such user action consumption models may be one-sided, resulting in reduced efficiency and effectiveness of the promotion of interactive content cases.
Disclosure of Invention
The embodiment of the invention provides a service evaluation information determining method and a server, which can fully consider the demand of a user on a target service when evaluating the target service, and improve the influence of social behaviors on the target service, thereby enhancing the popularization efficiency and efficiency of the target service.
In view of this, a first aspect of the present invention provides a method for determining service evaluation information, including:
acquiring user perception quantity of a target service, wherein the user perception quantity is a degree parameter of the target service perceived by a user;
obtaining comment attribute information of a user on the target service through a preset feature extraction rule, wherein the comment attribute information comprises at least one of positive comment information, negative comment information and neutral comment information;
and determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information.
A second aspect of the present invention provides a server, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring the user perception quantity of a target service, and the user perception quantity is a degree parameter of the target service perceived by a user;
the second acquisition module is used for acquiring comment attribute information of the user on the target service through a preset feature extraction rule, wherein the comment attribute information comprises at least one of positive comment information, negative comment information and neutral comment information;
and the determining module is used for determining the service evaluation information of the target service according to the user perception quantity acquired by the first acquiring module and/or the comment attribute information acquired by the second acquiring module.
According to the technical scheme, the embodiment of the invention has the following advantages:
the embodiment of the invention provides a method for determining service evaluation information, which comprises the steps that a server firstly obtains user perception quantity of a target service, the user perception quantity is a degree parameter of the target service perceived by a user, then the server obtains comment attribute information of the user to the target service, and finally the service evaluation information of the target service is determined according to the user perception quantity and/or the comment attribute information. By the method, when the target service is evaluated, the demand of the user on the target service is fully considered, the influence of social behaviors on the target service is improved, the popularization efficiency and the efficiency of the target service are enhanced, meanwhile, the comment attribute information is acquired by combining deep learning and neuro-linguistic programming, the emotion face of the user can be identified and judged more accurately, and the accuracy and the reliability of the scheme are facilitated.
Drawings
FIG. 1 is a system architecture diagram of a business evaluation model in an embodiment of the invention;
FIG. 2 is a schematic diagram of a downloading platform of a business evaluation model according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an embodiment of a method for determining service evaluation information according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating a method for using neuro-linguistic programming in accordance with an embodiment of the present invention;
FIG. 5 is a diagram illustrating comparison of effects of a multi-model integration method according to an embodiment of the present invention;
FIG. 6 is a diagram of interface effects of input business resources in a business evaluation model;
FIG. 7 is a diagram of the interface effect of inputting primary data in a business evaluation model;
FIG. 8 is a diagram of interface effects of output service evaluation information in a service evaluation model;
FIG. 9 is a bar chart of user perception in a business assessment model;
FIG. 10 is a bar graph illustrating a public praise index in a business assessment model;
FIG. 11 is a schematic diagram of an interface showing user behavior data in a business assessment model;
FIG. 12 is a diagram of one embodiment of a server in an embodiment of the invention;
FIG. 13 is a diagram of another embodiment of a server in an embodiment of the present invention;
FIG. 14 is a diagram of another embodiment of a server in an embodiment of the present invention;
FIG. 15 is a diagram of another embodiment of a server in an embodiment of the present invention;
FIG. 16 is a diagram of another embodiment of a server in an embodiment of the present invention;
FIG. 17 is a diagram of another embodiment of a server in an embodiment of the present invention;
FIG. 18 is a diagram of another embodiment of a server in accordance with the present invention;
FIG. 19 is a diagram of another embodiment of a server in accordance with the present invention;
FIG. 20 is a diagram of another embodiment of a server in accordance with the present invention;
FIG. 21 is a diagram of another embodiment of a server in accordance with the present invention;
fig. 22 is a schematic structural diagram of a server in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a service evaluation information determining method and a server, which can fully consider the demand of a user on a target service when evaluating the target service, and improve the influence of social behaviors on the target service, thereby enhancing the popularization efficiency and efficiency of the target service.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that the present invention may be applied to a service evaluation model, please refer to fig. 1, where fig. 1 is a System architecture diagram of the service evaluation model in the embodiment of the present invention, and specifically, the service evaluation model may also be referred to as a content-marketing-effect evaluation model (hereinafter, referred to as "sensor-identity-share-action", hereinafter, abbreviated as SISA "), and the SISA System is based on a mature download platform, a Hadoop Distributed File System (hereinafter, referred to as" HDFS ") computing platform, a retrieval System, and a semantic analysis technology to implement functions such as impurity cleaning, text extraction, emotion analysis, and the like, so as to provide a trend analysis service for a service, and generally employs 200 or more types of machines. A
The downloading platform comprises a writing crawler (full English name: Spider) and an open-source browser engine (full English name: Webkit), wherein the Spider is a class written by a user and used for grabbing information from a domain (or a domain group). The user may define a preliminary list of Uniform Resource Locators (URLs) for downloading, and may trace links and parse the contents of these web pages to extract services. And the WebKit is mainly used for developing browsers and has the characteristics of high efficiency, stability and good compatibility.
The HDFS computing platform implements a distributed file system that is highly fault tolerant and designed for deployment on inexpensive hardware, and that provides high throughput access to application data, suitable for applications with very large data sets. The HDFS can access data in a file system in the form of a stream.
The retrieval system comprises two modules, one module is used for storing real-time data, the data are placed in the memory of the SISA system, the requirement condition of the service can be evaluated by taking the number of days as a dimension, and therefore the data volume of one day is usually stored in the module. And the other module stores data in a period of time, wherein 3 months in the figure is only one example, in practical application, the data in other periods of time can also be stored in a Solid State drive (Solid State Drives, SSD) so that the SISA system can call the data in a period of time.
In addition, the downloading platform also separately establishes a Webkit engine and a scheduling system for the SISA system to meet the requirement of page parsing of a transliteration script language (full name of english: JavaScript, abbreviation of english: JS), please refer to fig. 2, fig. 2 is a schematic diagram of a framework of a service evaluation model downloading platform in the embodiment of the present invention, the downloading platform includes an access module, a control module, a crawler module and an extraction module, the access module is configured to receive data scheduled by the scheduling module, the data may be user behavior data acquired by the operating system and user behavior data stored in the system, the control module re-inputs the data to the crawler module, the crawler module is a program capable of automatically acquiring web page content and is also an important component of the search engine, and finally, the extraction module extracts keywords in the user behavior data to perform semantic recognition.
