CN113468394A - Data processing method and device, electronic equipment and storage medium - Google Patents
Data processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113468394A CN113468394A CN202110762943.8A CN202110762943A CN113468394A CN 113468394 A CN113468394 A CN 113468394A CN 202110762943 A CN202110762943 A CN 202110762943A CN 113468394 A CN113468394 A CN 113468394A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- value
- target object
- determining
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 533
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 14
- 238000003058 natural language processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001816 cooling Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 abstract description 11
- 238000004458 analytical method Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 11
- 230000009193 crawling Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000013486 operation strategy Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010205 computational analysis Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure provides a data processing method, an apparatus, an electronic device and a storage medium, the method comprising: respectively acquiring first evaluation data and second evaluation data aiming at a target object; determining an evaluation value of the target object according to the first evaluation data, and determining a recommended value of the target object according to the second evaluation data; the evaluation value is used for measuring the degree of commendability and derogation of the target object in a plurality of evaluation channels, and the recommended value is used for measuring the recommended degree of a plurality of target users on the target object; determining a word-of-mouth index for the target object based on the evaluation value and the recommendation value. According to the embodiment of the disclosure, the evaluation values of the plurality of evaluation channels and the recommendation values of the plurality of target users are combined to perform comprehensive calculation analysis, so that the authenticity and reliability of the target object public praise can be improved, and the user and the service side can make more accurate judgment.
Description
Technical Field
The present disclosure relates to the field of electronic commerce technologies, and in particular, to a data processing method and apparatus, an electronic device, and a storage medium.
Background
In recent years, with the development of computer internet technology, more and more internet products are appearing in the public view. For various internet products, such as an internet game, a user often refers to other users' evaluation of the game before selecting the game, namely, the public praise of the game. Meanwhile, for game developers, public praise symbolizes brand and determines business development and operation strategies. Thus, evaluation and generation of word-of-mouth is important to both the user and the developer.
However, at present, a public praise of a certain product is often obtained through comment contents in a product main page or a comment area of an application market, and the comment contents usually cannot represent the real feelings of all users, so that the public praise of the obtained product lacks certain objectivity and reliability.
Disclosure of Invention
The embodiment of the disclosure at least provides a data processing method, a data processing device, electronic equipment and a computer readable storage medium.
In a first aspect, an embodiment of the present disclosure provides a data processing method, including:
respectively acquiring first evaluation data and second evaluation data aiming at a target object;
determining an evaluation value of the target object according to the first evaluation data, and determining a recommended value of the target object according to the second evaluation data; the evaluation value is used for measuring the degree of commendability and derogation of the target object in a plurality of evaluation channels, and the recommended value is used for measuring the recommended degree of a plurality of target users on the target object;
determining a word-of-mouth index for the target object based on the evaluation value and the recommendation value.
In the embodiment of the disclosure, the evaluation values of the plurality of evaluation channels and the recommendation values of the plurality of target users are combined to perform comprehensive calculation analysis, so that the authenticity and reliability of the target object public praise can be improved, and the user and the service party can make more accurate judgment.
In a possible implementation manner, the determining the evaluation value of the target object according to the first evaluation data includes:
calculating a weight of each of the plurality of evaluation channels;
determining the positive evaluation quantity and the negative evaluation quantity according to the evaluation contents in the first evaluation data;
determining the importance of each evaluation according to the attribute information of each evaluation;
determining the evaluation value based on the weight of each evaluation channel, the number of positive evaluations, the number of negative evaluations and the importance of each evaluation.
In the embodiment of the disclosure, the evaluation value of the target object is determined based on a plurality of parameters, so that the user evaluation condition of the target object in a plurality of evaluation channels can be accurately and objectively reflected, public praise evaluation is more comprehensive and detailed, and the problem of single channel scoring mechanism is avoided.
In a possible implementation according to the first aspect, the determining the evaluation value based on the weight of each evaluation channel, the number of positive evaluations, the number of derogatory evaluations, and the importance of each evaluation includes:
taking the product of the recognition evaluation number of each evaluation channel and the evaluation importance of each evaluation channel as a recognition evaluation index, and summing the recognition evaluation indexes to obtain a total recognition evaluation index of the plurality of evaluation channels;
taking the product of the derogatory evaluation quantity of each evaluation channel and each evaluation importance as a sub-derogatory evaluation index, and summing the sub-derogatory evaluation indexes to obtain a total derogatory evaluation index of the plurality of evaluation channels;
taking the difference value of the total positive evaluation index and the total negative evaluation index as the comprehensive evaluation index of the plurality of evaluation channels;
taking the product of the evaluation quantity of each evaluation channel and the weight of each evaluation channel as a sub-evaluation quantity, and summing the sub-evaluation quantities to obtain the total evaluation quantity of the plurality of evaluation channels;
and determining the quotient of the comprehensive evaluation index and the total evaluation quantity as the evaluation value.
In a possible implementation manner, the determining the positive evaluation amount and the negative evaluation amount according to the evaluation contents in the first evaluation data includes:
and determining the commendative evaluation quantity and the derogative evaluation quantity by adopting a Natural Language Processing (NLP) technology according to a plurality of evaluation contents in the first evaluation data.
In the embodiment of the disclosure, the number of positive evaluations and the number of negative evaluations are determined by adopting the NLP recognition technology, so that the processing efficiency is improved, and the time is saved.
In a possible implementation manner, the attribute information of each evaluation includes a number of praise and a number of click, and the determining the importance of each evaluation according to the attribute information of each evaluation includes:
constructing a time attenuation function according to Newton's cooling law;
calculating a time weight of a time period in which each evaluation is based on the time decay function;
and determining the importance of each evaluation based on the time weight, the number of praise, the number of click and step and the weight of each evaluation channel.
In the embodiment of the disclosure, the importance of each evaluation is used as a parameter for calculating the evaluation value, so that the calculation is more accurate and objective, and the influence of factors such as the channel cardinality, crowds and types is eliminated.
According to the first aspect, in one possible implementation, the method further comprises:
judging whether at least one of the praise quantity and the tramp quantity exceeds a preset threshold value or not;
processing the number of the praise exceeding the preset threshold value or the number of the trample exceeding the preset threshold value under the condition that at least one of the number of the praise and the number of the trample exceeds a preset threshold value to obtain the number of the praise of the target point or the number of the trample of the target point;
determining the importance of each evaluation based on the time weight, the number of praise, the number of click-to-step and the weight of each evaluation channel, comprising:
and determining the importance of each evaluation based on the time weight, the target point number of praise, the target point number of tread and the weight of each evaluation channel.
In the embodiment of the disclosure, the condition that a user (water army) who brushes the screen with the wind exists in the evaluation channel is avoided by processing the praise number or the tramp number which exceeds the preset threshold value.
In a possible implementation manner, the determining a recommended value of the target object according to the second evaluation data includes:
determining a recommender ratio and a derogator ratio for the target object from the plurality of target users according to the content of the second evaluation data;
determining the absolute value of the difference between the recommender ratio and the derogator ratio as a net recommendation value;
correcting the confidence coefficient of the net recommended value, and calculating a Wilson confidence interval lower limit value;
and determining the lower limit value of the confidence interval as the recommended value of the target object.
In the embodiment of the disclosure, the recommendation value of the target object is determined based on the net recommendation value and the optimization process, so that the recommendation intentions of the target object in a plurality of target users can be accurately and objectively reflected, the problem of insufficient number of the target users in the statistical sense is solved, and meanwhile, the defect that the target object public praise is judged only through an evaluation channel is avoided.
In a possible implementation manner, the determining a word-of-mouth index of the target object based on the evaluation value and the recommendation value includes:
adding the evaluation quantity of the plurality of evaluation channels and the evaluation quantity of the plurality of target users to obtain a total evaluation quantity;
taking the product of the ratio of the evaluation quantity of the plurality of evaluation channels in the total evaluation quantity and the evaluation value as the evaluation index of the target object;
taking the product of the ratio of the evaluation quantity of the plurality of target users in the total evaluation quantity and the recommendation value as the recommendation index of the target object;
and adding the evaluation index and the recommendation index to determine a public praise index of the target object.
In a second aspect, an embodiment of the present disclosure further provides a data processing apparatus, including:
the acquisition module is used for respectively acquiring first evaluation data and second evaluation data aiming at a target object;
the first determination module is used for determining the evaluation value of the target object according to the first evaluation data and determining the recommended value of the target object according to the second evaluation data; the evaluation value is used for measuring the degree of commendability and derogation of the target object in a plurality of evaluation channels, and the recommended value is used for measuring the recommended degree of a plurality of target users on the target object;
a second determination module to determine a word-of-mouth index of the target object based on the evaluation value and the recommendation value.
According to the second aspect, in a possible implementation manner, the first evaluation data includes a plurality of pieces of evaluation content, and the first determining module is specifically configured to:
calculating a weight of each of the plurality of evaluation channels;
determining the positive evaluation quantity and the negative evaluation quantity according to the evaluation contents in the first evaluation data;
determining the importance of each evaluation according to the attribute information of each evaluation;
determining the evaluation value based on the weight of each evaluation channel, the number of positive evaluations, the number of negative evaluations and the importance of each evaluation.
According to the second aspect, in a possible implementation manner, the first determining module is specifically configured to:
taking the product of the recognition evaluation number of each evaluation channel and the evaluation importance of each evaluation channel as a recognition evaluation index, and summing the recognition evaluation indexes to obtain a total recognition evaluation index of the plurality of evaluation channels;
taking the product of the derogatory evaluation quantity of each evaluation channel and each evaluation importance as a sub-derogatory evaluation index, and summing the sub-derogatory evaluation indexes to obtain a total derogatory evaluation index of the plurality of evaluation channels;
taking the difference value of the total positive evaluation index and the total negative evaluation index as the comprehensive evaluation index of the plurality of evaluation channels;
taking the product of the evaluation quantity of each evaluation channel and the weight of each evaluation channel as a sub-evaluation quantity, and summing the sub-evaluation quantities to obtain the total evaluation quantity of the plurality of evaluation channels;
and determining the quotient of the comprehensive evaluation index and the total evaluation quantity as the evaluation value.
According to the second aspect, in a possible implementation manner, the first determining module is specifically configured to:
and determining the commendative evaluation quantity and the derogative evaluation quantity by adopting a Natural Language Processing (NLP) technology according to a plurality of evaluation contents in the first evaluation data.
According to the second aspect, in a possible implementation manner, the attribute information of each evaluation includes a number of praise and a number of click, and the first determining module is specifically configured to:
constructing a time attenuation function according to Newton's cooling law;
calculating a time weight of a time period in which each evaluation is based on the time decay function;
and determining the importance of each evaluation based on the time weight, the number of praise, the number of click and step and the weight of each evaluation channel.
According to the second aspect, in a possible implementation manner, the first determining module is further specifically configured to:
judging whether at least one of the praise quantity and the tramp quantity exceeds a preset threshold value or not;
processing the number of the praise exceeding the preset threshold value or the number of the trample exceeding the preset threshold value under the condition that at least one of the number of the praise and the number of the trample exceeds a preset threshold value to obtain the number of the praise of the target point or the number of the trample of the target point;
determining the importance of each evaluation based on the time weight, the number of praise, the number of click-to-step and the weight of each evaluation channel, comprising:
and determining the importance of each evaluation based on the time weight, the target point number of praise, the target point number of tread and the weight of each evaluation channel.
According to the second aspect, in a possible implementation manner, the first determining module is specifically configured to:
determining a recommender ratio and a derogator ratio for the target object from the plurality of target users according to the content of the second evaluation data;
determining the absolute value of the difference between the recommender ratio and the derogator ratio as a net recommendation value;
correcting the confidence coefficient of the net recommended value, and calculating a Wilson confidence interval lower limit value;
and determining the lower limit value of the confidence interval as the recommended value of the target object.
According to the second aspect, in a possible implementation manner, the second determining module is specifically configured to:
adding the evaluation quantity of the plurality of evaluation channels and the evaluation quantity of the plurality of target users to obtain a total evaluation quantity;
taking the product of the ratio of the evaluation quantity of the plurality of evaluation channels in the total evaluation quantity and the evaluation value as the evaluation index of the target object;
taking the product of the ratio of the evaluation quantity of the plurality of target users in the total evaluation quantity and the recommendation value as the recommendation index of the target object;
and adding the evaluation index and the recommendation index to determine a public praise index of the target object.
In a third aspect, an embodiment of the present disclosure further provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory communicate via the bus when the electronic device is running, and the machine-readable instructions, when executed by the processor, perform the data processing method of the first aspect or any possible implementation manner of the first aspect.
In a fourth aspect, the disclosed embodiments also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the data processing method described in the first aspect or any one of the possible implementation manners of the first aspect.
In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.
Fig. 1 shows a flow chart of a data processing method provided by an embodiment of the present disclosure;
fig. 2 is a flowchart illustrating a method for determining an evaluation value of the target object according to the first evaluation data according to an embodiment of the present disclosure;
FIG. 3 illustrates a flowchart of a method for determining the importance of each rating provided by an embodiment of the present disclosure;
fig. 4 is a flowchart illustrating another method for determining an evaluation value of the target object according to the first evaluation data according to the embodiment of the disclosure;
FIG. 5 is a flowchart illustrating a method for determining a recommended value of the target object according to the second evaluation data according to an embodiment of the disclosure;
FIG. 6 illustrates a flow chart of a method for determining a word-of-mouth index of the target object provided by an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a data processing apparatus provided in an embodiment of the present disclosure;
fig. 8 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The term "and/or" herein merely describes an associative relationship, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
In recent years, with the development of computer internet technology, more and more internet products are appearing in the public view. For various internet products, such as an internet game, a user often refers to other users' evaluation of the game before selecting the game, namely, the public praise of the game. Meanwhile, for game developers, public praise symbolizes brand and determines business development and operation strategies. Thus, evaluation and generation of word-of-mouth is important to both the user and the developer.
However, at present, a public praise of a certain product is often obtained through comment contents in a product main page or a comment area of an application market, and the comment contents usually cannot represent the real feelings of all users, so that the public praise of the obtained product lacks certain objectivity and reliability. Meanwhile, data of a main page or an application market of the product are scattered, the data are not directly observed and focused, the evaluation calibers of the product are not uniform, the public praise emotion color concentration cannot be accurately quantized, and the professional product thinning project cannot be effectively fed back and improved.
Based on the above-described studies, the present disclosure provides a data processing method that can acquire first evaluation data and second evaluation data for a target object, respectively, then determining an evaluation value of the target object based on the first evaluation data and determining a recommended value of the target object based on the second evaluation data, the evaluation value is used for measuring the degree of the recognition and the derogation of the target object in a plurality of evaluation channels, the recommended value is used for measuring the degree of recommendation of a plurality of target users to the target object, and the public praise index of the target object is determined based on the evaluation value and the recommended value, so that, by performing comprehensive calculation analysis by combining the evaluation values of a plurality of evaluation channels and the recommendation values of a plurality of target users, the authenticity and the reliability of the target object public praise can be improved, and more accurate judgment can be made by the user and the service party.
To facilitate understanding of the present embodiment, first, a data processing method disclosed in the embodiments of the present disclosure is described in detail, where an execution subject of the data processing method provided in the embodiments of the present disclosure is generally an electronic device with certain computing capability, and the electronic device includes, for example: a terminal device, which may be a mobile device, a user terminal, a handheld device, a computing device, a vehicle device, a wearable device, or the like, or a server or other processing device. In some possible implementations, the data processing method may be implemented by a processor calling computer readable instructions stored in a memory.
Referring to fig. 1, a flowchart of a data processing method provided by the embodiment of the present disclosure is shown, where the method may be applied to the electronic device, or applied to a local or cloud server. The data processing method shown in fig. 1 includes the following S101 to S103:
s101, first evaluation data and second evaluation data aiming at the target object are respectively acquired.
For example, the target object may be a network game, a commodity of an e-commerce platform, or an online education product, which is not limited herein, and for convenience of understanding, in the following description of the embodiments, the game is taken as an example for illustration.
For example, the first rating data is rating data for the target object obtained from a plurality of internet rating channels, and the plurality of rating channels may be channels such as a post bar, a microblog, a forum, an online live broadcast, an application market, a social platform, and the like, which are not limited herein. The evaluation data comprises user comment content, the number of likes and clicks, the number of forwards, the number of collections, comment authors, comment time and the like of the target object in the evaluation channel.
Illustratively, the manner of acquiring the first evaluation data may be to crawl evaluation data from a plurality of evaluation channels through a web crawler technology, where the web crawler technology is a program or a script that automatically crawls world wide web information according to certain rules, and may automatically collect all page contents that can be accessed by the web crawler technology, so as to acquire or update the contents and retrieval manners of the websites. In order to improve comprehensiveness of obtaining evaluation data, a crawling keyword list can be set in a crawling process to cover all terms of a target object under user comments as much as possible, for example, a game may have multiple terms in a player, and then the crawling keyword should cover all terms of the target object as much as possible. Meanwhile, in order to avoid unclear designation, the crawling data needs to be accurate and careful, for example, the name of a game may be an animation name, and it may not be determined whether the game is end-play or hand-play, so that when the data is crawled, the crawling range can be narrowed in a mode of game name + hand-play, and the crawling accuracy is improved.
For example, the second evaluation data is evaluation data for the target object obtained from a plurality of target users, such as a game, a plurality of senior players may be selected from a large number of game players as target users, then questionnaires are issued to the plurality of target users, the target users are invited to score the recommendation degree of the game, and finally the questionnaires are collected and sorted for subsequent computational analysis. It is to be understood that the manner of obtaining the second evaluation data is not limited to questionnaire, and may be random access or obtaining from an online customer service communication record, which is not limited herein.
S102, determining the evaluation value of the target object according to the first evaluation data, and determining the recommended value of the target object according to the second evaluation data.
Based on the first evaluation data and the second evaluation data acquired in the above steps, evaluation values of the target object in the plurality of evaluation channels and recommended values of the target object in the plurality of evaluation channels may be calculated through a preset rule, where the evaluation values are used to measure the degree of acceptance and acceptance of the target object in the plurality of evaluation channels, and the recommended values are used to measure the degree of recommendation of the target object by the plurality of target users, and a specific calculation process will be described in detail in the following steps.
S103, determining a word-of-mouth index of the target object based on the evaluation value and the recommendation value.
It can be understood that the evaluation value can visually reflect the comprehensive performance of the target object in the external market evaluation channel, the recommendation value can visually reflect the real experience of the target user on the target object, and finally, the word-of-mouth index of the target object is calculated according to a preset algorithm by combining the values of two different dimensions, and the specific calculation process is also described in detail in the following steps.
According to the embodiment of the disclosure, by respectively acquiring the first evaluation data and the second evaluation data of the target object, then determining the evaluation value of the target object according to the first evaluation data, determining the recommended value of the target object according to the second evaluation data, and then determining the word-of-mouth index of the target object based on the evaluation value and the recommended value, the authenticity and reliability of the word-of-mouth index of the target object can be improved by combining the evaluation values of a plurality of evaluation channels and the recommended values of a plurality of target users for comprehensive calculation analysis, thereby being beneficial to the users and the service providers to make more accurate judgment.
With respect to the above S102, referring to fig. 2, a flowchart of a method for determining an evaluation value of the target object according to the first evaluation data is shown, and includes the following steps S1021 to S1024:
s1021, calculating the weight of each evaluation channel in the plurality of evaluation channels.
It is understood that since the first evaluation data is acquired from a plurality of evaluation channels, and the plurality of evaluation channels are different in influence on the evaluation value due to factors such as user quality, number of evaluations, channel influence, and the like, it is necessary to scientifically and reasonably give a weight to each evaluation channel.
In some embodiments, an Analytic Hierarchy Process (AHP) may be used to calculate the weight of each evaluation channel, where the AHP is a hierarchical weight decision analysis method, and is a qualitative and quantitative decision analysis method for solving multi-target complex problems, and the relative importance degree between each measurement target is determined by the experience of a decision maker, and the weight of each decision scheme is given to determine the priority, which is not described in detail herein. For example, questionnaires can be issued to industry channel experts, a plurality of evaluation channels are compared and scored, and the weight and the sequence of each evaluation channel are summarized according to results.
In some embodiments, based on the evaluation channel weight calculated by the AHP analytic hierarchy process, a channel qualification expert can be searched for one-to-one deep interview, deep communication is performed on evaluation channel selection logic, selection reason background, channel weight, expert scoring result expectation and the like, better opinions and suggestions are solicited, and the channel weight is further optimized.
S1022, determining the positive evaluation quantity and the negative evaluation quantity according to the multiple evaluation contents in the first evaluation data.
For example, the first evaluation data may include a plurality of evaluation contents acquired from a plurality of evaluation channels, and for the evaluation contents, Natural Language Processing (NLP) may be used for semantic recognition, and whether the evaluation contents are a positive evaluation or a negative evaluation is determined, so as to count the number of positive evaluations and the number of negative evaluations.
The NLP technology is an important component of artificial intelligence machine learning, and is a capability of reshaping the human language system, and the computer analyzes, understands and acquires meanings in human language in an intelligent and efficient manner. By utilizing NLP technology, an algorithm model can be organized and constructed to enable a computer to automatically execute tasks such as automatic summarization, machine translation, entity recognition, relation extraction, emotion analysis, voice recognition, topic segmentation and the like, complete machine recognition can be achieved, and accuracy is gradually improved as data volume increases and regular manual bias is carried out.
In some embodiments, since each user in the evaluation channel may have multiple pieces of evaluation content, only one piece of evaluation content may be selected for fairness and objectivity; meanwhile, since the plurality of evaluation contents of each user may be evaluated at different time periods, for example, the user feels that the experience is not good after playing the game for the first time and leaves a piece of evaluation content which is relatively devastating, and after a period of time, the user gradually generates interest in the game and feels that the experience is good, and a piece of positive evaluation content is left, in order to obtain the most real evaluation content of the user, the last evaluation may be selected from the plurality of evaluation contents, and it is ensured that the obtained evaluation data is the most real evaluation of the user.
Therefore, the number of positive evaluations and the number of negative evaluations are determined by adopting the NLP technology, so that the processing efficiency is improved, and the time is saved.
S1023, according to the attribute information of each evaluation, the importance of each evaluation is determined.
The attribute information of each evaluation comprises the number of praise, the number of click and step and the time weight of the evaluation.
Specifically, referring to fig. 3, a flowchart of a method for determining the importance of each evaluation includes the following steps S10231 to S10233:
s10231, constructing a time attenuation function according to Newton' S cooling law.
For example, if a cup of hot water is placed in an environment with room temperature, the temperature of the hot water will gradually cool down over time based on newton's law of cooling, that is, the cooling speed of the object is proportional to the temperature difference between the current temperature and the room temperature, and is expressed by the following formula:
T＝T0e-α(t-t0)
and S10232, calculating the time weight of the time period of each evaluation based on the time attenuation function.
Based on newton's law of cooling, it can be considered that the heat of an evaluation will gradually "cool down" with the lapse of time, that is, the current heat of an evaluation is different from the heat of a period of time ago, so each evaluation needs to be given a time weight, and the time weight of the evaluation calculated by using the time decay function can be expressed as:
past weight ═ current weight x exp (- (cooling coefficient) x interval time number)
The "cooling coefficient" is a predetermined value, and may be assumed to be 0.192, and then, for example, 1 month is used as a decay period, the channel weight of the current month is assumed to be 1, the time weight of the previous month is 1 × exp (-0.192 × 1) ═ 0.8253, the time weight of the next previous month is 1 × exp (-0.192 × 2) ═ 0.6811, and so on, the time weight of the last 24 months is 1 × exp (-0.192 × 24) — 0.00997, which is approximately 0.01, and the weight of the comments before two years can be considered to be 0.01.
And S10233, determining the importance of each evaluation based on the time weight, the number of praise, the number of click and step and the weight of each evaluation channel.
Specifically, the importance of calculating each evaluation can be represented by the following formula:
each evaluation importance is the weight of the time period of the evaluation channel (1+ the number of evaluation points-the number of stamping of the comment points)
Therefore, the importance of each evaluation is used as a parameter for calculating the evaluation value, so that the calculation is more accurate and objective, and the influence of factors such as the channel cardinality, the crowd, the type and the like is eliminated.
In some embodiments, in order to avoid a situation that a user (water force) who brushes the screen with the wind exists in the evaluation channel, when the number of praise or tramp exceeds a preset threshold, for example, the number of praise or tramp exceeds 50, the number of praise or tramp may be processed by using an ln function, and the processed value is used as a new number of praise or tramp.
S1024, determining the evaluation value based on the weight of each evaluation channel, the number of positive evaluations, the number of negative evaluations and the importance of each evaluation.
Specifically, referring to fig. 4, another flowchart of the method for determining the evaluation value includes the following steps S10241 to S10245:
s10241, taking the product of the recognition evaluation number of each evaluation channel and the evaluation importance as a recognition evaluation index, and summing the recognition evaluation indexes to obtain the total recognition evaluation index of the plurality of evaluation channels.
S10242, taking the product of the derogatory evaluation quantity of each evaluation channel and each evaluation importance as a sub-derogatory evaluation index, and summing the sub-derogatory evaluation indexes to obtain a total derogatory evaluation index of the plurality of evaluation channels.
S10243, taking the difference between the total positive evaluation index and the total depreciation evaluation index as the comprehensive evaluation index of the plurality of evaluation channels.
S10244, taking the product of the evaluation quantity of each evaluation channel and the weight of each evaluation channel as a sub-evaluation quantity, and summing the sub-evaluation quantities to obtain a total evaluation quantity of the plurality of evaluation channels.
S10245, determining the total evaluation number as the evaluation value.
The calculation processes of S10241 to S10245 described above can be expressed by the following formulas:
evaluation value ═ number of positive evaluations per evaluation channel-number of derogatory comments per evaluation channel-number of positive comments per evaluation channel-number of effective comments per evaluation channel-corresponding channel weight.
The above steps S1021 to S1024 are the whole calculation process of determining the evaluation value of the target object from the first evaluation data.
In the embodiment of the disclosure, the evaluation value of the target object is determined based on a plurality of parameters, so that the user evaluation condition of the target object in a plurality of evaluation channels can be accurately and objectively reflected, public praise evaluation is more comprehensive and detailed, and the problem of single channel scoring mechanism is avoided.
With respect to the above S102, referring to fig. 5, a flowchart of a method for determining the recommended value of the target object includes the following steps S1021a to S1024 a:
s1021a, determining a recommender ratio and a derogator ratio for the target object from the plurality of target users according to the content of the second evaluation data.
For example, if the recommender is 500 and the derogator is 300 among 1000 target users, the recommender ratio is 50% and the derogator ratio is 30%.
S1022a, determines the absolute value of the difference between the recommender ratio and the derogator ratio as the net recommendation.
For example, in the above example, the net recommendation value 50% to the derogator ratio 30% to 20%.
S1023a, the confidence of the net recommendation value is corrected, and a wilson confidence interval lower limit value is calculated.
In some cases, such as a game with A, B two groups of target users voting, group a has only 10 people, 8 recommended, 2 derogated; group B had 100 people, with 80 recommended and 20 derogated. The recommender ratios of the two groups of target users are both 80%, but based on the statistical theory, the result is more reliable when the number of samples is larger, and after all, the more samples are more statistically significant, that is, the voting result of the target users in the group B is more reliable. In order to solve the problem of the small number of target users, in the present embodiment, the net recommendation value calculated in S1022a is corrected, and the confidence of the net recommendation value is optimized by calculating the wilson confidence interval lower limit based on the statistical theory. The lower Wilson confidence interval limit can be expressed by the following equation:
where ^ p represents the recommender ratio of the target users, n represents the number of target users, and z is a constant, typically with a 95% confidence level, the value of the z statistic is 1.96.
Therefore, the lower limit and the size of the confidence interval can represent the minimum recommendation intention of the target user to the target object, that is, the recommendation value of the target user to the target object can be measured by comparing the lower limit of the confidence interval. For example, in A, B two groups of target users, although the recommender ratio is 80%, the confidence interval of the group a target users is (say [ 70%, 90% ]), the confidence interval of the group B target users is (say [ 75%, 85% ]), and the lower limit value (75%) of the confidence interval of the group B is greater than the lower limit value (70%) of the confidence interval of the group a by comparing, so the result of the group B is better than that of the group a.
S1024a, determining the confidence interval lower limit value as the recommended value of the target object.
In the embodiment of the disclosure, the recommendation value of the target object is determined based on the net recommendation value and the optimization process, so that the recommendation intentions of the target object in a plurality of target users can be accurately and objectively reflected, the problem of insufficient number of the target users in the statistical sense is solved, and meanwhile, the defect that the target object public praise is judged only through an evaluation channel is avoided.
For the above S103, after the evaluation value and the recommender are determined, a preset algorithm may be adopted to fuse the evaluation value and the recommender, and calculate a public praise index of the target object.
Specifically, referring to fig. 6, a flowchart of a method for determining a word-of-mouth index of the target object includes the following steps S1031 to S1034:
and S1031, summing the evaluation quantity of the plurality of evaluation channels and the evaluation quantity of the plurality of target users to obtain a total evaluation quantity.
And S1032, taking the product of the ratio of the evaluation quantity of the plurality of evaluation channels in the total evaluation quantity and the evaluation value as the evaluation index of the target object.
And S1033, taking the product of the ratio of the evaluation quantity of the plurality of target users in the total evaluation quantity and the recommendation value as the recommendation index of the target object.
S1034, summing the evaluation index and the recommendation index to determine a public praise index of the target object.
The calculation procedures of S1031 to S1034 described above can be expressed by the following formulas:
where WR denotes a word-of-mouth index, v denotes the number of target user evaluations, m denotes the number of evaluation channel evaluations, R denotes a recommendation value, and C denotes an evaluation value.
It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.
Based on the same technical concept, a data processing apparatus corresponding to the data processing method is also provided in the embodiments of the present disclosure, and because the principle of the apparatus in the embodiments of the present disclosure for solving the problem is similar to the data processing method described above in the embodiments of the present disclosure, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not described again.
Referring to fig. 7, which is a schematic structural diagram of a data processing apparatus provided in an embodiment of the present disclosure, the apparatus 500 includes:
an obtaining module 501, configured to obtain first evaluation data and second evaluation data for a target object respectively;
a first determining module 502, configured to determine an evaluation value of the target object according to the first evaluation data, and determine a recommended value of the target object according to the second evaluation data; the evaluation value is used for measuring the degree of commendability and derogation of the target object in a plurality of evaluation channels, and the recommended value is used for measuring the recommended degree of a plurality of target users on the target object;
a second determining module 503, configured to determine a word-of-mouth index of the target object based on the evaluation value and the recommendation value.
In a possible implementation manner, the first evaluation data includes a plurality of evaluation contents, and the first determining module 502 is specifically configured to:
calculating a weight of each of the plurality of evaluation channels;
determining the positive evaluation quantity and the negative evaluation quantity according to the evaluation contents in the first evaluation data;
determining the importance of each evaluation according to the attribute information of each evaluation;
determining the evaluation value based on the weight of each evaluation channel, the number of positive evaluations, the number of negative evaluations and the importance of each evaluation.
In a possible implementation manner, the first determining module 502 is specifically configured to:
taking the product of the recognition evaluation number of each evaluation channel and the evaluation importance of each evaluation channel as a recognition evaluation index, and summing the recognition evaluation indexes to obtain a total recognition evaluation index of the plurality of evaluation channels;
taking the product of the derogatory evaluation quantity of each evaluation channel and each evaluation importance as a sub-derogatory evaluation index, and summing the sub-derogatory evaluation indexes to obtain a total derogatory evaluation index of the plurality of evaluation channels;
taking the difference value of the total positive evaluation index and the total negative evaluation index as the comprehensive evaluation index of the plurality of evaluation channels;
taking the product of the evaluation quantity of each evaluation channel and the weight of each evaluation channel as a sub-evaluation quantity, and summing the sub-evaluation quantities to obtain the total evaluation quantity of the plurality of evaluation channels;
and determining the quotient of the comprehensive evaluation index and the total evaluation quantity as the evaluation value.
In a possible implementation manner, the first determining module 502 is specifically configured to:
and determining the commendative evaluation quantity and the derogative evaluation quantity by adopting a Natural Language Processing (NLP) technology according to a plurality of evaluation contents in the first evaluation data.
In a possible implementation manner, the attribute information of each evaluation includes a number of praise and a number of click, and the first determining module 502 is specifically configured to:
constructing a time attenuation function according to Newton's cooling law;
calculating a time weight of a time period in which each evaluation is based on the time decay function;
and determining the importance of each evaluation based on the time weight, the number of praise, the number of click and step and the weight of each evaluation channel.
In a possible implementation manner, the first determining module 502 is further specifically configured to:
judging whether at least one of the praise quantity and the tramp quantity exceeds a preset threshold value or not;
processing the number of the praise exceeding the preset threshold value or the number of the trample exceeding the preset threshold value under the condition that at least one of the number of the praise and the number of the trample exceeds a preset threshold value to obtain the number of the praise of the target point or the number of the trample of the target point;
determining the importance of each evaluation based on the time weight, the number of praise, the number of click-to-step and the weight of each evaluation channel, comprising:
and determining the importance of each evaluation based on the time weight, the target point number of praise, the target point number of tread and the weight of each evaluation channel.
In a possible implementation manner, the first determining module 502 is specifically configured to:
determining a recommender ratio and a derogator ratio for the target object from the plurality of target users according to the content of the second evaluation data;
determining the absolute value of the difference between the recommender ratio and the derogator ratio as a net recommendation value;
correcting the confidence coefficient of the net recommended value, and calculating a Wilson confidence interval lower limit value;
and determining the lower limit value of the confidence interval as the recommended value of the target object.
In a possible implementation manner, the second determining module 503 is specifically configured to:
adding the evaluation quantity of the plurality of evaluation channels and the evaluation quantity of the plurality of target users to obtain a total evaluation quantity;
taking the product of the ratio of the evaluation quantity of the plurality of evaluation channels in the total evaluation quantity and the evaluation value as the evaluation index of the target object;
taking the product of the ratio of the evaluation quantity of the plurality of target users in the total evaluation quantity and the recommendation value as the recommendation index of the target object;
and adding the evaluation index and the recommendation index to determine a public praise index of the target object.
The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.
Based on the same technical concept, the embodiment of the disclosure also provides an electronic device. Referring to fig. 8, a schematic structural diagram of an electronic device 700 provided in the embodiment of the present disclosure includes a processor 701, a memory 702, and a bus 703. The memory 702 is used for storing execution instructions and includes a memory 7021 and an external memory 7022; the memory 7021 is also referred to as an internal memory and temporarily stores operation data in the processor 701 and data exchanged with an external memory 7022 such as a hard disk, and the processor 701 exchanges data with the external memory 7022 via the memory 7021.
In this embodiment, the memory 702 is specifically configured to store application program codes for executing the scheme of the present application, and is controlled by the processor 701 to execute. That is, when the electronic device 700 is operated, the processor 701 and the memory 702 communicate with each other via the bus 703, so that the processor 701 executes the application program code stored in the memory 702 to perform the method disclosed in any of the foregoing embodiments.
The Memory 702 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 701 may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It is to be understood that the illustrated structure of the embodiment of the present application does not specifically limit the electronic device 700. In other embodiments of the present application, the electronic device 700 may include more or fewer components than shown, or combine certain components, or split certain components, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The embodiment of the present disclosure also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the data processing method in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.
The embodiments of the present disclosure also provide a computer program product, where the computer program product carries a program code, and instructions included in the program code may be used to execute the data processing method in the foregoing method embodiments, which may be referred to specifically for the foregoing method embodiments, and are not described herein again.
The computer program product may be implemented by hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above 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 disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and 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 of devices or units through some communication interfaces, 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 disclosure 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 functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several 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 disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (11)
1. A data processing method, comprising:
respectively acquiring first evaluation data and second evaluation data aiming at a target object;
determining an evaluation value of the target object according to the first evaluation data, and determining a recommended value of the target object according to the second evaluation data; the evaluation value is used for measuring the degree of commendability and derogation of the target object in a plurality of evaluation channels, and the recommended value is used for measuring the recommended degree of a plurality of target users on the target object;
determining a word-of-mouth index for the target object based on the evaluation value and the recommendation value.
2. The method according to claim 1, wherein the first evaluation data includes a plurality of pieces of evaluation content, and the determining the evaluation value of the target object from the first evaluation data includes:
calculating a weight of each of the plurality of evaluation channels;
determining the positive evaluation quantity and the negative evaluation quantity according to the evaluation contents in the first evaluation data;
determining the importance of each evaluation according to the attribute information of each evaluation;
determining the evaluation value based on the weight of each evaluation channel, the number of positive evaluations, the number of negative evaluations and the importance of each evaluation.
3. The method of claim 2 wherein determining the rating values based on the weight of each rating channel, the number of positive ratings, the number of depreciative ratings, and the importance of each rating comprises:
taking the product of the recognition evaluation number of each evaluation channel and the evaluation importance of each evaluation channel as a recognition evaluation index, and summing the recognition evaluation indexes to obtain a total recognition evaluation index of the plurality of evaluation channels;
taking the product of the derogatory evaluation quantity of each evaluation channel and each evaluation importance as a sub-derogatory evaluation index, and summing the sub-derogatory evaluation indexes to obtain a total derogatory evaluation index of the plurality of evaluation channels;
taking the difference value of the total positive evaluation index and the total negative evaluation index as the comprehensive evaluation index of the plurality of evaluation channels;
taking the product of the evaluation quantity of each evaluation channel and the weight of each evaluation channel as a sub-evaluation quantity, and summing the sub-evaluation quantities to obtain the total evaluation quantity of the plurality of evaluation channels;
and determining the quotient of the comprehensive evaluation index and the total evaluation quantity as the evaluation value.
4. The method of claim 2, wherein determining the amount of positive evaluation and the amount of negative evaluation based on the plurality of evaluations in the first evaluation data comprises:
and determining the commendative evaluation quantity and the derogative evaluation quantity by adopting a Natural Language Processing (NLP) technology according to a plurality of evaluation contents in the first evaluation data.
5. The method of claim 2, wherein the attribute information of each evaluation comprises a number of likes and a number of clicks, and the determining the importance of each evaluation according to the attribute information of each evaluation comprises:
constructing a time attenuation function according to Newton's cooling law;
calculating a time weight of a time period in which each evaluation is based on the time decay function;
and determining the importance of each evaluation based on the time weight, the number of praise, the number of click and step and the weight of each evaluation channel.
6. The method of claim 5, further comprising:
judging whether at least one of the praise quantity and the tramp quantity exceeds a preset threshold value or not;
processing the number of the praise exceeding the preset threshold value or the number of the trample exceeding the preset threshold value under the condition that at least one of the number of the praise and the number of the trample exceeds a preset threshold value to obtain the number of the praise of the target point or the number of the trample of the target point;
determining the importance of each evaluation based on the time weight, the number of praise, the number of click-to-step and the weight of each evaluation channel, comprising:
and determining the importance of each evaluation based on the time weight, the target point number of praise, the target point number of tread and the weight of each evaluation channel.
7. The method of claim 1, wherein determining the recommended value for the target object based on the second ratings data comprises:
determining a recommender ratio and a derogator ratio for the target object from the plurality of target users according to the content of the second evaluation data;
determining the absolute value of the difference between the recommender ratio and the derogator ratio as a net recommendation value;
correcting the confidence coefficient of the net recommended value, and calculating a Wilson confidence interval lower limit value;
and determining the lower limit value of the confidence interval as the recommended value of the target object.
8. The method of claim 1, wherein determining a word-of-mouth index for the target object based on the evaluation value and the recommendation value comprises:
adding the evaluation quantity of the plurality of evaluation channels and the evaluation quantity of the plurality of target users to obtain a total evaluation quantity;
taking the product of the ratio of the evaluation quantity of the plurality of evaluation channels in the total evaluation quantity and the evaluation value as the evaluation index of the target object;
taking the product of the ratio of the evaluation quantity of the plurality of target users in the total evaluation quantity and the recommendation value as the recommendation index of the target object;
and adding the evaluation index and the recommendation index to determine a public praise index of the target object.
9. A data processing apparatus, comprising:
the acquisition module is used for respectively acquiring first evaluation data and second evaluation data aiming at a target object;
the first determination module is used for determining the evaluation value of the target object according to the first evaluation data and determining the recommended value of the target object according to the second evaluation data; the evaluation value is used for measuring the degree of commendability and derogation of the target object in a plurality of evaluation channels, and the recommended value is used for measuring the recommended degree of a plurality of target users on the target object;
a second determination module to determine a word-of-mouth index of the target object based on the evaluation value and the recommendation value.
10. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is operating, the machine-readable instructions when executed by the processor performing the data processing method of any of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the data processing method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762943.8A CN113468394A (en) | 2021-07-06 | 2021-07-06 | Data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762943.8A CN113468394A (en) | 2021-07-06 | 2021-07-06 | Data processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113468394A true CN113468394A (en) | 2021-10-01 |
Family
ID=77878583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110762943.8A Pending CN113468394A (en) | 2021-07-06 | 2021-07-06 | Data processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113468394A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114039755A (en) * | 2021-10-29 | 2022-02-11 | 中国银联股份有限公司 | Authority control method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102903047A (en) * | 2011-07-26 | 2013-01-30 | 阿里巴巴集团控股有限公司 | Method and device for releasing commodity information |
| CN105183731A (en) * | 2014-06-04 | 2015-12-23 | 腾讯科技（深圳）有限公司 | Method, device, and system for generating recommended information |
| CN108920596A (en) * | 2018-06-27 | 2018-11-30 | 广东亿迅科技有限公司 | A kind of personalized recommendation algorithm and terminal |
| CN109190042A (en) * | 2018-09-06 | 2019-01-11 | 北京奇虎科技有限公司 | A kind of application recommended method and device |
| CN109242359A (en) * | 2018-10-26 | 2019-01-18 | 上海恺英网络科技有限公司 | A kind of method and apparatus obtaining net recommendation |
| CN110942344A (en) * | 2019-11-22 | 2020-03-31 | 汉海信息技术(上海)有限公司 | Method, device, equipment and storage medium for generating food recommendation list |
-
2021
- 2021-07-06 CN CN202110762943.8A patent/CN113468394A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102903047A (en) * | 2011-07-26 | 2013-01-30 | 阿里巴巴集团控股有限公司 | Method and device for releasing commodity information |
| CN105183731A (en) * | 2014-06-04 | 2015-12-23 | 腾讯科技（深圳）有限公司 | Method, device, and system for generating recommended information |
| CN108920596A (en) * | 2018-06-27 | 2018-11-30 | 广东亿迅科技有限公司 | A kind of personalized recommendation algorithm and terminal |
| CN109190042A (en) * | 2018-09-06 | 2019-01-11 | 北京奇虎科技有限公司 | A kind of application recommended method and device |
| CN109242359A (en) * | 2018-10-26 | 2019-01-18 | 上海恺英网络科技有限公司 | A kind of method and apparatus obtaining net recommendation |
| CN110942344A (en) * | 2019-11-22 | 2020-03-31 | 汉海信息技术(上海)有限公司 | Method, device, equipment and storage medium for generating food recommendation list |
Non-Patent Citations (1)
| Title |
|---|
| 无名: "基于内容热度的推荐", 《腾讯云开发者社区》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114039755A (en) * | 2021-10-29 | 2022-02-11 | 中国银联股份有限公司 | Authority control method and device, electronic equipment and storage medium |
| CN114039755B (en) * | 2021-10-29 | 2024-03-22 | 中国银联股份有限公司 | Authority control method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107341268B (en) | Hot searching ranking method and system | |
| US9703877B2 (en) | Computer-based evaluation tool for selecting personalized content for users | |
| CN106485562B (en) | Commodity information recommendation method and system based on user historical behaviors | |
| Liu et al. | Modeling and predicting the helpfulness of online reviews | |
| CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
| CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
| CN110543598B (en) | Information recommendation method and device and terminal | |
| US20170249389A1 (en) | Sentiment rating system and method | |
| CA3150500C (en) | Uploader matching method and device | |
| CN110334356A (en) | Article matter method for determination of amount, article screening technique and corresponding device | |
| US20190065611A1 (en) | Search method and apparatus | |
| CN113239182A (en) | Article recommendation method and device, computer equipment and storage medium | |
| Adamopoulos et al. | Personality-Based Recommendations: Evidence from Amazon. com. | |
| CN113468394A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN109118243B (en) | Product sharing, useful evaluation identification and pushing method and server | |
| CN117114772A (en) | Method, device, equipment and storage medium for mining put-in materials | |
| CN111738754A (en) | Object recommendation method and device, storage medium and computer equipment | |
| KR20210003421A (en) | Method and sever for sorting user preferred post | |
| CN111859946A (en) | Method and device for ranking comments and machine-readable storage medium | |
| Vasconcelos et al. | Popularity dynamics of foursquare micro-reviews | |
| CN114756764A (en) | Enterprise-based content information stream recommendation method and device, electronic equipment and storage medium | |
| CN115168700A (en) | Information flow recommendation method, system and medium based on pre-training algorithm | |
| Sun et al. | Fashionable technology, fashion waves, and post-adoption regret and satisfaction | |
| Pribadi et al. | Analysis of Marketplace Social Media User Engagement by Topic | |
| Liu et al. | Understanding Consumer Preferences---Eliciting Topics from Online Q&A Community |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |