CN111144941A - Merchant score generation method, device, equipment and readable storage medium - Google Patents
Merchant score generation method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN111144941A CN111144941A CN201911360033.6A CN201911360033A CN111144941A CN 111144941 A CN111144941 A CN 111144941A CN 201911360033 A CN201911360033 A CN 201911360033A CN 111144941 A CN111144941 A CN 111144941A
- Authority
- CN
- China
- Prior art keywords
- score
- target
- historical
- merchant
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- 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
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a generation method, a generation device and a readable storage medium of merchant scores, and relates to the technical field of information processing. The method comprises the following steps: acquiring a target score for scoring a target merchant by a first account; acquiring a historical score value of a first account for scoring a reference merchant and a first historical score value received by the reference merchant; carrying out relevancy detection on the historical score and the first historical score to obtain a relevancy result between the historical score and the first historical score; determining the weighting weight of the target score according to the result of the correlation; and generating a target score of the target merchant according to the weighted weight and the target score. By the method of detecting the relevancy of the target score and the historical score of the target merchant and determining the weighted weight of the target score according to the relevancy result obtained by detection, the possible weight correction of abnormal comments is used as the reference of the final merchant target score, so that the accuracy of the merchant total score is improved.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for generating a score for a merchant.
Background
On some platform of applications related to a merchant, a user may express a rating for the merchant in a way that a user comment is posted after experiencing the service of the merchant. In part of the application programs, the evaluation of the user on the merchants is intuitively embodied in a scoring mode, and the scores are calculated in a gathering mode and are embodied as the total scores of the merchants in an interface of the application program.
In the related technology, the application software searches for invalid comment information by configuring the server and inputting a certain characteristic in the server for query, and directly deletes the searched invalid comment information which seriously affects the rating of the merchant.
However, the related art processes invalid comment information in an absolute manner, which easily results in inaccurate overall rating of the merchant.
Disclosure of Invention
The application relates to a generation method, a generation device and a readable storage medium for scoring a merchant, which can solve the problem that the processing mode of invalid comment information in the related technology is too absolute, so that the total scoring of the merchant is easy to be inaccurate. The technical scheme is as follows:
in one aspect, a method for generating a merchant score is provided, where the method includes:
acquiring a target score for scoring a target merchant by a first account;
acquiring a historical score value of a first account for scoring a reference merchant and a first historical score value received by the reference merchant;
carrying out relevancy detection on the historical score and the first historical score to obtain a relevancy result between the historical score and the first historical score;
determining the weighting weight of the target score according to the result of the correlation;
and generating a target score of the target merchant according to the weighted weight and the target score, wherein the target score is used for evaluating the target merchant.
In an alternative embodiment, determining the weighted weight of the target score according to the relevancy results includes:
when the relevancy result meets the relevancy requirement, determining the weighted weight of the target score according to the relevancy result;
when the relevancy result does not meet the relevancy requirement, performing dispersion test on a second historical score received by the target merchant to obtain a dispersion result of the second historical score; and determining the weighted weight of the target score according to the dispersion result.
In an alternative embodiment, determining the weighted weight of the target score according to the dispersion result includes:
when the dispersion result accords with the dispersion condition, carrying out frequency inspection on the frequency of the target score appearing in the historical score to obtain a frequency inspection result;
and determining the weighted weight of the target score according to the frequency test result.
In an alternative embodiment, determining the weighted weight of the target score based on the frequency test results comprises:
when the frequency detection result reaches a frequency threshold value, determining the weighting weight for performing weight reduction processing on the target score;
and when the frequency detection result does not reach the frequency threshold value, determining the weighting weight for weighting up the target score.
In an optional embodiment, before performing the dispersion test on the second history score received by the target merchant, the method further includes:
carrying out distribution inspection on the second historical scores received by the target commercial tenants to obtain confidence intervals in the second historical scores;
and when the target score is not within the confidence interval, performing dispersion test on the second historical score received by the target merchant.
In an optional embodiment, the performing relevance detection on the historical score and the first historical score to obtain a relevance result between the historical score and the first historical score includes:
selecting n target first history scores from the first history scores,
calculating to obtain a reference merchant historical score average according to the n target first historical scores;
and detecting the relevancy according to the historical scoring average of the reference commercial tenant, the n target first historical scores and the historical scoring score to obtain a relevancy result between the first historical score and the historical scoring score.
In an alternative embodiment, the selecting n target first history scores from the first history scores includes:
and removing the first historical scores reaching the preset numerical value threshold value to obtain n target first historical scores.
In another aspect, a generation of merchant ratings is provided, the apparatus comprising:
the acquisition module is used for acquiring a target score for the first account to grade the target merchant;
the acquisition module is also used for acquiring a historical score value of the reference merchant graded by the first account and a first historical score value received by the reference merchant;
the detection module is used for carrying out relevancy detection on the historical score value and the first historical score value to obtain a relevancy result between the historical score value and the first historical score value;
the determining module is used for determining the weighting weight of the target score according to the relevancy result;
and the generating module is used for generating a target score of the target merchant according to the weighted weight and the target score, and the target score is used for evaluating the target merchant.
In an optional embodiment, the determining module is configured to determine, when the relevancy result meets the relevancy requirement, a weighting weight of the target score according to the relevancy result;
the checking module is used for carrying out dispersion checking on the second historical score received by the target merchant when the relevancy result does not meet the relevancy requirement to obtain a dispersion result of the second historical score; and determining the weighted weight of the target score according to the dispersion result.
In an optional embodiment, the checking module is configured to, when the dispersion result meets the dispersion condition, perform frequency checking on frequencies of target scores appearing in the historical score scores to obtain a frequency checking result;
and the determining module is used for determining the weighting weight of the target score according to the frequency test result.
In an optional embodiment, the determining module is configured to determine, when the frequency check result reaches the frequency threshold, a weighting weight for performing a weight reduction process on the target score;
and the determining module is further used for determining the weighting weight for weighting the target score when the frequency detection result does not reach the frequency threshold.
In an optional embodiment, the verification module is configured to perform distribution verification on the second history score received by the target merchant, so as to obtain a confidence interval in the second history score;
and the checking module is also used for carrying out dispersion checking on the second historical score received by the target merchant when the target score is not within the confidence interval.
In an optional embodiment, the obtaining module is configured to select n target first history scores from the first history scores,
the acquisition module is also used for calculating and obtaining a reference merchant historical score average according to the n target first historical scores;
and the detection module is used for carrying out relevancy detection according to the historical scoring average of the reference commercial tenant, the n target first historical scores and the historical scoring score to obtain a relevancy result between the first historical score and the historical scoring score.
In an optional embodiment, the apparatus further comprises: a rejection module;
and the removing module is used for removing the first historical scores reaching the preset numerical value threshold value to obtain n target first historical scores.
In another aspect, a computer device is provided, where the computer device includes a processor and a memory, where at least one instruction, at least one program, a code set, or a set of instructions is stored in the memory, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the method for generating a merchant score provided in the embodiment of the present application.
In another aspect, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a code set, or a set of instructions is stored, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by a processor to implement the method for generating a merchant score provided in the embodiments of the present application.
In another aspect, a computer program product is provided, which when run on a computer causes the computer to execute the method for generating a merchant score as described in any one of the embodiments of the present application.
The beneficial effect that technical scheme that this application provided brought includes at least:
according to the method, the relevance detection is carried out on the target score and the historical scoring score of the target merchant, the weighting weight of the target score is determined according to the relevance result obtained by the detection, and then the target scoring of the target merchant is generated according to the weighting weight and the target score, the possible weight correction of abnormal comments is carried out, and then the corrected weight is used as the reference of the final merchant target scoring, so that the data of the final merchant target scoring reference is more diversified, the probability of mistakenly deleting the normal scoring is reduced, and the accuracy of the total scoring of the merchant is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating a merchant ratings summary interface in the related art;
FIG. 2 is a diagram illustrating a user comment interface in the related art;
fig. 3 shows a flowchart of a method for generating a merchant score according to an embodiment of the disclosure;
fig. 4 shows a flowchart of a method for generating a merchant score according to an embodiment of the disclosure;
fig. 5 shows a flowchart of a method for generating a merchant score according to an embodiment of the disclosure;
fig. 6 is a schematic flow chart illustrating a method for generating a merchant score according to an embodiment of the present disclosure;
fig. 7 shows a block diagram of a structure of a device for generating a merchant score according to an embodiment of the present disclosure;
fig. 8 shows a schematic structural diagram of a server provided by an embodiment of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
In the related art, a user may rate a merchant, which the user wants to rate, on an application program in a scoring manner. Optionally, on some application program interfaces of the platform for embodying evaluation content on merchant quality, the evaluation and scoring performed by the user for one merchant in all target time periods are collectively displayed, and illustratively, the evaluation and scoring performed by all users for one merchant in one month are collectively displayed. Optionally, the interface is also used to score and aggregate the ratings for the merchant. FIG. 1 is a schematic diagram illustrating a merchant ratings summary interface in the related art. Referring to fig. 1, the merchant ratings summary interface includes merchant general ratings information 11 and merchant other information 12.
Optionally, the merchant general comment information includes a merchant picture, a merchant name and a merchant property provided by the merchant. Optionally, the merchant property and the merchant name are provided by the merchant; the commercial tenant picture can be provided by the commercial tenant, publicize the commercial tenant through the picture or the short video form, and can also be provided by the user; the values of the merchant scoring, the scoring number of people and the per-person consumption are determined by the original content of the user and the algorithm of the platform server. In one example, the merchant score is obtained by the scoring of all users in the comment within the target time through a calculation rule inside the server; the scoring number represents the number of all users who comment; the consumption amount of each person in the comment reflected by all the users in the target time is obtained through a calculation rule in the server.
Optionally, in the embodiment shown in fig. 1, the interface further includes merchant other information, which includes merchant service information 102 and merchant address information 103. Optionally, the merchant other information discloses specific service information such as the location and the open time of the merchant, and the information may be issued by the merchant or may be selected by the server after being issued by the user.
Optionally, in the merchant general rating information 101 shown in fig. 1, the merchant score is obtained by the score of all users in the review in the target time through a calculation rule inside the server. Optionally, the scoring performed by the user may also be embodied on the corresponding application program interface.
FIG. 2 illustrates a schematic diagram of a user comment interface in the related art. Optionally, a part of the at least one user comment is included in the user comment interface, please refer to fig. 2, where the user comment 205 and the user comment 206 are shown in the user comment interface shown in fig. 2. Optionally, the user comment 205 includes published user information 202, comment content 203, and interactive function keys 204.
Optionally, the posting user information 202 includes a user name, a user level identifier, a user avatar, a comment posting time, and other information related to the comment and the user posting the comment. Optionally, the user scoring score 201 is also included in the publishing user information 202. Optionally, the merchant score is obtained by collecting user scores in all user comments in the target time, and summarizing the user scores according to a calculation rule in the server. Optionally, the user comment 205 further includes an interaction function key 204, which is used for interacting with a user who browses the interface when the user needs to interact with the user who issues information, and optionally, the interaction function key 204 includes a comment key, a share key, and an attention key, and the user can activate a corresponding function on the interface by operating a corresponding key on the interface. Optionally, user comment 206 shows a presentation of user scoring scores 201 and comment content 203. Optionally, the user score is scored under a score rule corresponding to the application program, and in the score rule of the user comment 206, the user may select a decimal within 0 to 10 as the user score. Optionally, at least one comment drawing may be included in the comment content 203, in the comment content portion of the user comment 206, i.e., with two comment drawings.
Alternatively, the user may post exception comments for a variety of reasons. In one example, if the user randomly inputs a score and enters a messy code in the comment, the comment is considered as an abnormal comment. For abnormal comments, a method for directly removing the comments is commonly used in the related technology, so that the influence of the user scoring value corresponding to the abnormal comments on the merchant scoring of the merchant is prevented. However, the processing manner of the abnormal comments in the related art is too absolute, and the overall scoring of the merchant is easily inaccurate.
Fig. 3 shows a flowchart of a method for generating a merchant score according to an embodiment of the present disclosure, where the method is applied to a server as an example, the method includes:
Optionally, the first account is an account for scoring a target merchant on the application platform, the target merchant is a merchant for scoring the first account, and the target score is a score for scoring the target merchant by the first account. Alternatively, the target score may be a score evaluated for the target merchant; alternatively, the target score may be a score of a rating of a product at the target merchant. Optionally, the display forms of the target scores are different according to different application program interface designs, and in one example, the application program interface displays the target scores through the corresponding quantity of the five stars; or displaying the target score through the expression identifier; or the application program interface displays the target score through the color corresponding to the target score; or the application program interface directly shows the target score in a numerical form. Optionally, when the application program shows the target score in a non-numerical form, the target score is stored in the server, and subsequent score processing is performed.
Optionally, the reference merchant is used to indicate the merchant for which the first account has been scored. Optionally, the number of reference merchants is at least two. Optionally, the first historical score is a score which is received by the reference merchant and is scored by all accounts including the first account; or, the first historical score may be a score that is scored with reference to other accounts that the merchant has received, excluding the first account. Optionally, the number of first historical scores is at least two. In one example, if the reference merchant a, the reference merchant B, and the reference merchant C are all scored by the first account, the server stores the historical score value of the first account for the reference merchant a, the historical score value of the first account for the reference merchant B, and the historical score value of the first account for the reference merchant C, and the server also stores the first historical score values corresponding to the reference merchant a, the reference merchant B, and the reference merchant C. Optionally, the presentation form of the application program for the historical score and the first historical score is also the same as that of the target score, and shows diversity, but both the historical score and the first historical score are also stored in the server. Optionally, the reference merchant may comprise a target merchant, at which point the first historical score comprises a target score.
Optionally, data processing of the first historical score may be required before relevance detection of the historical score and the first historical score. Optionally, the purpose of data processing the first historical score is to cull at least some of the data that is particularly anomalous. Optionally, the small part of the specially abnormal data is removed only during data processing, rather than deleting the abnormal data from the data storage of the server, and the small part of the specially abnormal data still exists during other data processing processes related to the first historical score. Optionally, the first historical scores reaching the preset numerical threshold are removed to obtain n target first historical scores. In one example, the first historical score data of 10% with the highest numerical absolute value and the first historical score data of 10% with the lowest numerical absolute value in the first historical scores are culled. Optionally, the remaining n first history scores are used as the judgment of the n target first history scores, where n is a positive integer.
Optionally, after the n target first history scores are obtained, a reference merchant history score average is calculated according to the n target first history scores. Optionally, the reference merchant history scores are averaged to obtain an average value calculated by averaging the n target first history scores.
Optionally, relevance detection is performed according to the reference merchant historical score average, the n target first historical scores and the historical score scores, and a relevance result between the first historical scores and the historical score scores is obtained.
Optionally, the form of the relevancy detection is to obtain a corresponding relevancy result by bringing the reference merchant history score average, the first history score and the history score into a calculation formula of the pearson correlation coefficient.
Optionally, the correlation results include strong correlation and weak correlation versus no correlation. Illustratively, the value of the correlation result is a value greater than or equal to-1 and less than or equal to 1. When the value is larger than a certain first threshold value, the strong correlation between the first historical score and the historical score is embodied; when the numerical value is larger than the second threshold and smaller than the first threshold, the weak correlation between the first historical score and the historical score is embodied; when the value is smaller than the second threshold value, the first historical score is irrelevant to the historical score. Illustratively, when the relevancy result value is greater than or equal to 0.6, determining that the first historical score is strongly related to the historical score; when the correlation degree result value is greater than or equal to 0 and less than 0.6, determining that the first historical score is weakly correlated with the historical score; when the relevancy result value is less than 0 and greater than or equal to-1, the first historical score is determined to be irrelevant to the historical score.
And step 304, determining the weighted weight of the target score according to the relevancy result.
Optionally, after the average of the reference merchant historical scores, the first historical score and the historical score are substituted into the calculation formula of the pearson correlation coefficient, the correlation result may be obtained. Optionally, a weighted weight of the target score is obtained according to the relevancy result.
Optionally, the weighted weight refers to a weight given to the target score. Optionally, a new score may be generated by combining the weighted weights with the target scores. In one example, the target score is 10, the weighting is 0.8, and the new score is 10 × 0.8 — 8, i.e., the new score represents 8.
And 305, generating a target score of the target merchant according to the weighted weight and the target score, wherein the target score is used for evaluating the target merchant.
Alternatively, the method for generating the target score of the target merchant according to the weighted weight and the target score has been described in step 304. Optionally, the target score of the target merchant is generated by a plurality of target scores and their corresponding weighted weights. In one example, when a merchant receives 50 valid target scores and corresponding weighting weights, a new score is generated for each target score and corresponding weighting weight, and then each new score is summed and averaged to finally obtain a target score.
Optionally, the finally generated target score is used for evaluating the target merchant in the form of a score. Optionally, the higher the finally generated target score is, the better the user's evaluation on the target merchant is, and optionally, the finally generated target score will be displayed to the user at the merchant score in the merchant total evaluation information shown in fig. 1.
In summary, according to the method provided by this embodiment, relevance detection is performed on the target score and the historical score of the target merchant, the weighting weight of the target score is determined according to the relevance result obtained by the detection, and then the target score of the target merchant is generated according to the weighting weight and the target score, and the possible weight correction for abnormal comments is performed to serve as the reference of the final merchant target score, so that the data of the final merchant target score reference is more diversified, the probability of mistakenly deleting the normal score is reduced, and the accuracy of the total merchant score is improved.
In an optional embodiment based on fig. 3, fig. 4 shows a flowchart of a method for generating a merchant score according to an embodiment of the present disclosure, in this embodiment, step 304 in the above embodiment may be replaced with step 3041 to step 3049, which is described by taking an application of the method in a server as an example, where the method includes:
Optionally, after obtaining the relevancy result between the historical score and the first historical score, determining whether the relevancy result meets the relevancy requirement. Optionally, as described in step 303 corresponding to the embodiment in fig. 3, the relevancy result is embodied in a numerical form, illustratively, the relevancy requirement may be implemented as a given numerical value, when the relevancy result reaches the given numerical value, it is determined that the relevancy result meets the relevancy requirement, and when the relevancy result does not reach the given numerical value, it is determined that the relevancy result does not meet the relevancy requirement. In one example, a relevance result of the obtained target score to the historical score of 0.7 and a relevance requirement of 0.6 indicates that the relevance result meets the relevance requirement.
Optionally, when it is determined that the correlation result meets the correlation requirement, performing step 3042; when the correlation result does not meet the correlation requirement, go to step 3043.
Optionally, when the relevancy result meets the relevancy requirement, that is, the first historical score and the historical score are strongly correlated, that is, the target score is an abnormal score, and a weighting weight thereof needs to be determined. Optionally, determining the weighted weight of the target score comprises determining a weighted weight to which to weight down. Alternatively, since the target score is an outlier score, it is weighted down.
Illustratively, the target score is 8.0, and the relevancy result is 0.8, i.e. the relevancy requirement is met, and the result is represented as strong relevancy. In this case, the target score needs to be weighted down, and if the relevance result is 0.8, the weighting weight corresponding to the weighting down process is 0.6, and the weighting weight of the target score is determined to be 0.6, and at this time, the target score after the weighting process is 0.8 × 0.6 — 0.48. Optionally, the merchant score of the target merchant is generated from all the weighted target scores, that is, the score of which the relevancy result does not meet the relevancy requirement is determined in the subsequent step.
Optionally, when the relevancy result does not meet the relevancy requirement, the relevancy result indicates that the first historical score and the historical score are weakly correlated or uncorrelated, that is, the target score is represented as a non-abnormal value after the relevancy test, and then the dispersion test is performed on the second historical score. Optionally, the target score is included or excluded from the first historical score.
Optionally, the target score may or may not be included in the second historical score.
Optionally, the dispersion test result of the second historical score is obtained through dispersion test. Optionally, the dispersion test of the first historical score is performed by an information entropy formula. Alternatively, the information entropy formula is shown as the following formula 1:
equation 1:
in the formula, H represents the degree of dispersion of the first history scores, j represents the number of the first history scores subjected to dispersion test, and pi represents the frequency of occurrence of the ith first history score. Illustratively, the first historical score is 7, 8, 9, 10, and the third historical score is 7, and the same score as the third historical score appears three times in the total number j of 10 of historical scores, i.e., the frequency of occurrence of the third historical score is 0.3, and then p3 is 0.3. Optionally, i ≦ j. Alternatively, H is a value greater than 0, since two or more of the first historical scores must be present, and pi must necessarily be a number between 0 and 1. Optionally, H is the dispersion result.
Optionally, a dispersion condition is further set in the checking process, and the dispersion condition is embodied as a numerical value. When the dispersion result meets the dispersion condition, the first historical score meets the dispersion distribution, namely the scoring scores received by the target merchant from all the users are relatively discrete, and further the scoring scores are received from the merchant, and the scoring scores are not abnormal. Optionally, when the dispersion result does not meet the dispersion condition, that is, the first historical score does not meet the dispersion distribution, that is, the scoring scores received by the target merchant from all users are not dispersed, and further, the scoring scores are abnormal in terms of receiving the scoring scores from the merchant.
Alternatively, when the dispersion result does not meet the dispersion condition, step 3045 is executed; when the dispersion result meets the dispersion condition, step 3046 is executed.
Optionally, when the dispersion result does not meet the dispersion condition, it indicates that the score abnormality is derived from the rating abnormality of the merchant, and illustratively, when the user too concentrates the score on the merchant, the calculated dispersion test result H is smaller than the dispersion condition. In an example, the dispersion result H is 0.3, the dispersion requirement H is greater than or equal to 0.5, and at this time, if the dispersion result H does not meet the dispersion requirement, it may be determined that the abnormality of the score is derived from that the user scores the merchant too intensively, that is, the score abnormality is derived from the merchant. At this time, the weighted weight of the target score may be determined according to the dispersion result. Optionally, due to score abnormality, the target score needs to be weighted down. In one example, when the target score is 7 and the weighting weight corresponding to H is 0.3 is 0.75, the score obtained by weighting down the target score by the weighting weight is 7 × 0.75 — 5.25. I.e. representing a new score of 5.25 points. Optionally, the merchant score of the target merchant is generated from all the target scores after the weighted weighting processing, that is, the score of the dispersion result meeting the dispersion requirement is determined by the weighted weighting in the subsequent step.
Alternatively, when the dispersion result meets the dispersion condition, that is, the dispersion result indicates that the score values are received from the user, the score values are not abnormal, so that the reason for the abnormality needs to be analyzed from the viewpoint of scoring by the user.
Optionally, the reason for the abnormality is analyzed from the point of view of scoring by the user, including by analyzing the frequency of the scoring by the user, i.e. analyzing pi in formula 1. Optionally, a frequency check is performed on the frequency, i.e. the frequency pi is compared to a set frequency threshold.
Alternatively, the frequency threshold is a threshold set in the server, and since the frequency is a value greater than or equal to 0 and less than or equal to 1, the frequency threshold is also set to be greater than or equal to 0 and less than or equal to 1. In one example, the frequency threshold is set to 0.3.
Optionally, when the frequency check result reaches the frequency threshold, performing step 3048; when the frequency check result does not reach the frequency threshold, step 3049 is executed.
Optionally, when the frequency check result reaches the frequency threshold, the score is indicated as the high-frequency score of the first account, i.e. it is possible that the frequency of the user frequently scoring the score in the application software is higher. Optionally, it is determined that the target score is weighted down at this time. In one example, the target score is 9, the frequency is 0.7, and the set threshold is 0.3, the target score needs to be weighted down, and optionally, when the frequency is 0.7, the corresponding weighting weight is 0.6, and the score obtained by weighting down the target score by the weighting weight is 9 × 0.6 — 5.4.
Optionally, when the frequency check result does not reach the frequency threshold, it indicates that the score is the low-frequency score of the first account, and it is highly likely that the user makes a score which is not frequently used in the application software due to subjective feeling of the user or a special reason of the merchant. Optionally, it is determined that the target score is weighted up at this time. In one example, the target score is 9, the frequency is 0.2, and the set threshold is 0.3, then the target score needs to be weighted up. Optionally, when the frequency is 0.2, and the corresponding weighting weight is 1.3, the score of the target score after being weighted up by the weighting weight is 9 × 1.3 — 1.17.
Optionally, the values represented by the weighting up processing and the weighting down processing in the above steps are values represented by weights when the final target score of the target merchant is finally determined.
In summary, according to the method provided by this embodiment, relevance detection is performed on the target score and the historical score of the target merchant, the weighting weight of the target score is determined according to the relevance result obtained by the detection, and then the target score of the target merchant is generated according to the weighting weight and the target score, and the possible weight correction for abnormal comments is performed to serve as the reference of the final merchant target score, so that the data of the final merchant target score reference is more diversified, the probability of mistakenly deleting the normal score is reduced, and the accuracy of the total merchant score is improved. The determination of anomalous data after passing the correlation detection allows for additional anomaly detection of the anomalous data. The method comprises the steps of determining the reasons of abnormal values through a dispersion test and frequency test method, finally generating target scores of target merchants by giving a target score weighting method under the condition of determining the reasons of abnormal values, evaluating the target merchants, and further improving the accuracy of total merchant scores.
In an optional embodiment based on fig. 4, fig. 5 shows a flowchart of a method for generating a merchant score according to an embodiment of the present disclosure, in this embodiment, before step 3043 in the above embodiment, step 501 and step 502 are further included, which is described by taking an application of the method in a server as an example, the method includes:
step 501: and carrying out distribution inspection on the second historical score received by the target merchant to obtain a confidence interval in the second historical score.
Optionally, the second historical score is initially screened by a distribution test to select outliers to be tested.
Alternatively, the following equation 2 is taken as a test equation for performing the distribution test. Alternatively, the test is a variation of the t-test, replacing the mean with a median, and removing the portion of the target score itself when summing to emphasize the scoring criteria of other users. The equation 2 is as follows:
equation 2:
optionally, d is a statistic of the distribution test, for each of the second historical scores excluding the target score, and for a median of the other scores in the second historical scores excluding the target score. And m is n-1, namely m is the number of the second historical scores except the target scores, and n is the total number of the historical scores. i indicates the ith score in the second historical scores, and k indicates the score serial number corresponding to the target score, namely the target score.
Optionally, according to the statistic formula, a confidence interval corresponding to the statistic formula may be determined, and optionally, according to whether the target score is within the confidence interval, whether the target score is abnormal may be determined.
Alternatively, when the target score is not within the confidence interval, it indicates that the target score is abnormal. Optionally, when the target score is abnormal, performing dispersion test on the second historical score.
Alternatively, when the target score is within the confidence interval, it indicates that the target score is not abnormal. Optionally, when the target score is abnormal, the weighting weight of the target score is obtained according to the result of the relevance.
In summary, according to the method provided by this embodiment, relevance detection is performed on the target score and the historical score of the target merchant, the weighting weight of the target score is determined according to the relevance result obtained by the detection, and then the target score of the target merchant is generated according to the weighting weight and the target score, and the possible weight correction for abnormal comments is performed to serve as the reference of the final merchant target score, so that the data of the final merchant target score reference is more diversified, the probability of mistakenly deleting the normal score is reduced, and the accuracy of the total merchant score is improved. And the second historical score required to be tested is determined by a distributed testing method, so that the testing efficiency is improved.
Fig. 6 is a schematic flowchart illustrating a method for generating a merchant score according to an embodiment of the present disclosure, where for example, the method is applied to a server, the method includes:
step 601, obtaining a target score.
Optionally, the target score is a score obtained when the first account scores the target merchant.
Optionally, the historical score value is a value obtained when the first account scores the reference merchant, and optionally, the number of the historical score values is at least two.
Step 603, obtaining a first historical score.
Optionally, the first historical score is a score that has been received by the reference merchant and scored by all accounts including the first account.
And step 604, calculating the relevance, namely performing relevance detection on the historical score and the first historical score. Optionally, the purpose of the relevancy detection is to detect a historical scoring habit of the user, and determine whether the scoring habit indicates that the user is affected by the scoring of the merchant by other users.
Optionally, through the relevance detection, the first history score, the reference merchant history score average generated by the target score and the history score are obtained through a calculation formula of a pearson correlation coefficient to obtain a relevance result of the first history score and the history score. The correlation result is a value of 1 or less and-1 or more. Optionally, the correlation results include strong correlation, weak correlation and no correlation. Optionally, a correlation requirement is set.
When the correlation result meets the correlation requirement, step 606 is executed, and when the correlation result does not meet the correlation requirement, step 607 is executed.
Optionally, the weighted weight refers to a weight given to the target score. Alternatively, the target score may be combined with a weighted weight to generate a new score.
Step 607, the target score is retrieved.
Optionally, when the relevancy result does not meet the relevancy requirement, the target score is obtained again. Optionally, when the target score is obtained again, the weight of the target score that has been given is also obtained.
Step 608, obtain a second historical score.
Optionally, the second historical score is a score that the target merchant has received. Optionally, the target score is included in the second historical score.
Step 609, perform distributed verification.
Optionally, the historical score scores are initially screened by a distributed test to screen for outliers that require further testing.
Optionally, step 611 is performed on the outliers screened by the t-test and step 618 is performed on the non-outliers screened.
Step 611, obtain historical score.
Optionally, after the determining, a second historical score is obtained. The second historical score comprises a normal second historical score and an abnormal second historical score which are screened out through a t test. Optionally, the historical score scores are differentiated simultaneously in the acquisition process.
Optionally, a dispersion test is performed on the second historical score of the anomaly.
Step 613, the dispersion result is compared with the dispersion condition.
Optionally, the dispersion test is performed through an information entropy formula, and a dispersion test result of the second historical score is obtained through the dispersion test. Optionally, the dispersion result mainly checks whether the scores from all users accepted by the target merchant are dispersed. Alternatively, the dispersion condition is embodied as a numerical value. When the dispersion result meets the dispersion condition, the first historical score meets the dispersion distribution, namely the scoring scores received by the target merchant from all the users are relatively discrete, and further the scoring scores are received from the merchant, and the scoring scores are not abnormal. Optionally, when the dispersion result does not meet the dispersion condition, that is, the first historical score does not meet the dispersion distribution, that is, the scoring scores received by the target merchant from all users are not dispersed, and further, the scoring scores are abnormal in terms of receiving the scoring scores from the merchant.
Optionally, when the dispersion result does not meet the dispersion condition, step 614 is executed; when the dispersion result meets the dispersion condition, step 615 is executed.
At step 614, a weighting weight is determined.
Optionally, when the dispersion result does not meet the dispersion condition, that is, it indicates that the scores received by the merchant are too concentrated, the scores received by the merchant are abnormal, that is, the scores are determined by weighting. Optionally, the merchant score of the target merchant is generated from all the weighted target scores. Optionally, the weighting in this step includes not giving the first score a weighting weight.
At step 615, the frequency check result is compared to a frequency threshold.
Alternatively, when the dispersion result meets the dispersion condition, that is, the dispersion result indicates that the score values are received from the user, the score values are not abnormal, so that the reason for the abnormality needs to be analyzed from the viewpoint of scoring by the user.
Optionally, the reason for the abnormality is analyzed from the point of view of scoring by the user, including by analyzing the frequency of the scoring by the user. After determining the frequency check result and determining the frequency threshold, the frequency check result is compared with the set threshold.
Optionally, when the frequency checking result reaches the frequency threshold, step 616 is executed; when the frequency check result does not reach the frequency threshold, step 617 is performed.
At step 616, the weighting weight for the weight down process is determined.
Optionally, when the frequency check result reaches the frequency threshold, the score is indicated as the high-frequency score of the first account, i.e. it is possible that the frequency of the user frequently scoring the score in the application software is higher. Optionally, it is determined that the target score is weighted down at this time.
Optionally, when the frequency check result does not reach the frequency threshold, it indicates that the score is the low-frequency score of the first account, and it is highly likely that the user makes a score which is not frequently used in the application software due to subjective feeling of the user or a special reason of the merchant. Optionally, it is determined that the target score is weighted up at this time.
At step 618, a goal score is generated.
Optionally, a target score of the merchant is generated according to the target score and the weighting weight thereof, and the score is obtained by the score processing rule of this embodiment after the scores for the merchant are issued by the multiple accounts.
In summary, according to the method provided by this embodiment, relevance detection is performed on the target score and the historical score of the target merchant, the weighting weight of the target score is determined according to the relevance result obtained by the detection, and then the target score of the target merchant is generated according to the weighting weight and the target score, and the possible weight correction for abnormal comments is performed to serve as the reference of the final merchant target score, so that the data of the final merchant target score reference is more diversified, the probability of mistakenly deleting the normal score is reduced, and the accuracy of the total merchant score is improved. Through distribution inspection, dispersion inspection and frequency inspection, the reason of abnormal scoring of the user is analyzed, the corresponding weighting weight is determined according to the reason of the abnormal scoring, the weighting increasing processing is carried out on the first score, and the accuracy rate of total scoring of the merchants is further improved.
Fig. 7 shows a block diagram of a structure of a device for generating a merchant score according to an embodiment of the present disclosure, which is described by taking the device as an example for being applied to a server, and the device includes:
an obtaining module 701, configured to obtain a target score for a first account to score a target merchant;
the obtaining module 701 is further configured to obtain a historical score value of the first account for scoring the reference merchant and a first historical score value received by the reference merchant;
the detection module 702 is configured to perform relevance detection on the historical score value and the first historical score value to obtain a relevance result between the historical score value and the first historical score value;
a determining module 703, configured to determine a weighting of the target score according to the result of the relevance;
and a generating module 704, configured to generate a target score of the target merchant according to the weighted weight and the target score, where the target score is used to evaluate the target merchant.
In an optional embodiment, the determining module 703 is configured to determine, when the relevancy result meets the relevancy requirement, a weighting weight of the target score according to the relevancy result;
the checking module 702 is configured to, when the relevancy result does not meet the relevancy requirement, perform dispersion checking on the second historical score received by the target merchant, to obtain a dispersion result of the second historical score; and determining the weighted weight of the target score according to the dispersion result.
In an optional embodiment, the checking module 702 is configured to, when the dispersion result meets the dispersion condition, perform frequency checking on a frequency of occurrence of the target score in the historical score to obtain a frequency checking result;
a determining module 703, configured to determine a weighted weight of the target score according to the frequency checking result.
In an optional embodiment, the determining module 703 is configured to determine, when the frequency checking result reaches the frequency threshold, a weighting weight for performing a weight reduction process on the target score;
the determining module 703 is further configured to determine a weighting for weighting the target score when the frequency checking result does not reach the frequency threshold.
In an optional embodiment, the checking module 702 is configured to perform distribution checking on the second history score received by the target merchant, so as to obtain a confidence interval in the second history score;
the checking module 702 is further configured to perform a dispersion check on the second historical score received by the target merchant when the target score is not within the confidence interval.
In an alternative embodiment, the obtaining module 701 is configured to select n target first history scores from the first history scores,
the obtaining module 701 is further configured to calculate, according to the n target first history scores, to obtain a reference merchant history score average;
the detection module 702 is configured to perform relevancy detection according to the reference merchant historical score average, the n target first historical scores, and the historical score scores to obtain a relevancy result between the first historical scores and the historical score scores.
In an optional embodiment, the apparatus further comprises a culling module 705;
the removing module 705 is configured to remove the first history scores that reach the preset numerical threshold, so as to obtain n target first history scores.
It should be noted that: the device for generating a merchant score according to the foregoing embodiment is only illustrated by dividing each functional module, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above.
The application also provides a server, which comprises a processor and a memory, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement the merchant score generation method provided by the above method embodiments. It should be noted that the server may be a server as provided in fig. 8 below.
Referring to fig. 8, a schematic structural diagram of a server according to an exemplary embodiment of the present application is shown. Specifically, the method comprises the following steps: server 1300 includes a Central Processing Unit (CPU) 1301, a system Memory 1304 including a Random Access Memory (RAM) 1302 and a Read-Only Memory (ROM) 1303, and a system bus 1305 connecting system Memory 104 and CPU 1301. The server 1300 also includes a basic Input/output (I/O) system 106, which facilitates the transfer of information between devices within the computer, and a mass storage device 1307 for storing an operating system 1313, application programs 1314 and other program modules 1315.
The basic input/output system 1306 includes a display 1308 for displaying information and an input device 1309, such as a mouse, keyboard, etc., for user input of information. Wherein a display 1308 and an input device 1309 are connected to the central processing unit 1301 through an input-output controller 1310 connected to the system bus 1305. The basic input/output system 1306 may also include an input/output controller 1310 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input-output controller 1310 also provides output to a display screen, a printer, or other type of output device.
The mass storage device 1307 is connected to the central processing unit 1301 through a mass storage controller (not shown) connected to the system bus 1305. The mass storage device 1307 and its associated computer-readable media provide non-volatile storage for the server 1300. That is, the mass storage device 1307 may include a computer-readable medium (not shown) such as a hard disk or CD-ROI drive.
Without loss of generality, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash Memory or other solid state Memory technology, CD-ROM, Digital Versatile Disks (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 1304 and mass storage device 1307 described above may be collectively referred to as memory.
The memory stores one or more programs configured to be executed by the one or more central processing units 1301, the one or more programs containing instructions for implementing the above-described merchant score generation method, and the central processing unit 1301 executes the one or more programs to implement the merchant score generation method provided by the various method embodiments described above.
According to various embodiments of the invention, the server 1300 may also operate as a remote computer connected to a network through a network, such as the Internet. That is, the server 1300 may be connected to the network 1312 through the network interface unit 1311, which is connected to the system bus 1305, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 1311.
The memory further comprises one or more programs, the one or more programs are stored in the memory, and the one or more programs comprise steps executed by the server for performing the merchant score generation method provided by the embodiment of the invention.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, which may be a computer readable storage medium contained in a memory of the above embodiments; or it may be a separate computer-readable storage medium not incorporated in the terminal. The computer readable storage medium has at least one instruction, at least one program, a set of codes, or a set of instructions stored therein, which is loaded and executed by a processor to implement the above-mentioned merchant score generation method.
Optionally, the computer-readable storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a Solid State Drive (SSD), or an optical disc. The Random Access Memory may include a resistive Random Access Memory (ReRAM) and a Dynamic Random Access Memory (DRAM). The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps of implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method for generating a merchant score, the method comprising:
acquiring a target score for scoring a target merchant by a first account;
acquiring a historical score value of the first account for scoring a reference merchant and a first historical score value received by the reference merchant;
carrying out relevancy detection on the historical score and the first historical score to obtain a relevancy result between the historical score and the first historical score;
determining the weighting weight of the target score according to the relevancy result;
and generating a target score of the target merchant according to the weighted weight and the target score, wherein the target score is used for evaluating the target merchant.
2. The method of claim 1, wherein determining the weighted weight of the target score based on the relevancy results comprises:
when the relevancy result meets the relevancy requirement, determining the weighting weight of the target score according to the relevancy result;
when the relevancy result does not meet the relevancy requirement, performing dispersion degree inspection on a second historical score received by the target merchant to obtain a dispersion degree result of the second historical score; and determining the weighted weight of the target score according to the dispersion result.
3. The method of claim 2, wherein determining the weighted weight of the target score according to the dispersion result comprises:
when the dispersion result accords with a dispersion condition, carrying out frequency inspection on the frequency of the target score appearing in the historical score to obtain a frequency inspection result;
and determining the weighting weight of the target score according to the frequency test result.
4. The method of claim 3, wherein said determining said weighted weight of said target score based on said frequency test results comprises:
when the frequency detection result reaches a frequency threshold value, determining the weighting weight for carrying out weight reduction processing on the target score;
and when the frequency detection result does not reach the frequency threshold value, determining the weighting weight for weighting up the target score.
5. The method according to any one of claims 2 to 4, wherein before performing the dispersion test on the second historical score received by the target merchant, the method further comprises:
performing distribution inspection on the second historical score received by the target merchant to obtain a confidence interval in the second historical score;
when the target score is not within the confidence interval, performing the dispersion test on the second historical score received by the target merchant.
6. The method according to any one of claims 1 to 4, wherein the performing the relevancy detection on the historical score and the first historical score to obtain the relevancy result between the historical score and the first historical score comprises:
selecting n target first history scores from the first history scores,
determining a mean value of the n target first historical scores as a historical score average of the reference merchant;
and carrying out relevance detection on the n target first historical scores and the historical score by combining the historical scores to obtain a relevance result of the first historical scores and the historical score.
7. The method of claim 6, wherein selecting n target first historical scores from the first historical scores comprises:
and removing the first historical scores reaching a preset numerical threshold value to obtain the n target first historical scores.
8. An apparatus for generating a merchant score, the apparatus comprising:
the acquisition module is used for acquiring a target score for the first account to grade the target merchant;
the acquisition module is further configured to acquire a historical score value of the first account for scoring the reference merchant and a first historical score value received by the reference merchant;
the detection module is used for carrying out relevancy detection on the historical score and the first historical score to obtain a relevancy result between the historical score and the first historical score;
the determining module is used for determining the weighting weight of the target score according to the relevancy result;
and the generating module is used for generating a target score of the target merchant according to the weighted weight and the target score, wherein the target score is used for evaluating the target merchant.
9. A computer device, characterized in that the computer device comprises a processor and a memory, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored in the memory, and the at least one instruction, at least one program, a set of codes, or a set of instructions is loaded and executed by the processor to implement the generation method of merchant score according to any one of claims 1 to 7.
10. A computer-readable storage medium, having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the method of generating a merchant score as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911360033.6A CN111144941A (en) | 2019-12-25 | 2019-12-25 | Merchant score generation method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911360033.6A CN111144941A (en) | 2019-12-25 | 2019-12-25 | Merchant score generation method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111144941A true CN111144941A (en) | 2020-05-12 |
Family
ID=70520192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911360033.6A Pending CN111144941A (en) | 2019-12-25 | 2019-12-25 | Merchant score generation method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144941A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111949837A (en) * | 2020-08-18 | 2020-11-17 | 北京字节跳动网络技术有限公司 | Information processing method, information processing apparatus, electronic device, and storage medium |
| CN112035569A (en) * | 2020-08-14 | 2020-12-04 | 联动数科(北京)科技有限公司 | Merchant scoring method and system |
| CN112580887A (en) * | 2020-12-25 | 2021-03-30 | 百果园技术(新加坡)有限公司 | Weight determination method, device and equipment for multi-target fusion evaluation and storage medium |
| CN112684110A (en) * | 2020-12-14 | 2021-04-20 | 江西省蚕桑茶叶研究所(江西省经济作物研究所) | Tea sensory evaluation method based on favorite expressions |
| CN113592333A (en) * | 2021-08-07 | 2021-11-02 | 杭州找查科技有限公司 | Internet comprehensive scoring method, system and device and readable storage medium |
| CN113707308A (en) * | 2021-08-31 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Medical data analysis device and computer readable storage medium |
-
2019
- 2019-12-25 CN CN201911360033.6A patent/CN111144941A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112035569A (en) * | 2020-08-14 | 2020-12-04 | 联动数科(北京)科技有限公司 | Merchant scoring method and system |
| CN111949837A (en) * | 2020-08-18 | 2020-11-17 | 北京字节跳动网络技术有限公司 | Information processing method, information processing apparatus, electronic device, and storage medium |
| CN112684110A (en) * | 2020-12-14 | 2021-04-20 | 江西省蚕桑茶叶研究所(江西省经济作物研究所) | Tea sensory evaluation method based on favorite expressions |
| CN112580887A (en) * | 2020-12-25 | 2021-03-30 | 百果园技术(新加坡)有限公司 | Weight determination method, device and equipment for multi-target fusion evaluation and storage medium |
| CN112580887B (en) * | 2020-12-25 | 2023-12-01 | 百果园技术(新加坡)有限公司 | Weight determination method, device, equipment and storage medium for multi-target fusion evaluation |
| CN113592333A (en) * | 2021-08-07 | 2021-11-02 | 杭州找查科技有限公司 | Internet comprehensive scoring method, system and device and readable storage medium |
| CN113707308A (en) * | 2021-08-31 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Medical data analysis device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111144941A (en) | Merchant score generation method, device, equipment and readable storage medium | |
| Gao et al. | Evaluating user reputation in online rating systems via an iterative group-based ranking method | |
| CN109299356B (en) | Activity recommendation method and device based on big data, electronic equipment and storage medium | |
| US8725735B2 (en) | Information processing system, information processing method, program, and non-transitory information storage medium | |
| CN110945538A (en) | Automatic rule recommendation engine | |
| CN108345601A (en) | Search result ordering method and device | |
| US11775412B2 (en) | Machine learning models applied to interaction data for facilitating modifications to online environments | |
| CN110457595B (en) | Emergency alarm method, device, system, electronic equipment and storage medium | |
| CN106327230B (en) | Abnormal user detection method and equipment | |
| CN111754241A (en) | User behavior perception method, device, equipment and medium | |
| CN106408325A (en) | User consumption behavior prediction analysis method based on user payment information and system | |
| CN113076416A (en) | Information heat evaluation method and device and electronic equipment | |
| CN114270391A (en) | Quantifying privacy impact | |
| CN111858245A (en) | Abnormal data analysis method and device, electronic equipment and storage medium | |
| KR20070070062A (en) | Service evaluation method, system, and computer program product | |
| CN112116969B (en) | Information recommendation method and device, storage medium and computer equipment | |
| CN111340540B (en) | Advertisement recommendation model monitoring method, advertisement recommendation method and advertisement recommendation model monitoring device | |
| CN111177564B (en) | Product recommendation method and device | |
| CN112819476A (en) | Risk identification method and device, nonvolatile storage medium and processor | |
| CN115907906A (en) | Method and device for determining to-be-recommended article, storage medium and electronic equipment | |
| CN115641198A (en) | User operation method, device, electronic equipment and storage medium | |
| CN115271866A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN115481694A (en) | Data enhancement method, device, equipment and storage medium for training sample set | |
| CN111625720B (en) | Method, device, equipment and medium for determining execution strategy of data decision item | |
| CN107977413A (en) | Feature selection approach, device, computer equipment and the storage medium of user data |
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 |