Referring to fig. 3, a method for determining service evaluation information according to the present invention will be described below from the perspective of a server, where an embodiment of the method for determining service evaluation information according to the present invention includes:
101. acquiring user perception quantity of the target service, wherein the user perception quantity is a degree parameter of the target service perceived by a user;
in this embodiment, the server obtains the user perception amount about the target service through the relevant resources.
The target service may be a product displayed on the social application, or may be a product displayed on the interactive application, where the display mode includes at least one of text, picture, audio, video, and web page. The user perception amount is the degree of the user perceiving the target service, and can be a target service like or a target service dislike, and also can keep neutral attitude for the target service.
102. Obtaining comment attribute information of a user on a target service through a preset feature extraction rule, wherein the comment attribute information comprises at least one of positive comment information, negative comment information and neutral comment information;
in this embodiment, the server needs to obtain the comment attribute information of the user on the target service in addition to the user perception of the target service, where the sequence between step 101 and step 102 is not limited.
Specifically, two problems need to be considered for obtaining the comment attribute information of the user on the target service, the first problem is that the spoken language expression layer is endless, the randomness of the spoken language expression is strong, and some new expressions often appear, such as "playing in a city" or "playing in a natural egg" and the like. The second problem is that the sentence pattern causes emotional drift, and if only emotional character is used, completely opposite emotional polarity is often obtained, for example, the positive comment is that "this is a good mobile phone", the neutral comment is that "this is a good mobile phone", and the negative comment is that "this is a good mobile phone". In order to solve the difficulty in emotion classification, the current mainstream methods can be divided into two categories, one category is that a classifier is built by relying on Neuro-Linguistic Programming (English abbreviation: NLP) technology and taking emotion words, dependency relationship analysis, sentence pattern recognition, language models and the like as characteristics, and the other category is that a deep learning model is trained by using deep learning and word embedding technologies. The preset feature extraction rule may be at least one of the two types of manners.
The invention mainly adopts the two technologies simultaneously, namely an NLP + deep learning combined mode is adopted, the problem of condition classification with clear characteristics is solved through NLP, and the problem that emotion classification can be judged only by combining context is solved through deep learning. For example, in the comment, "this apple is really good at," really good at "is a positive vocabulary, so that it can be inferred that the comment attribute information is positive comment information using NLP, and for example, in the comment," he is pride "and" i am a person who feels pride, "there are two meanings of" pride "being positive or negative, so that deep learning is required to determine the attribute of the comment.
For easy understanding, please refer to fig. 4, where fig. 4 is a schematic diagram of an application neuro-linguistic programming method in an embodiment of the present invention, and as shown in the figure, the key point of the NLP method is how to quickly and automatically mine and supplement features, and solve the problems of feature diversity and colloquialization, we can mine words, new words, compound words, etc. and supplement them into a feature library in time with "hour" as the minimum duration on the basis of billions of social media data. More than seventy thousand effective features of various types are mined, the features are automatically iterated and mined every day.
When the user condition is analyzed by adopting the combination mode of the NLP + the deep learning and the comment attribute information of the user to the target service is determined, a better and more accurate effect can be achieved, please refer to FIG. 5, FIG. 5 is a schematic diagram for comparing the effect of the multi-model integration method in the embodiment of the invention, obviously, the emotion analysis calling-in rate obtained by the combination mode of the NLP + the deep learning is all more than 80%.
103. And determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information.
In this embodiment, the server obtains the service evaluation information of the target service by calculation according to the obtained user perception quantity, may also determine the service evaluation information of the target service according to the comment attribute information, and may also determine the service evaluation information of the target service by combining the user perception quantity and the comment attribute information.
The business evaluation information can be used for quantifying the marketing effect, and the perceptual brand formation and public praise propagation effect is converted into a quantifiable data index. And by directly communicating the comprehensive index with the product data, the relation between the product user and the content marketing can be directly explained, the making and putting of subsequent marketing content can be guided, and the understanding of the user behavior can be enriched.
The embodiment of the invention provides a method for determining service evaluation information, which comprises the steps that a server firstly obtains user perception quantity of a target service, the user perception quantity is a degree parameter of the target service perceived by a user, then the server obtains comment attribute information of the user to the target service, and finally the service evaluation information of the target service is determined according to the user perception quantity and/or the comment attribute information. By the method, when the target service is evaluated, the demand of the user on the target service is fully considered, the influence of social behaviors on the target service is improved, the popularization efficiency and the efficiency of the target service are enhanced, meanwhile, the comment attribute information is acquired by combining deep learning and neuro-linguistic programming, the emotion face of the user can be identified and judged more accurately, and the accuracy and the reliability of the scheme are facilitated.
Optionally, on the basis of the embodiment corresponding to fig. 3, in a first optional embodiment of the method for determining service evaluation information according to the embodiment of the present invention, obtaining the user perception amount of the target service may include:
acquiring a first user perception parameter of a target service through a first service platform;
and acquiring a second user perception parameter of the target service through a second service platform, wherein the second service platform is at least one of the first service platforms.
In this embodiment, the user perception amount of the target service acquired by the server may be specifically divided into two different parameters, one of which is a first user perception parameter acquired by the server through the first service platform, and the other is a second user perception parameter acquired by the server through the second service platform.
Specifically, the first user perception parameter is a user perception amount brought by a resource, that is, a reach amount of native content, where the native content refers to a service that needs to be paid for. The second user perception parameter is the perception increment brought by the spontaneous second propagation of the user, and the second propagation does not need to pay.
The server obtains a first user perception parameter through data provided by a first service platform, the first service platform comprises all platforms (an external platform and an internal platform) of a service party, the external platform can include but is not limited to news, videos, microblogs, Teng-news socializes, application programs, forums, posts, QQ spaces, televisions, planes and the like, and the internal platform includes but is not limited to official websites, game communities, game competition platforms and the like.
The server can provide and capture related second user perception parameters on the network through a second service platform according to the keywords, the second service platform comprises an online platform, namely a part of all the platforms, and the online platform comprises but is not limited to news, videos, microblogs, Teng-news social contacts, application programs, forums, posts and the like.
It should be noted that the manner in which the user perceives the service may be at least one of the following three manners, or may be other manners, which is not limited herein.
The first method is as follows: a user clicks a target service on a platform;
the second method comprises the following steps: a user stops a selection cursor on a target service on a platform, and the stop time exceeds a preset threshold;
the third method comprises the following steps: and the user moves the selection cursor on the target service for multiple times on the platform, and the moving times are more than a preset threshold.
In the embodiment of the present invention, the server may further obtain the first user perception parameter and the second user perception parameter through the first service platform and the second service platform, that is, the user perception obtained by the server may be specifically divided into two perception parameters.
For convenience of introduction, the following four calculation modes are facilitated to respectively obtain service evaluation information, and in practical application, the four service evaluation information can be comprehensively considered, so that the desirability of various types of services can be obtained, and a more reasonable service promotion scheme can be formulated.
First, effect evaluation comprehensive index
Optionally, on the basis of the first embodiment corresponding to fig. 3 or fig. 3, in a second optional embodiment of the service evaluation information determining method provided in the embodiment of the present invention,
the service evaluation information is an effect evaluation comprehensive index;
determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information may include:
and determining an effect evaluation comprehensive index according to the user perception quantity and the comment attribute information.
In this embodiment, when the service evaluation information is the effect evaluation comprehensive index, the server needs to calculate the effect evaluation comprehensive index according to the first user perception parameter, the second user perception parameter, and the comment attribute information. The effect evaluation comprehensive index is mainly used for evaluating the comprehensive performance of the business public praise, and the higher the effect evaluation comprehensive index is, the better the sound volume of the business on the market and the comprehensive performance of the public praise are.
Thirdly, in the embodiment of the invention, the comprehensive effect evaluation index can be used as service evaluation information to measure the public praise performance of the target service in the market, and the relation between the service and the marketing is explained through the comprehensive effect evaluation index to guide the making and releasing of the subsequent marketing content, so that the understanding of the user behavior is enriched, and the practicability of the scheme is enhanced.
Optionally, on the basis of the second embodiment corresponding to fig. 3, in a third optional embodiment of the method for determining service evaluation information according to the embodiment of the present invention, determining an effect evaluation comprehensive index according to the user perception amount and the comment attribute information may include:
the effect evaluation composite index was calculated as follows:
S＝(log2((S1+S2)×k×(a+0.1×b+1)^((a+0.1×b)÷(a+0.1×b+c+0.0001))))^3
s represents an effect evaluation comprehensive index;
s1 represents a first user perception parameter;
s2 represents a second user perception parameter;
k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a character influence coefficient and a picture influence coefficient;
a represents the number of positive comment information;
b represents the number of neutral comment information;
c represents the number of negative comment information.
In this embodiment, in the formula for calculating the effect evaluation comprehensive index, S may also be referred to as SISA comprehensive index, where the SISA comprehensive index is used to evaluate the comprehensive performance of the service content public praise, and a higher index indicates that the public praise of the service is better in the market.
Assume that the server obtains the first user perception parameter S1 as 50000 through all platforms, obtains the second user perception parameter S2 as 20000 through the online platform, and k is a picture influence coefficient, which can be set to 1, and if the second user perception parameter is a video influence coefficient, it can be set to 2, the page influence coefficient can be 1.6, and the text influence coefficient can be 1, which is not limited herein. The number a of the positive comment information is 20000, the number b of the neutral comment information is 10000, and the number c of the negative comment information is 40000, then the calculation result of the effect evaluation comprehensive index is:
S＝(log2((S1+S2)×k×(a+0.1×b+1)^((a+0.1×b)÷(a+0.1×b+c+0.0001))))^3
＝(log2((70000)×1×(21001)^((21000)÷(61000.0001))))^3
＝21.036
the calculation of the composite index of effectiveness evaluation may also be performed for different services over a period of time, so that changes in the public praise of the service may be compared with the horizontal.
Furthermore, in the embodiment of the invention, a calculation mode of the effect evaluation comprehensive index is specifically introduced, so that a practical and effective implementation basis is provided for implementation of the scheme, and the practicability and feasibility of the scheme are improved.
Second, public praise index
Optionally, on the basis of the first embodiment corresponding to fig. 3 or fig. 3, in a fourth optional embodiment of the method for determining service evaluation information according to the embodiment of the present invention, the service evaluation information is a public praise index, and the public praise index is used to indicate a popularity of the target service;
determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information may include:
determining a word-of-mouth index based on the review attribute information.
In this embodiment, when the service evaluation information is a public praise index, the server needs to determine comment attribute information from a plurality of user comments by combining an NLP and a deep learning method. The word-of-mouth index comprises a positive word-of-mouth and a negative word-of-mouth, namely the popularity of the target business can be seen, and the higher the word-of-mouth index can indicate that the comment interaction amount of the user using the target business on the social platform is larger, and the positive or negative comments are more, but the positive or negative comments are in a certain sense, the experience of the user in using the target business is provided.
At present, as described in the above embodiment, the present solution may adopt a preset feature extraction rule to obtain the comment attribute information, where the preset feature extraction rule may be NLP, deep learning, or a combination of the two, and how these two methods are applied is briefly described below.
For example, it is explained by using NLP to solve the problem of spoken language, assuming that a spoken word "destroy three views" appears, the Point-to-Point Mutual Information (PMI) value and the H value of the word can be calculated first, and the PMI calculates the probability that three words of "destroy", "three" and "view" appear at the same time, which represents the correlation of the words formed by combining the several words, and the higher the value, the higher the probability that the mark becomes a phrase is. The more the H value calculates the variability of context before and after the word "three views are destroyed", the more likely the word is to form a word independently. Take "destroy three views" as an example:
words in a word are highly relevant and often occur together.
MI (ruined, three-observation) 0.6 ÷ (0.8 × 1.0) 0.75
MI (destroyalty, observation) 0.6 ÷ (0.6 × 1.0) ═ 1.0
PMI (ruined, three-viewed) ═ min { MI (ruined, three-viewed), MI (ruined, three-viewed) } 0.75
The words can be flexibly employed in a variety of contexts.
"look-three" preamble context is { right (1/3), at (1/3), would (1/3) }
"destroy three views" after context { is (1/3), and (1/3) }
H (destroyed by three views) -log (1 × 1/3) -log (1 × 1/3) -log (1 × 1/3) -1.43
According to the calculation characteristics and the set threshold, words meeting the conditions can be selected, and words with PMI greater than 0.001 and H greater than 0.9 are usually selected.
And deep learning can analyze the same emotional word and judge whether the emotional word belongs to positive emotion, negative emotion or neutral emotion by combining context.
In the embodiment of the invention, the public praise index can be used as the service evaluation information, public praise sound volume and positive and negative comment information on the network are comprehensively considered, and the higher the public praise index is, the larger comment interaction volume of the user using the target service on the social platform is, and the stronger the positive or negative face of the comment is. The relationship between the user comments and the target business is explained through the public praise index so as to guide the making and putting of subsequent marketing contents, and the understanding of the user behaviors is enriched, so that the practicability of the scheme is enhanced.
Optionally, on the basis of the fourth embodiment corresponding to fig. 3, in a fifth optional embodiment of the method for determining service evaluation information according to the embodiment of the present invention, determining a word-of-mouth index according to the comment attribute information may include:
the word of mouth index was calculated as follows:
I＝5×log10((a+b×0.1+1)^((a+b×0.1)÷(a+b×0.1+c+0.0001)))+1
i represents a public praise index;
a represents the number of positive comment information;
b represents the number of neutral comment information;
c represents the number of negative comment information.
In this embodiment, in the formula for calculating the public praise index, if the number a of the positive comment information, the number b of the neutral comment information, and the number c of the negative comment information, which are obtained by the server, are 20000, 10000, and 40000, the public praise index calculation result is:
I＝5×log10((a+b×0.1+1)^((a+b×0.1)÷(a+b×0.1+c+0.0001)))+1
＝5×log10((21001)^((21000)÷(61000.0001)))+1
＝5×log10((21001)^(0.344))+1
＝8.434
this gave a negative percentage of about 57% and a public praise index of 8.434.
Furthermore, in the embodiment of the invention, a public praise index calculation mode is specifically introduced, so that a practical and effective implementation basis is provided for implementation of a scheme, and the practicability and feasibility of the scheme are improved.
Third, diffusion coefficient
Optionally, on the basis of the first embodiment corresponding to fig. 3 or fig. 3, in a sixth optional embodiment of the method for determining service evaluation information according to the embodiment of the present invention, the service evaluation information is a diffusion coefficient, the expansion coefficient is used to indicate a propagation degree of a target service, and the larger the expansion coefficient is, the wider the propagation range of the target service is;
determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information may include:
and determining the diffusion coefficient according to the user perception quantity.
In this embodiment, when the service evaluation information is a diffusion coefficient, the server needs to calculate an effect evaluation comprehensive index through the first user perception parameter and the second user perception parameter. The diffusion coefficient is mainly used for reflecting the secondary diffusion effect of the target service, and the higher the diffusion coefficient is, the better the propagation diffusion of the target service is.
In the embodiment of the present invention, the diffusion coefficient may be used as service evaluation information, and the secondary diffusion effect of the target service is considered comprehensively, and the larger the diffusion coefficient is, the better the service propagation diffusion is. The relation between the secondary propagation and the target service is explained through the diffusion coefficient, so that the making and putting of subsequent marketing contents are guided, the understanding of user behaviors is enriched, and the practicability of the scheme is enhanced.
Optionally, on the basis of the sixth embodiment corresponding to fig. 3, in a seventh optional embodiment of the method for determining service assessment information according to the embodiment of the present invention, determining a diffusion coefficient according to a user perception amount may include:
the diffusion coefficient was calculated as follows:
Q＝(S1+S2)÷S1
q represents a diffusion coefficient;
s1 represents a first user perception parameter;
s2 denotes a second user perception parameter.
In this embodiment, if the server obtains the first user perception parameter S1 being 50000 through all platforms and obtains the second user perception parameter S2 being 20000 through the online platform, the calculation result of the diffusion coefficient is:
Q＝(S1+S2)÷S1
＝(50000+20000)÷50000
＝1.4
the diffusion coefficient of the service is 1.4, the secondary propagation degree can be transversely compared among a plurality of different services through the diffusion coefficient, and of course, the same service can also obtain different diffusion coefficients through different marketing modes, so that which marketing mode is longitudinally compared is more favorable for secondary propagation.
Furthermore, in the embodiment of the invention, a calculation mode of the diffusion coefficient is specifically introduced, so that a practical and effective implementation basis is provided for implementation of the scheme, and the practicability and feasibility of the scheme are improved.
Fourth, cost coefficient
Optionally, on the basis of the first embodiment corresponding to fig. 3 or fig. 3, in an eighth optional embodiment of the method for determining service assessment information according to the embodiment of the present invention, the service assessment information is a cost coefficient, and the cost coefficient is used to represent a cost for acquiring a user perception quantity each time;
determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information may include:
and determining the cost coefficient according to the user perception quantity.
In this embodiment, when the service evaluation information is a cost coefficient, the server needs to calculate the effect evaluation comprehensive index through the first user perception parameter and the second user perception parameter. The Cost coefficient can be called marketing perception Cost (Cost Per Click, abbreviated as CPC), namely the Cost required by each Click of the network advertisement, and the CPC is important reference data for the network advertisement delivery effect. Such pricing models are typically employed in pay-per-effect advertising formats, such as keyword advertising.
The lower and more popular the CPC, indicating a preference by channel or provision of content quality, the cost of the captured user attention is reduced.
In the embodiment of the present invention, the cost coefficient may be used as the service evaluation information, and the relationship between the perceived cost and the service is considered comprehensively, and the lower the cost coefficient is, the better the channel is or the quality of the service content is, and the lower the obtained user attention cost is. The relation between the business cost and the target business is explained through the cost coefficient, so that the making and putting of subsequent marketing contents are guided, the understanding of user behaviors is enriched, and the practicability of the scheme is enhanced.
Optionally, on the basis of the eighth embodiment corresponding to fig. 3, in a ninth optional embodiment of the method for determining service assessment information according to the embodiment of the present invention, determining the cost coefficient according to the user perception amount may include:
the cost coefficient is calculated as follows:
CPC＝M÷((S1+S2)×k)
CPC represents a cost coefficient;
m represents the total cost put into the target service;
s1 represents a first user perception parameter;
s2 represents a second user perception parameter;
k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a text influence coefficient and a picture influence coefficient.
In this embodiment, it is assumed that the server obtains the first user perception parameter S1 as 50000 through all platforms, obtains the second user perception parameter S2 as 20000 through the online platform, where k is a picture influence coefficient and can be set to 1, and the total cost M for a certain service investment can be 80000, and then the calculation result of the cost coefficient is:
CPC＝M÷((S1+S2)×k)
＝80000÷((50000+20000)×1)
＝1.14
furthermore, in the embodiment of the present invention, a cost coefficient calculation method is specifically introduced, so as to provide a practical and effective implementation basis for implementation of the scheme, thereby improving the practicability and feasibility of the scheme.
For convenience of understanding, the following may describe in detail a method for determining service assessment information in the present invention in a specific application scenario, specifically:
at present, a company adopts a business evaluation model system introduced by the invention to evaluate the content marketing effect of the game product.
Firstly, company personnel can track the comprehensive propagation SISA index of the nodes of the game product and the daily related marketing content through a service evaluation model system, please refer to FIG. 6, wherein FIG. 6 is an interface effect diagram of inputting service resources in the service evaluation model, and the company personnel need to periodically input the system schedule and the cost required by link release. And a time period and/or a product name can be selected in the business evaluation model system, so as to review the entered related primary content data, specifically referring to fig. 7, where fig. 7 is an interface effect diagram of the primary data input in the business evaluation model.
Furthermore, the service evaluation model system can also be used for checking daily SISA comprehensive indexes and checking other detailed content keywords and index item data, the content output by the system comprises the parts shown in FIG. 8, and the service evaluation information output by the system can be easily seen through the service evaluation information output by the system in FIG. 8, the SISA indexes are higher in 2016, 6 and 19 days, namely, the condition that the user perceives the game product better. By combining the bar diagrams shown in fig. 9 and fig. 10, it can be further understood that the most perceived amount of the user comes from "microblog", followed by "Tencent video" and "WeChat public number", and the user public praise index increases from 2016, 6, 15, wherein the three word groups most frequently used by the user in the comment are "feelings", "money in the pit" and "guild", and it is obvious that "money in the pit" is a word with negative emotion, and a user who has a considerable score from the user comment cannot recognize the game product well.
Therefore, company personnel know the content, channel and cost release in the actual business according to the related data, the company can track the registration, activity, reflux, payment and the like of the game product by using the account number cross matching among different platforms, know the demand of the hierarchical users on the marketing content in the platforms and enrich the knowledge on the product, please refer to fig. 11, and fig. 11 is an interface schematic diagram showing user behavior data in a business evaluation model. And the company personnel guide the marketing strategy in the later period according to the user behavior data, so that the popularity of the product is improved.
Referring to fig. 12, a server 20 according to an embodiment of the present invention includes:
a first obtaining module 201, configured to obtain a user perception amount of a target service, where the user perception amount is a parameter of a degree that the target service is perceived by a user;
the second obtaining module 202 is configured to obtain comment attribute information of the user on the target service through a preset feature extraction rule, where the comment attribute information includes at least one of positive comment information, negative comment information, and neutral comment information;
a determining module 203, configured to determine service evaluation information of the target service according to the user perception amount obtained by the first obtaining module 201 and/or the comment attribute information obtained by the second obtaining module 202.
In this embodiment, a first obtaining module 201 obtains a user perception amount of a target service, where the user perception amount is a parameter of a degree of perception of the target service by a user, a second obtaining module 202 obtains comment attribute information of the target service by the user through a preset feature extraction rule, where the comment attribute information includes at least one of positive comment information, negative comment information, and neutral comment information, and a determining module 203 determines service evaluation information of the target service according to the user perception amount obtained by the first obtaining module 201 and/or the comment attribute information obtained by the second obtaining module 202.
The embodiment of the invention provides a server for determining service evaluation information, wherein the server firstly acquires user perception of a target service, the user perception is a degree parameter of the target service perceived by a user, then the server acquires comment attribute information of the target service by the user through a preset feature extraction rule, and finally, the service evaluation information of the target service is determined according to the user perception and/or the comment attribute information. By the method, when the target service is evaluated, the demand of the user on the target service is fully considered, the influence of social behaviors on the target service is improved, the popularization efficiency and the efficiency of the target service are enhanced, meanwhile, the comment attribute information is acquired by combining deep learning and neuro-linguistic programming, the emotion face of the user can be identified and judged more accurately, and the accuracy and the reliability of the scheme are facilitated.
Alternatively, referring to fig. 13 on the basis of the embodiment corresponding to fig. 12, in another embodiment of the server 20 provided in the embodiment of the present invention,
the first obtaining module 201 includes:
a first obtaining unit 2011, configured to obtain the first user awareness parameter of the target service through a first service platform;
a second obtaining unit 2012, configured to obtain the second user awareness parameter of the target service through a second service platform, where the second service platform is at least one of the first service platforms.
In the embodiment of the present invention, the server may further obtain the first user perception parameter and the second user perception parameter through the first service platform and the second service platform, that is, the user perception obtained by the server may be specifically divided into two perception parameters.
Alternatively, on the basis of the embodiment corresponding to fig. 12 or fig. 13, referring to fig. 14, in another embodiment of the server 20 provided in the embodiment of the present invention,
the service evaluation information is an effect evaluation comprehensive index;
the determining module 203 comprises:
a first determining unit 2031 configured to determine the effect evaluation composite index according to the user perception amount and the comment attribute information.
Thirdly, in the embodiment of the invention, the comprehensive effect evaluation index can be used as service evaluation information to measure the public praise performance of the target service in the market, and the relation between the service and the marketing is explained through the comprehensive effect evaluation index to guide the making and releasing of the subsequent marketing content, so that the understanding of the user behavior is enriched, and the practicability of the scheme is enhanced.
Alternatively, referring to fig. 15 on the basis of the embodiment corresponding to fig. 14, in another embodiment of the server 20 provided in the embodiment of the present invention,
the first determining unit 2031 includes:
a first calculating subunit 20311, configured to calculate the effect evaluation comprehensive index as follows:
S＝(log2(S1+ S2). times.k × (a +0.1 × b +1) ^3 ((a +0.1 × b) ÷ (a +0.1 × b + c +0.0001)))) said S represents said effect evaluation summary index;
said S1 represents said first user perception parameter;
said S2 represents said second user perception parameter;
the k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a character influence coefficient and a picture influence coefficient;
the a represents the number of the positive comment information;
the b represents the number of the neutral comment information;
the c represents the number of the negative comment information.
Furthermore, in the embodiment of the invention, a calculation mode of the effect evaluation comprehensive index is specifically introduced, so that a practical and effective implementation basis is provided for implementation of the scheme, and the practicability and feasibility of the scheme are improved.
Alternatively, on the basis of the embodiment corresponding to fig. 12 or fig. 13, referring to fig. 16, in another embodiment of the server 20 provided in the embodiment of the present invention,
the service evaluation information is a public praise index which is used for indicating the popularity of the target service;
the determining module 203 comprises:
a second determining unit 2032 for determining the tombstone index according to the comment attribute information.
In the embodiment of the invention, the public praise index can be used as the service evaluation information, public praise sound volume and positive and negative comment information on the network are comprehensively considered, and the higher the public praise index is, the larger comment interaction volume of the user using the target service on the social platform is, and the stronger the positive or negative face of the comment is. The relationship between the user comments and the target business is explained through the public praise index so as to guide the making and putting of subsequent marketing contents, and the understanding of the user behaviors is enriched, so that the practicability of the scheme is enhanced.
Alternatively, referring to fig. 17 on the basis of the embodiment corresponding to fig. 16, in another embodiment of the server 20 provided in the embodiment of the present invention,
the second determining unit 2032 includes:
a second calculating subunit 20321 for calculating the tombstoning index as follows:
I＝5×log10((a+b×0.1+1)^((a+b×0.1)÷(a+b×0.1+c+0.0001)))+1
said I represents said public praise index;
the a represents the number of the positive comment information;
the b represents the number of the neutral comment information;
the c represents the number of the negative comment information.
Furthermore, in the embodiment of the invention, a public praise index calculation mode is specifically introduced, so that a practical and effective implementation basis is provided for implementation of a scheme, and the practicability and feasibility of the scheme are improved.
Alternatively, on the basis of the embodiment corresponding to fig. 12 or fig. 13, referring to fig. 18, in another embodiment of the server 20 provided in the embodiment of the present invention,
the service evaluation information is a diffusion coefficient, the expansion coefficient is used for indicating the propagation degree of the target service, and the larger the expansion coefficient is, the wider the propagation range of the target service is;
the determining module 203 comprises:
a third determining unit 2033 configured to determine the diffusion coefficient according to the user perception amount.
In the embodiment of the present invention, the diffusion coefficient may be used as service evaluation information, and the secondary diffusion effect of the target service is considered comprehensively, and the larger the diffusion coefficient is, the better the service propagation diffusion is. The relation between the secondary propagation and the target service is explained through the diffusion coefficient, so that the making and putting of subsequent marketing contents are guided, the understanding of user behaviors is enriched, and the practicability of the scheme is enhanced.
Alternatively, referring to fig. 19 on the basis of the embodiment corresponding to fig. 18, in another embodiment of the server 20 provided in the embodiment of the present invention,
the third determining unit 2033 includes:
a third calculating subunit 20331 configured to calculate the diffusion coefficient as follows:
Q＝(S1+S2)÷S1
said Q represents said diffusion coefficient;
said S1 represents said first user perception parameter;
the S2 represents the second user perception parameter.
Furthermore, in the embodiment of the invention, a calculation mode of the diffusion coefficient is specifically introduced, so that a practical and effective implementation basis is provided for implementation of the scheme, and the practicability and feasibility of the scheme are improved.
Alternatively, on the basis of the embodiment corresponding to fig. 12 or fig. 13, referring to fig. 20, in another embodiment of the server 20 provided in the embodiment of the present invention,
the service evaluation information is a cost coefficient, and the cost coefficient is used for representing the cost of acquiring the user perception quantity each time;
the determining module 203 comprises:
a fourth determining unit 2034 configured to determine the cost coefficient according to the user perception amount.
In the embodiment of the present invention, the cost coefficient may be used as the service evaluation information, and the relationship between the perceived cost and the service is considered comprehensively, and the lower the cost coefficient is, the better the channel is or the quality of the service content is, and the lower the obtained user attention cost is. The relation between the business cost and the target business is explained through the cost coefficient, so that the making and putting of subsequent marketing contents are guided, the understanding of user behaviors is enriched, and the practicability of the scheme is enhanced.
Alternatively, referring to fig. 19 on the basis of the embodiment corresponding to fig. 20, in another embodiment of the server 21 provided in the embodiment of the present invention,
the fourth determining unit 2034 includes:
a fourth calculating subunit 20341 configured to calculate the cost coefficient as follows:
CPC＝M÷((S1+S2)×k)
the CPC represents the cost coefficient;
the M represents the total cost invested in the target service;
said S1 represents said first user perception parameter;
said S2 represents said second user perception parameter;
and k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a text influence coefficient and a picture influence coefficient.
Furthermore, in the embodiment of the present invention, a cost coefficient calculation method is specifically introduced, so as to provide a practical and effective implementation basis for implementation of the scheme, thereby improving the practicability and feasibility of the scheme.
Fig. 22 is a schematic diagram of a server 300 according to an embodiment of the present invention, where the server 300 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 322 (e.g., one or more processors) and a memory 332, and one or more storage media 330 (e.g., one or more mass storage devices) for storing applications 342 or data 344. Memory 332 and storage media 330 may be, among other things, transient storage or persistent storage. The program stored on the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 322 may be configured to communicate with the storage medium 330 to execute a series of instruction operations in the storage medium 330 on the server 300.
The server 300 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input-output interfaces 353, and/or one or more operating systems 341, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and the like.
The steps performed by the server in the above embodiment may be based on the server structure shown in fig. 22.
The central processor 322 is used.
Acquiring user perception quantity of a target service, wherein the user perception quantity is a degree parameter of the target service perceived by a user;
obtaining comment attribute information of a user on the target service, wherein the comment attribute information comprises at least one of positive comment information, negative comment information and neutral comment information;
and determining the service evaluation information of the target service according to the user perception quantity and/or the comment attribute information.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (19)
1. A method for determining service evaluation information is characterized by comprising the following steps:
acquiring user perception quantity of a target service, wherein the user perception quantity is a degree parameter of the target service perceived by a user; the degree parameter of the target service perceived by the user comprises: acquiring a first user perception parameter of the target service through a first service platform; acquiring a second user perception parameter of the target service through a second service platform, wherein the second service platform is at least one of the first service platforms; the first user perception parameter is a user perception quantity brought by resources, the second user perception parameter is a perception increment brought by spontaneous secondary propagation of a user, and the target service is an interactive content promotion service displayed on a social application;
obtaining comment attribute information of a user on the target service in a mode of combining neuro-linguistic technology and deep learning, wherein the comment attribute information comprises at least one of positive comment information, negative comment information and neutral comment information, the neuro-linguistic technology is used for classifying comments with clear characteristics, and the deep learning is used for classifying comments with unclear characteristics by combining with context;
and determining the service evaluation information of the target service according to the user perception quantity or the user perception quantity and the comment attribute information.
2. The method of claim 1, wherein the service evaluation information is an effectiveness evaluation composite index;
the determining the service evaluation information of the target service according to the user perception quantity and the comment attribute information includes:
and determining the effect evaluation comprehensive index according to the user perception quantity and the comment attribute information.
3. The method of claim 2, wherein determining the effectiveness evaluation composite index according to the user perception amount and the comment attribute information comprises:
the effect evaluation composite index is calculated as follows:
S＝(log2((S1+S2)×k×(a+0.1×b+1)^((a+0.1×b)÷(a+0.1×b+c+0.0001))))^3
the S represents the effect evaluation comprehensive index;
said S1 represents said first user perception parameter;
said S2 represents said second user perception parameter;
the k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a character influence coefficient and a picture influence coefficient;
the a represents the number of the positive comment information;
the b represents the number of the neutral comment information;
the c represents the number of the negative comment information.
4. The method of claim 1, further comprising:
determining a public praise index according to the comment attribute information, wherein the public praise index is used for indicating the popularity of the target business.
5. The method of claim 4, wherein said determining the public praise index from the commentary attribute information comprises:
the word of mouth index was calculated as follows:
I＝5×log10((a+b×0.1+1)^((a+b×0.1)÷(a+b×0.1+c+0.0001)))+1
said I represents said public praise index;
the a represents the number of the positive comment information;
the b represents the number of the neutral comment information;
the c represents the number of the negative comment information.
6. The method according to claim 1, wherein the service evaluation information is a diffusion coefficient, the diffusion coefficient is used to indicate the propagation degree of the target service, and the larger the diffusion coefficient is, the wider the propagation range of the target service is;
the determining the service evaluation information of the target service according to the user perception quantity comprises:
and determining the diffusion coefficient according to the user perception quantity.
7. The method of claim 6, wherein determining the diffusion coefficient according to the user perception comprises:
the diffusion coefficient was calculated as follows:
Q＝(S1+S2)÷S1
said Q represents said diffusion coefficient;
said S1 represents said first user perception parameter;
the S2 represents the second user perception parameter.
8. The method according to claim 1, wherein the service evaluation information is a cost coefficient representing a cost for acquiring the user perception amount each time;
the determining the service evaluation information of the target service according to the user perception quantity comprises:
and determining the cost coefficient according to the user perception quantity.
9. The method of claim 8, wherein determining the cost factor according to the user perception comprises:
the cost coefficient is calculated as follows:
CPC＝M÷((S1+S2)×k)
the CPC represents the cost coefficient;
the M represents the total cost invested in the target service;
said S1 represents said first user perception parameter;
said S2 represents said second user perception parameter;
and k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a text influence coefficient and a picture influence coefficient.
10. A server, comprising:
a first obtaining module, configured to obtain a user perception quantity of a target service, where the user perception quantity is a parameter of a degree of perception of the target service by a user, and the first obtaining module is configured to: a first obtaining unit, configured to obtain a first user perception parameter of the target service through a first service platform; a second obtaining unit, configured to obtain a second user perception parameter of the target service through a second service platform, where the second service platform is at least one of the first service platforms; the first user perception parameter is a user perception quantity brought by resources, the second user perception parameter is a perception increment brought by spontaneous secondary propagation of a user, and the target service is an interactive content promotion service displayed on a social application;
the second acquisition module is used for acquiring comment attribute information of the user on the target service in a mode of combining neuro-linguistic technology and deep learning, wherein the comment attribute information comprises at least one of positive comment information, negative comment information and neutral comment information, the neuro-linguistic technology is used for classifying comments with clear characteristics, and the deep learning is used for classifying comments with unclear characteristics in combination with context;
and the determining module is used for determining the service evaluation information of the target service according to the user perception quantity acquired by the first acquiring module or the user perception quantity and the comment attribute information.
11. The server according to claim 10, wherein the service evaluation information is an effectiveness evaluation composite index;
the determining module comprises:
and the first determining unit is used for determining the effect evaluation comprehensive index according to the user perception quantity and the comment attribute information.
12. The server according to claim 11, wherein the first determining unit includes:
a first calculating subunit, configured to calculate the effect evaluation comprehensive index as follows:
S＝(log2((S1+S2)×k×(a+0.1×b+1)^((a+0.1×b)÷(a+0.1×b+c+0.0001))))^3
the S represents the effect evaluation comprehensive index;
said S1 represents said first user perception parameter;
said S2 represents said second user perception parameter;
the k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a character influence coefficient and a picture influence coefficient;
the a represents the number of the positive comment information;
the b represents the number of the neutral comment information;
the c represents the number of the negative comment information.
13. The server of claim 10, wherein the determining module further comprises:
a second determining unit, configured to determine a public praise index according to the comment attribute information, where the public praise index is used to indicate a popularity of the target service.
14. The server according to claim 13, wherein the second determining unit includes:
a second calculating subunit for calculating the public praise index as follows:
I＝5×log10((a+b×0.1+1)^((a+b×0.1)÷(a+b×0.1+c+0.0001)))+1
said I represents said public praise index;
the a represents the number of the positive comment information;
the b represents the number of the neutral comment information;
the c represents the number of the negative comment information.
15. The server according to claim 10, wherein the service evaluation information is a diffusion coefficient, the diffusion coefficient is used to indicate a propagation degree of the target service, and the larger the diffusion coefficient is, the wider the propagation range of the target service is;
the determining module comprises:
and the third determining unit is used for determining the diffusion coefficient according to the user perception quantity.
16. The server according to claim 15, wherein the third determining unit includes:
a third calculation subunit for calculating the diffusion coefficient as follows:
Q＝(S1+S2)÷S1
said Q represents said diffusion coefficient;
said S1 represents said first user perception parameter;
the S2 represents the second user perception parameter.
17. The server according to claim 10, wherein the service evaluation information is a cost coefficient, and the cost coefficient is used to represent a cost for acquiring the user perception amount each time;
the determining module comprises:
a fourth determining unit, configured to determine the cost coefficient according to the user perception amount.
18. The server according to claim 17, wherein the fourth determination unit includes:
a fourth calculating subunit, configured to calculate the cost coefficient as follows:
CPC＝M÷((S1+S2)×k)
the CPC represents the cost coefficient;
the M represents the total cost invested in the target service;
said S1 represents said first user perception parameter;
said S2 represents said second user perception parameter;
and k represents a content influence coefficient, wherein the content influence coefficient comprises at least one of a video influence coefficient, a page influence coefficient, a text influence coefficient and a picture influence coefficient.
19. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the service assessment information determination method according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610946369.0A CN106503907B (en) | 2016-10-26 | 2016-10-26 | Service evaluation information determination method and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610946369.0A CN106503907B (en) | 2016-10-26 | 2016-10-26 | Service evaluation information determination method and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106503907A CN106503907A (en) | 2017-03-15 |
| CN106503907B true CN106503907B (en) | 2020-11-10 |
Family
ID=58322127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610946369.0A Active CN106503907B (en) | 2016-10-26 | 2016-10-26 | Service evaluation information determination method and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503907B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11069258B2 (en) * | 2017-06-14 | 2021-07-20 | Ifwizard Coprporation | System for behavioral conditioning through gamification |
| TWI649712B (en) | 2017-12-08 | 2019-02-01 | 財團法人工業技術研究院 | Electronic device, presentation process module presentation method and computer readable medium |
| CN108256005A (en) * | 2018-01-02 | 2018-07-06 | 深圳壹账通智能科技有限公司 | Internet product monitoring method and terminal device |
| CN110598960B (en) * | 2018-05-23 | 2022-06-03 | 北京国双科技有限公司 | Entity-level emotion assessment method and device |
| CN109582897A (en) * | 2018-10-22 | 2019-04-05 | 中国平安人寿保险股份有限公司 | Lecture content displaying method, device and storage medium, computer equipment |
| CN112766482A (en) * | 2020-12-21 | 2021-05-07 | 北京航空航天大学 | Input layer structure and BP neural network |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184174A (en) * | 2010-11-10 | 2011-09-14 | 湖北铂金智慧网络科技有限公司 | Method for recording mouse trace in network |
| CN102760138B (en) * | 2011-04-26 | 2015-03-11 | 北京百度网讯科技有限公司 | Classification method and device for user network behaviors and search method and device for user network behaviors |
| CN102591977A (en) * | 2012-01-04 | 2012-07-18 | 北京百度网讯科技有限公司 | Method and system for sequencing search results |
| CN103973902B (en) * | 2013-01-28 | 2017-01-18 | 中国移动通信集团浙江有限公司 | Quantizing device and monitoring system and method for business quality of user perception |
| CN103336796A (en) * | 2013-06-09 | 2013-10-02 | 北京百度网讯科技有限公司 | Method and system for displaying door buster directly |
| CN105373558A (en) * | 2014-08-27 | 2016-03-02 | 青岛海尔智能家电科技有限公司 | Method and system for measuring recommendation levels of products |
| CN105913322A (en) * | 2016-04-07 | 2016-08-31 | 合肥学院 | Subscriber social circle-based information dissemination assessment method and device |
-
2016
- 2016-10-26 CN CN201610946369.0A patent/CN106503907B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106503907A (en) | 2017-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106503907B (en) | Service evaluation information determination method and server | |
| US10567329B2 (en) | Methods and apparatus for inserting content into conversations in on-line and digital environments | |
| US10325033B2 (en) | Determination of content score | |
| Sabou et al. | Crowdsourcing research opportunities: lessons from natural language processing | |
| Liu et al. | Analysis on the word-formation of English netspeak neologism | |
| US8521818B2 (en) | Methods and apparatus for recognizing and acting upon user intentions expressed in on-line conversations and similar environments | |
| US20170270416A1 (en) | Method and apparatus for building prediction models from customer web logs | |
| CN109145216A (en) | Network public-opinion monitoring method, device and storage medium | |
| KR20190017739A (en) | System and method for searching and matching content through personal social networks | |
| CN106462640B (en) | Contextual search of multimedia content | |
| Pyatkin et al. | QADiscourse--Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines | |
| JP5884740B2 (en) | Time-series document summarization apparatus, time-series document summarization method, and time-series document summarization program | |
| CN107885785A (en) | Text emotion analysis method and device | |
| CN112104642A (en) | Abnormal account number determination method and related device | |
| US11651039B1 (en) | System, method, and user interface for a search engine based on multi-document summarization | |
| Nguyen | Text as social and cultural data: A computational perspective on variation in text | |
| Meyer et al. | User participation in the Internet era | |
| Chi et al. | Counterattacking long videos: exploring the characteristics of popular instant videos and roles of producers and viewers | |
| CN110069686A (en) | User behavior analysis method, apparatus, computer installation and storage medium | |
| Clarke | Linguistic variation across Twitter and Twitter trolling | |
| EP4235438A2 (en) | Assessing applications for delivery via an application delivery server | |
| Bauer et al. | Rule-based Approach to Text Generation in Natural Language-Automated Text Markup Language (ATML3). | |
| TWI643080B (en) | A method to parse network data and simulate specific objects accordingly | |
| CN114077710B (en) | Social network account identification method and device and electronic equipment | |
| Munuku | Influence of twitter hashtags on the formation of public opinion on socio-political issues in Kenya |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |