CN111428963A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN111428963A CN111428963A CN202010108589.2A CN202010108589A CN111428963A CN 111428963 A CN111428963 A CN 111428963A CN 202010108589 A CN202010108589 A CN 202010108589A CN 111428963 A CN111428963 A CN 111428963A
- Authority
- CN
- China
- Prior art keywords
- data
- feature
- probability
- category
- negative
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000012549 training Methods 0.000 description 19
- 238000012360 testing method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000006399 behavior Effects 0.000 description 5
- 230000001186 cumulative effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a data processing method and a device, wherein the method comprises the following steps: counting first business data of a first type of personnel to form a forward feature library; counting second service data of the second type of personnel to form a negative characteristic library; constructing a naive Bayes classifier according to the positive feature library and the negative feature library; inputting the characteristic data of the person to be tested into a naive Bayes classifier to obtain a classification result; and if the data belong to the negative category, acquiring difference information between the feature data and the data in the positive feature library and sending the difference information to a preset terminal. According to the data processing method and device provided by the embodiment of the invention, the naive Bayes classifier is constructed according to the positive characteristic library and the negative characteristic library to identify the performance condition of the personnel to be tested and send corresponding difference information for reminding, so that the automatic acquisition of the personnel capacity information and the automatic reminding about the capacity difference condition are realized, and the real-time monitoring of the personnel capacity is realized.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a data processing method and device.
Background
With the continuous growth of the scale of enterprises, more and more new people are added. Many enterprises do not have perfect new people cultivation guiding systems, and more, the teacher-apprentice system is adopted to cultivate and guide new people to enter. Although the skill level of the master is generally higher, the teaching is limited to the difference of teaching abilities, some masters bring out "vain" professional skills high, and some masters bring out "vain" professional skills lower.
In addition, in a business, the ability level between employees is not uniform, and the employees usually have difficulty in recognizing the difference between themselves and other employees and are not aware of the defects of themselves. Therefore, how to automatically acquire information representing individual abilities so as to help guide employees with poor abilities to perform skill improvement in an automatic manner is a problem to be solved.
Disclosure of Invention
To solve the problems in the prior art, embodiments of the present invention provide a data processing method and apparatus.
In a first aspect, an embodiment of the present invention provides a data processing method, including: counting first business data of a first type of personnel within a preset time to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data; counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data; the first type of personnel is personnel with a first proportion preset before performance ranking, and the second type of personnel is personnel with a second proportion preset after performance ranking; constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category; processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data; and if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
Further, the preset feature items include: the method comprises the steps of service flow, user communication times, online duration of an operation platform, number of acquired user contact ways, times of unanswered users within preset waiting time, times of harassing users and times of losing lists.
Further, the constructing a naive bayes classifier according to the positive feature library and the negative feature library comprises: dividing the value intervals of the feature items; calculating a first probability of the positive category and a second probability of the negative category from the positive feature library and the negative feature library; calculating a third probability of each value interval under the positive category condition and a fourth probability of each value interval under the negative category condition; and acquiring the naive Bayes classifier for dividing the feature data belonging to the positive category or the negative category according to the first probability, the second probability, the third probability and the fourth probability.
Further, the inputting the feature data into the naive bayes classifier to obtain a classification result of the feature data comprises: acquiring the value range to which each feature item belongs in the feature data; according to each value interval, respectively obtaining the third probability corresponding to each value interval under the positive category condition and the fourth probability corresponding to each value interval under the negative category condition; acquiring a fifth probability of the forward category under the characteristic data condition according to the product of the first probability and each third probability; acquiring a sixth probability of the negative category under the characteristic data condition according to the product of the second probability and each fourth probability; if the fifth probability is greater than the sixth probability, the feature data belongs to the forward category; otherwise, the feature data belongs to the negative category.
Further, the difference information between the feature data and the data in the forward feature library is the difference information between the feature item in the feature data and the mean value of the corresponding feature item in the first statistical data; before the sending the gap information to a terminal corresponding to the person to be tested, the method further includes: setting a reminding triggering mode corresponding to each feature item, wherein the reminding triggering mode comprises a single triggering mode and/or a triggering mode based on a preset time window; if the triggering condition of the reminding triggering mode is met, the step of sending the gap information to a terminal corresponding to the to-be-tested person is executed; if the feature item set as the single triggering mode exists in the feature data and the first statistic data, reminding the user if a preset difference condition exists between the feature data and the first statistic data and the feature item; and for the feature item set as the trigger mode based on the preset time window, if the frequency of the feature data and the first statistic data about the preset difference situation of the feature item exceeds a preset frequency or the proportion of the preset difference situation exceeds a preset proportion, reminding.
Further, the sending the gap information to a terminal corresponding to the to-be-tested person includes: and sending the gap information to a terminal corresponding to the to-be-tested person through at least one of WeChat, short message or telephone.
Further, the method further comprises: and continuously updating and iterating the naive Bayes classifier through the accumulated service data.
In a second aspect, an embodiment of the present invention provides a data processing apparatus, including: a feature library construction module to: counting first business data of a first type of personnel within a preset time to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data; counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data; the first type of personnel is personnel with a first proportion preset before performance ranking, and the second type of personnel is personnel with a second proportion preset after performance ranking; a naive Bayes classifier construction module to: constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category; a classification module to: processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data; a notification module to: and if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method provided in the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method as provided in the first aspect.
According to the data processing method and device provided by the embodiment of the invention, the naive Bayes classifier is constructed according to the positive characteristic library and the negative characteristic library, the achievement condition of the personnel to be tested is identified by using the naive Bayes classifier, and corresponding difference information is sent for reminding, so that the automatic acquisition of the personnel capacity information and the automatic reminding about the capacity difference condition are realized, and the real-time monitoring of the personnel capacity is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a data processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data processing method according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating test results of a data processing method according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention;
fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of a data processing method according to an embodiment of the present invention. As shown in fig. 1, the method includes:
The first type of person is a person with a first predetermined percentage of performance ranking top, such as 20% top. Which service data the service data is may be determined according to the preset feature item. For example, when the method of the embodiment of the invention is applied to a real estate brokerage industry to test the ability of brokers, the feature items may include information such as service flow, number of times of communicating with users, online duration of an operation platform, number of times of obtaining user contact information, number of times of not replying users for a preset time, number of times of harassing users, and number of times of losing orders. The service data is service data that can be counted to obtain the feature items, such as information of obtaining a user contact information. The method comprises the steps of counting first business data in a preset time of a first type of personnel to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data. For example, the preset time period may be within 3 months.
And counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data. And the second type of personnel presets a second proportion of personnel after performance ranking, such as 20% of personnel after performance ranking. Of course, the first and second ratios are not necessarily the same. For example, the first type of person is 15% of those who rank top performance, and the second type of person is 20% of those who rank bottom performance.
102, constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category.
And taking the data in the positive direction feature library and the negative direction feature library as training samples to construct a naive Bayes classifier. The constructed naive Bayesian classifier is used for classifying data into two categories, namely a positive category and a negative category. Wherein the first statistical data in the training sample represents data of a better performing person belonging to a forward category; the second statistical data in the training sample represents data for a poorly performing person, belonging to the negative category.
And 103, processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data.
And carrying out the same statistical processing process on the business data of the person to be tested when the first statistical data and the second statistical data are obtained to obtain the characteristic data containing the characteristic items. The feature data is input into the naive Bayes classifier, and a classification result of the feature data can be obtained. The classification result of the feature data is the positive-going category or the negative-going category.
And 104, if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
And if the characteristic data belong to the negative category, the performance of the personnel to be tested corresponding to the characteristic data is not good. And taking data in a forward feature library as a benchmark, acquiring difference information between the feature data and the data in the forward feature library, and sending the difference information to a terminal corresponding to the to-be-tested person. The number of the terminals corresponding to the testers may be multiple, and for example, the terminals may include a terminal device of the testers themselves and a terminal device of the testers with teachers. Therefore, the person receiving the gap information can know which places and what kind of defects exist in the person to be tested. Of course, besides sending the gap information, a corresponding improvement suggestion can be sent to the terminal corresponding to the person to be tested.
According to the embodiment of the invention, the naive Bayes classifier is constructed according to the positive characteristic library and the negative characteristic library, and is used for identifying the performance condition of the personnel to be tested and sending corresponding difference information for reminding, so that the automatic acquisition of personnel capacity information and the automatic reminding of the capacity difference condition are realized, and the real-time monitoring of the personnel capacity is realized.
Further, based on the above embodiment, the preset feature items include: the method comprises the following steps of service flow, user communication times, online duration of an operation platform, number of acquired user contact ways, times of unanswered users above a preset time, times of harassing users and times of losing lists.
On the basis of the embodiment, the embodiment of the invention improves the accuracy of the capacity evaluation of the house broker by reasonably setting the feature item data for evaluating the performance of the house broker.
Further, based on the foregoing embodiment, the constructing a naive bayes classifier according to the positive feature library and the negative feature library includes: dividing the value intervals of the feature items; calculating a first probability of the positive category and a second probability of the negative category from the positive feature library and the negative feature library; calculating a third probability of each value interval under the positive category condition and a fourth probability of each value interval under the negative category condition; and acquiring the naive Bayes classifier for dividing the feature data belonging to the positive category or the negative category according to the first probability, the second probability, the third probability and the fourth probability.
The process of constructing a naive bayes classifier according to the positive feature library and the negative feature library is explained by taking the feature items for evaluating the capacity of the house broker, which are provided by the above, as examples, including the number of times of communication with the user, the online time of the operation platform and the number of the obtained user contact ways.
Firstly, dividing the value range of the characteristic item. Such as:
the communication times a with the user are divided into: { a <20, 20< a <100, a > -100 };
the online time b of the operation platform is divided into: { b <100 h,100h < b <500h, a > -500 h };
the number c of the acquired contact information of the user is divided into: { c < ═ 5,5< c <20, c > -20 }.
Calculating a first probability for the positive category and a second probability for the negative category based on the positive feature library and the negative feature library. Let the positive category be denoted c1 and the negative category be denoted c2, i.e. P (c1) and P (c2) are calculated, respectively. If the number of the first statistical data is d1 and the number of the second statistical data is d2, P (c1) can be obtained by d1/(d1+ d2), and P (c2) can be obtained by d2/(d1+ d 2).
And calculating a third probability of each value interval under the forward category condition. That is, P (a ═ 20| c1), P (20< a <100| c1), P (a > ═ 100| c1), P (b ═ 100h | c1), P (100h < b <500h | c1), P (a > ═ 500h | c1), P (c ═ 5| c1), P (5< c <20| c1), and P (c > ═ 20| c1) are calculated, respectively. If the number of the occurrences of a < ═ 20 in the first statistical data is d3, P (a < ═ 20| c1) can be obtained by d3/d 1. By analogy, the third probabilities of the other value intervals under the forward category condition can be obtained.
And calculating the fourth probability of each value interval under the negative category condition. That is, P (a ═ 20| c2), P (20< a <100| c2), P (a > ═ 100| c2), P (b ═ 100h | c2), P (100h < b <500h | c2), P (a > ═ 500h | c2), P (c ═ 5| c2), P (5< c <20| c2), and P (c > ═ 20| c2) are calculated, respectively. If the number of the occurrences of a < ═ 20 in the first statistical data is d4, P (a < ═ 20| c2) can be obtained by d4/d 2. By analogy, the fourth probabilities of the other value intervals under the forward category condition can be obtained.
And obtaining the first probability, the second probability, the third probability and the fourth probability to obtain the naive Bayes classifier for dividing the characteristic data belonging to the positive category or the negative category. The first probability and the third probability can be used for solving the probability that the feature data of the person to be tested belongs to the forward category. The second probability and the fourth probability may be used to determine a probability that the feature data of the person to be tested belongs to a negative category. The category corresponding to the one with the larger probability is the category to which the feature data belongs.
On the basis of the embodiment, the naive Bayes classifier is constructed by dividing the value intervals of the feature items and solving the first probability, the second probability, the third probability and the fourth probability, so that the reliability and the classification accuracy of the naive Bayes classifier are improved, and the accuracy of the personal ability test result is improved.
Further, based on the foregoing embodiment, the inputting the feature data into the naive bayes classifier to obtain a classification result of the feature data includes: acquiring the value range to which each feature item belongs in the feature data; according to each value interval, respectively obtaining the third probability corresponding to each value interval under the positive category condition and the fourth probability corresponding to each value interval under the negative category condition; acquiring a fifth probability of the forward category under the characteristic data condition according to the product of the first probability and each third probability; acquiring a sixth probability of the negative category under the characteristic data condition according to the product of the second probability and each fourth probability; if the fifth probability is greater than the sixth probability, the feature data belongs to the forward category; otherwise, the feature data belongs to the negative category.
For example, if the service data of the person to be tested is processed to obtain feature data including the feature items, where a is 20, b is 400h, and c is 1, the value-taking interval to which each feature item belongs in the feature data is first obtained. According to the division condition, corresponding to the characteristic item a, the value range is a < ═ 20; corresponding to the characteristic item b, the value interval is 100h < b <500 h; and corresponding to the characteristic item c, the value range is c < 5.
And respectively acquiring the third probability corresponding to each value interval under the forward category condition according to each value interval. That is, P (a <20| c1), P (100h < b <500h | c1), and P (c < 5| c1) are obtained, respectively. And acquiring the fourth probability corresponding to each value interval under the negative category condition according to each value interval. That is, P (a <20| c2), P (100h < b <500h | c2), and P (c < 5| c2) are obtained, respectively.
And acquiring a fifth probability of the forward category under the characteristic data condition according to the product of the first probability and each third probability. The fifth probability is a product of the first probability and each of the third probabilities. For example, in this embodiment, the fifth probability takes the value of P (c1) · P (a < ═ 20| c1) · P (100h < b <500h | c1) · P (c < ═ 5| c 1).
And acquiring a sixth probability of the negative category under the characteristic data condition according to the product of the second probability and each fourth probability. The sixth probability is a product of the second probability and each of the fourth probabilities. For example, in the present embodiment, the value of the sixth probability is P (c2) · P (a < ═ 20| c2) · P (100h < b <500h | c2) · P (c < ═ 5| c 2).
The results of the above-mentioned P (c1), P (a <20| c1), P (100h < b <500h | c1), P (c < 5| c1), P (c2), P (a <20| c2), P (100h < b <500h | c2), and P (c < 5| c2) are already stored in the trained naive bayes classifier and can be directly obtained.
Judging the magnitude relation between a fifth probability and a sixth probability, and if the fifth probability is greater than the sixth probability, the feature data belongs to the forward category; otherwise, the feature data belongs to the negative category.
On the basis of the above embodiment, in the embodiment of the present invention, the third probability and the fourth probability are obtained according to the feature data, the fifth probability that the feature data is in the positive category is obtained according to the first probability and the third probability, the sixth probability that the feature data is in the negative category is obtained according to the second probability and the fourth probability, and the final classification result is obtained by comparing the fifth probability and the sixth probability, so that the accuracy of the feature data classification of the tested person is improved, and the accuracy of the personal ability test is further improved.
Further, based on the above embodiment, the difference information between the feature data and the data in the forward feature library is the difference information between the feature item in the feature data and the mean value of the corresponding feature item in the first statistical data; before the sending the gap information to a terminal corresponding to the person to be tested, the method further includes: setting a reminding triggering mode corresponding to each feature item, wherein the reminding triggering mode comprises a single triggering mode and/or a triggering mode based on a preset time window; if the triggering condition of the reminding triggering mode is met, the step of sending the gap information to a terminal corresponding to the to-be-tested person is executed; if the feature item set as the single triggering mode exists in the feature data and the first statistic data, reminding the user if a preset difference condition exists between the feature data and the first statistic data and the feature item; and for the feature item set as the trigger mode based on the preset time window, if the frequency of the feature data and the first statistic data about the preset difference situation of the feature item exceeds a preset frequency or the proportion of the preset difference situation exceeds a preset proportion, reminding.
The mean of the feature terms in the first statistical data may reflect the general data indicators of the better performing broker. Taking the example that the feature items comprise the number of times of communicating with the user, the number of acquired user contact ways and the number of times of losing the order, the average values of the corresponding feature items in the first statistical data are the average value of the number of times of communicating with the user, the average value of the number of acquired user contact ways and the average value of the number of times of losing the order respectively.
And the difference information between the feature data and the data in the forward feature library is the difference information between the feature items in the feature data and the mean values of the corresponding feature items in the first statistic data. The gap information represents the situation that the feature data is inconsistent with the first statistical data about one or some feature items. The inconsistent performance includes that the value of the corresponding characteristic item in the characteristic data is larger than the value of the corresponding characteristic item in the first statistical data, and the value of the corresponding characteristic item in the characteristic data is smaller than the value of the corresponding characteristic item in the first statistical data.
However, different feature items have different meanings, so that the performance is different when the value is large or small. For example, the larger the number of contact details of the user is, the better the number of times the user is lost is, the smaller the number of times the user is lost is, the better the number of times the user is lost is. Therefore, for different feature items, a gap condition for triggering a reminder, i.e., the preset gap condition, needs to be preset. For example, the preset gap condition for obtaining the number of the contact ways of the user may be set to be that a value in the feature data is smaller than a value in the first statistical data; for the lost single number, the preset difference condition can be set to be that the value in the characteristic data is larger than the value in the first statistical data.
When the preset gap situation of the corresponding characteristic item occurs, reminding can be carried out according to a reminding triggering mode preset with the corresponding characteristic item, and the gap information is sent to the terminal corresponding to the tested person. The reminding triggering mode can be a single triggering mode or a triggering mode based on a preset time window. And for the feature item set as the single triggering mode, if the feature data and the first statistic data have a preset gap with respect to the feature item, the prompt is given, and the method is suitable for the particularly serious and infrequent situation. For general feature items, the reminding mode may be set as a trigger mode based on a preset time window, for example, a first threshold of the cumulative occurrence number may be set, and when the cumulative occurrence number is greater than the first threshold, the reminding is performed. Or setting a second threshold value of the ratio of the cumulative occurrence times to the total test times, and reminding when the ratio of the cumulative occurrence times to the total test times is greater than the second threshold value.
On the basis of the embodiment, the embodiment of the invention improves the flexibility and rationality of reminding by setting a single trigger mode and/or a trigger mode based on a preset time window.
Further, based on the above embodiment, the sending the gap information to a terminal corresponding to the person to be tested includes: and sending the gap information to a terminal corresponding to the to-be-tested person through at least one of WeChat, short message or telephone.
When the difference information is sent to the terminal corresponding to the to-be-tested person, the difference information can be sent to the terminal corresponding to the to-be-tested person in the forms of WeChat, short message or telephone. The communication tool may be a self-research tool or a third-party tool.
On the basis of the embodiment, the embodiment of the invention transmits the gap information to the terminal corresponding to the to-be-tested person through at least one of WeChat, short message or telephone, thereby improving the flexibility of transmitting the reminding information.
Further, based on the above embodiment, the method further includes: and continuously updating and iterating the naive Bayes classifier through the accumulated service data.
The model construction and model training at the early stage of the system need multiple times of tuning and debugging, the capability can not be formed in a short time, and a process of constructing and accumulating data for a long time is needed. For example, when more data is accumulated, more training data can be added to train and optimize the naive Bayes classifier. The training samples can also be updated over time to retrain the model, so that the constructed naive Bayes classifier is more adaptive to the current situation.
On the basis of the embodiment, the embodiment of the invention continuously updates the iterative naive Bayes classifier by the accumulated service data, thereby ensuring the classification performance of the naive Bayes classifier.
Fig. 2 is a schematic diagram of a data processing method according to an embodiment of the present invention. The data processing method provided by the embodiment of the invention is further described below with reference to fig. 2 by taking the test applied to the real estate domain broker as an example.
The embodiment of the invention tracks, collects and models the daily business logs of the brokers according to the broker operation platforms (L INK and A +), counts, models and contrastively analyzes the model difference of the business behavior data of the master exceller and the Caomi brother, quantifies the business skill difference, guides the Caomi brother to rapidly master the professional skill, better serves the clients and improves the performance and income of the clients.
Collecting, counting and modeling service platform operation logs of brokers 20% before performance ranking to form a 'forward behavior' feature library; and collecting, counting and modeling service platform operation logs of 20% of brokers after the performance ranking to form a 'negative behavior' feature library. And processing the business operation data of the newly-entered broker or the poorly-performed broker every week, comparing the business operation data with a positive characteristic library and a negative characteristic library, seeing which characteristic library the broker belongs to and what differences exist, and informing the broker and the master of the differences to perform targeted correction and improvement.
The method comprises the following specific steps:
1) collecting operation logs of the broker operation platform (L INK and A +), and collecting more than 100 important business interface data of the operation platform according to the dimension and the operation frequency of the broker.
2) Data statistics and model item definition;
3) model construction
A. Forward library model:
counting the operation data of the service platform of nearly 3 months of the brokers with 20% of the performance ranking, and constructing a feature library;
B. negative reservoir model
Counting the operation data of the service platform of nearly 3 months of 20% of brokers after the performance ranking, and constructing a feature library;
the data in the feature library includes: the method comprises the following steps of (1) daily 'important' business flow, user communication times, operation platform 'online' time length, number of acquired user contact ways, times of un-replied clients for more than 5 minutes, 'harassment' user times, 'list losing' times and the like;
4) model training
Training the model by taking data of a new job broker and a broker service platform with poor performance; after several rounds of model training, the model is gradually formed and perfected.
5) Setting reminder thresholds, providing improved suggestions
And setting a specific triggering mode and a threshold value of each reminding rule. There are generally two ways of a single trigger and based on a certain time window.
Single trigger mode: hitting a rule, i.e., violating the rule, applies to a particularly serious and uncommon type of error.
Setting mode based on time window: based on the cumulative behavior over a certain time period. The method is suitable for most alarm rules. In this mode, the size of the time window may be set.
And setting a statistical mode and a reminding threshold value of log accumulation based on a time window.
An abnormal log statistical mode: 1. single bar accumulation mode 2, and a statistical mode based on proportion, namely the ratio of the number and the total call volume.
And (3) reminding a threshold value: and setting the threshold size according to the severity and the influence range. According to the statistical manner of the above abnormal logs, the threshold value can be set in two manners of a number and a percentage.
6) And setting a reminding information delivery mode when each reminding rule is triggered, short message reminding, L INK & A +, IM (instant messaging) reminding or WeChat reminding.
In fig. 2, the service platform system is configured to collect service operation log data of all brokers, and record log service operation of each broker according to dimensions such as users and services. Broker business capability system: the main functions include model construction, model training and reminder and suggestion functions. Each function will be described below.
1, model construction:
1.1, according to the broker and the service dimension, the log is standardized and defined by data items to form service broker basic data and statistical data Document.
1.2 classify Category to the normalized data of the log system.
1.3. Modeling the positive library model and the negative library model by adopting a Bayesian classifier.
1.3.1 general overview of the concept
-formula P (Category | Category) ═ P (Category | Category) × (Category)/P (Category));
-naive bayes classifier: p (c | d) to P (c) × P (d | c);
-a training phase: estimating prior conditional probability P (W _ k | C _ i) and probability P (C _ i) for each W _ k, C _ i; w _ k represents an element in the training document; c _ i represents the ith classification;
-a classification phase: calculating the posterior probability, and returning the class which maximizes the posterior probability;
--C(d)＝argmax{P(C_i)*P(d|C_i)；
for a new training document d, which of the above four classes belongs to, the object can be changed into a specific object only at this moment according to the bayesian formula.
> P (Category | Document): testing the probability that a document belongs to a certain class;
> P (Category)): a document d is randomly drawn from the document space, with a probability of belonging to category c. (number of documents of a certain type/total number of documents);
p (Document | Category), the probability (number of words in a Document of a class/total number of words in a class) of a Document d for a given class c;
> P (document): randomly extracting the probability of a document d from the document space (the same for each category, and neglecting not calculating, in this case, solving the maximum likelihood probability);
- > C (d) ═ argmax { P (C _ i) × P (d | C _ i) }: and (4) solving the probability of each class of the approximate Bayes, comparing to obtain the maximum probability, and classifying the documents successfully when the documents are classified into the class with the maximum probability.
To sum up: the process of constructing the training classifier model for the training set is essentially the solution of the parametric model. Then, the parameters are used in a prediction method, and the document classification can be completed by acquiring the maximum probability according to a formula.
1.3.2 formula derivation and resolution
Naive bayes formula: (assuming that when the document d belongs to the class c, the value of the element w in the document d and the value of the element w in the class c are in an independent relation [ actually displayed is not independent, an approximate process ])
And (3) formula analysis:
> P (d): randomly extracting the probability of a document d from the document space (the same for each category, and neglecting not calculating, in this case, solving the maximum likelihood probability);
> P (c): a document d is randomly drawn from the document space, with a probability of belonging to category c. (number of documents of a certain type/total number of documents);
p (d | c) the probability (number of words in a document of a class/total number of words in a class) of a document d for a given class c;
a > document vector, d ═ w1, w2,.. ang., wn };
a > class set, c ═ c1, c2.
> P (c | d): probability (estimated conditional probability) that test document d belongs to a certain class c [ estimated probability: the training process is carried out in a training set under certain assumed conditions;
> MaxP (c | d): the maximum probability that a test document d belongs to a certain class c.
2, model training:
fig. 3 is a schematic diagram of a test result of the data processing method according to an embodiment of the present invention. Assuming that c1 is a positive bank and c2 is a negative bank, the probability that the data point (x, y) belongs to the category c1 (the probability of a circle in fig. 3) is denoted by P (c1| x, y), and the probability that the data point (x, y) belongs to the category c2 (the probability of a triangle in fig. 3) is denoted by P (c2| x, y). Then for a new data point (x, y), its classification can be determined using the following rule.
If p (c1| x, y) > p (c2| x, y), the category is c1.
If p (c2| x, y) > p (c1| x, y), the category is c2.
That is, a class corresponding to a high probability is selected as the classification class. I.e. the decision with the highest probability is chosen to which class the broker belongs.
3 reminding and suggesting:
and (4) comparing the data of the broker service platform with the new working economy and poor performance every week according to the model, seeing where the broker is improved and where the broker is not improved, and setting a reminding threshold value to perform targeted prompt (service prompt improvement) on the broker below the threshold value.
The embodiment of the invention has the advantages or technical innovation points that:
1. the embodiment of the invention uniformly models the daily business behaviors of an excellent broker and a non-excellent broker according to big data thought and form; the broker cultivation can be more unified, normalized and standardized, and meanwhile, targeted suggestions and real-time monitoring can be promoted for the business of the broker.
2. The model construction and model training at the early stage of the system need multiple times of tuning and debugging, the capability can not be formed in a short time, and a process of constructing and accumulating data for a long time is needed.
Fig. 4 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention. As shown in fig. 4, the apparatus includes a feature library construction module 10, a naive bayes classifier construction module 20, a classification module 30, and a notification module 40, wherein: the feature library building module 10 is configured to: counting first business data of a first type of personnel within a preset time to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data; counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data; the first type of personnel is personnel with a first proportion preset before performance ranking, and the second type of personnel is personnel with a second proportion preset after performance ranking; the naive bayes classifier building module 20 is configured to: constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category; the classification module 30 is configured to: processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data; the notification module 40 is configured to: and if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
According to the embodiment of the invention, the naive Bayes classifier is constructed according to the positive characteristic library and the negative characteristic library, and is used for identifying the performance condition of the personnel to be tested and sending corresponding difference information for reminding, so that the automatic acquisition of personnel capacity information and the automatic reminding of the capacity difference condition are realized, and the real-time monitoring of the personnel capacity is realized.
Further, based on the above embodiment, the preset feature items include: the method comprises the steps of service flow, user communication times, online duration of an operation platform, number of acquired user contact ways, times of unanswered users within preset waiting time, times of harassing users and times of losing lists.
On the basis of the embodiment, the embodiment of the invention improves the accuracy of the capacity evaluation of the house broker by reasonably setting the feature item data for evaluating the performance of the house broker.
Further, based on the above embodiment, when the naive bayes classifier construction module 20 is configured to construct a naive bayes classifier according to the positive feature library and the negative feature library, it is specifically configured to: dividing the value intervals of the feature items; calculating a first probability of the positive category and a second probability of the negative category from the positive feature library and the negative feature library; calculating a third probability of each value interval under the positive category condition and a fourth probability of each value interval under the negative category condition; and acquiring the naive Bayes classifier for dividing the feature data belonging to the positive category or the negative category according to the first probability, the second probability, the third probability and the fourth probability.
On the basis of the embodiment, the naive Bayes classifier is constructed by dividing the value intervals of the feature items and solving the first probability, the second probability, the third probability and the fourth probability, so that the reliability and the classification accuracy of the naive Bayes classifier are improved, and the accuracy of the personal ability test result is improved.
Further, based on the above embodiment, when the classification module 30 is configured to input the feature data into the naive bayes classifier and obtain the classification result of the feature data, it is specifically configured to: acquiring the value range to which each feature item belongs in the feature data; according to each value interval, respectively obtaining the third probability corresponding to each value interval under the positive category condition and the fourth probability corresponding to each value interval under the negative category condition; acquiring a fifth probability of the forward category under the characteristic data condition according to the product of the first probability and each third probability; acquiring a sixth probability of the negative category under the characteristic data condition according to the product of the second probability and each fourth probability; if the fifth probability is greater than the sixth probability, the feature data belongs to the forward category; otherwise, the feature data belongs to the negative category.
On the basis of the above embodiment, in the embodiment of the present invention, the third probability and the fourth probability are obtained according to the feature data, the fifth probability that the feature data is in the positive category is obtained according to the first probability and the third probability, the sixth probability that the feature data is in the negative category is obtained according to the second probability and the fourth probability, and the final classification result is obtained by comparing the fifth probability and the sixth probability, so that the accuracy of the feature data classification of the tested person is improved, and the accuracy of the personal ability test is further improved.
Further, based on the above embodiment, the difference information between the feature data and the data in the forward feature library is the difference information between the feature item in the feature data and the mean value of the corresponding feature item in the first statistical data; the method further includes a reminding setting module, before the notifying module 40 sends the gap information to the terminal corresponding to the to-be-tested person, configured to: setting a reminding triggering mode corresponding to each feature item, wherein the reminding triggering mode comprises a single triggering mode and/or a triggering mode based on a preset time window; if the triggering condition of the reminding triggering mode is met, triggering the notification module 40 again to send the gap information to the terminal corresponding to the to-be-tested person; if the feature item set as the single triggering mode exists in the feature data and the first statistic data, reminding the user if a preset difference condition exists between the feature data and the first statistic data and the feature item; and for the feature item set as the trigger mode based on the preset time window, if the frequency of the feature data and the first statistic data about the preset difference situation of the feature item exceeds a preset frequency or the proportion of the preset difference situation exceeds a preset proportion, reminding.
On the basis of the embodiment, the embodiment of the invention improves the flexibility and rationality of reminding by setting a single trigger mode and/or a trigger mode based on a preset time window.
Further, based on the above embodiment, when the notifying module 40 is configured to send the gap information to the terminal corresponding to the to-be-tested person, it is specifically configured to: and sending the gap information to a terminal corresponding to the to-be-tested person through at least one of WeChat, short message or telephone.
On the basis of the embodiment, the embodiment of the invention transmits the gap information to the terminal corresponding to the to-be-tested person through at least one of WeChat, short message or telephone, thereby improving the flexibility of transmitting the reminding information.
Further, based on the above embodiment, the apparatus further includes an iterative update module, where the iterative update module is configured to: and continuously updating and iterating the naive Bayes classifier through the accumulated service data.
On the basis of the embodiment, the embodiment of the invention continuously updates the iterative naive Bayes classifier by the accumulated service data, thereby ensuring the classification performance of the naive Bayes classifier.
The apparatus provided in the embodiment of the present invention is used for the method, and specific functions may refer to the method flow described above, which is not described herein again.
Fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 5, the electronic device may include: a processor (processor)510, a communication Interface (Communications Interface)520, a memory (memory)530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may call logic instructions in memory 530 to perform the following method: counting first business data of a first type of personnel within a preset time to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data; counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data; the first type of personnel is personnel with a first proportion preset before performance ranking, and the second type of personnel is personnel with a second proportion preset after performance ranking; constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category; processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data; and if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to perform the method provided by the foregoing embodiments, for example, including: counting first business data of a first type of personnel within a preset time to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data; counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data; the first type of personnel is personnel with a first proportion preset before performance ranking, and the second type of personnel is personnel with a second proportion preset after performance ranking; constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category; processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data; and if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
The above-described embodiments of the apparatus are merely illustrative, and 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A data processing method, comprising:
counting first business data of a first type of personnel within a preset time to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data; counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data; the first type of personnel is personnel with a first proportion preset before performance ranking, and the second type of personnel is personnel with a second proportion preset after performance ranking;
constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category;
processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data;
and if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
2. The data processing method according to claim 1, wherein the preset feature items comprise:
the method comprises the steps of service flow, user communication times, online duration of an operation platform, number of acquired user contact ways, times of unanswered users within preset waiting time, times of harassing users and times of losing lists.
3. The data processing method of claim 1, wherein constructing a naive bayes classifier from the positive feature library and the negative feature library comprises:
dividing the value intervals of the feature items;
calculating a first probability of the positive category and a second probability of the negative category from the positive feature library and the negative feature library;
calculating a third probability of each value interval under the positive category condition and a fourth probability of each value interval under the negative category condition;
and acquiring the naive Bayes classifier for dividing the feature data belonging to the positive category or the negative category according to the first probability, the second probability, the third probability and the fourth probability.
4. The data processing method of claim 3, wherein the inputting the feature data into the naive Bayes classifier to obtain the classification result of the feature data comprises:
acquiring the value range to which each feature item belongs in the feature data;
according to each value interval, respectively obtaining the third probability corresponding to each value interval under the positive category condition and the fourth probability corresponding to each value interval under the negative category condition;
acquiring a fifth probability of the forward category under the characteristic data condition according to the product of the first probability and each third probability; acquiring a sixth probability of the negative category under the characteristic data condition according to the product of the second probability and each fourth probability;
if the fifth probability is greater than the sixth probability, the feature data belongs to the forward category; otherwise, the feature data belongs to the negative category.
5. The data processing method according to claim 1, wherein the difference information between the feature data and the data in the forward feature library is difference information between the feature item in the feature data and a mean value of the corresponding feature item in the first statistical data; before the sending the gap information to a terminal corresponding to the person to be tested, the method further includes:
setting a reminding triggering mode corresponding to each feature item, wherein the reminding triggering mode comprises a single triggering mode and/or a triggering mode based on a preset time window; if the triggering condition of the reminding triggering mode is met, the step of sending the gap information to a terminal corresponding to the to-be-tested person is executed;
if the feature item set as the single triggering mode exists in the feature data and the first statistic data, reminding the user if a preset difference condition exists between the feature data and the first statistic data and the feature item; and for the feature item set as the trigger mode based on the preset time window, if the frequency of the feature data and the first statistic data about the preset difference situation of the feature item exceeds a preset frequency or the proportion of the preset difference situation exceeds a preset proportion, reminding.
6. The data processing method of claim 1, wherein the sending the gap information to a terminal corresponding to the person to be tested comprises: and sending the gap information to a terminal corresponding to the to-be-tested person through at least one of WeChat, short message or telephone.
7. The data processing method of claim 1, wherein the method further comprises:
and continuously updating and iterating the naive Bayes classifier through the accumulated service data.
8. A data processing apparatus, comprising:
a feature library construction module to: counting first business data of a first type of personnel within a preset time to obtain first statistical data containing preset feature items, and forming a forward feature library by the first statistical data; counting second service data of a second type of personnel within the preset time to obtain second statistical data containing the characteristic items, and forming a negative characteristic library by the second statistical data; the first type of personnel is personnel with a first proportion preset before performance ranking, and the second type of personnel is personnel with a second proportion preset after performance ranking;
a naive Bayes classifier construction module to: constructing a naive Bayes classifier according to the positive feature library and the negative feature library; wherein the first statistical data belongs to a positive category and the second statistical data belongs to a negative category;
a classification module to: processing the service data of the person to be tested to obtain feature data containing the feature items, inputting the feature data into the naive Bayes classifier, and obtaining a classification result of the feature data;
a notification module to: and if the characteristic data belong to the negative category, acquiring difference information between the characteristic data and data in the positive characteristic library, and sending the difference information to a terminal corresponding to the to-be-tested person.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the data processing method according to any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the data processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010108589.2A CN111428963B (en) | 2020-02-21 | 2020-02-21 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010108589.2A CN111428963B (en) | 2020-02-21 | 2020-02-21 | Data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111428963A true CN111428963A (en) | 2020-07-17 |
| CN111428963B CN111428963B (en) | 2023-12-19 |
Family
ID=71547083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010108589.2A Active CN111428963B (en) | 2020-02-21 | 2020-02-21 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111428963B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112163633A (en) * | 2020-10-14 | 2021-01-01 | 北京嘀嘀无限科技发展有限公司 | Test evaluation method and device, electronic equipment and storage medium |
| CN112396114A (en) * | 2020-11-20 | 2021-02-23 | 中国科学院深圳先进技术研究院 | Evaluation system, evaluation method and related product |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105869088A (en) * | 2016-04-18 | 2016-08-17 | 李隆帜 | Teaching quality evaluation system based on online education |
| CN106127634A (en) * | 2016-06-20 | 2016-11-16 | 山东师范大学 | A kind of Forecasting The Scores method and system based on model-naive Bayesian |
| CN106168976A (en) * | 2016-07-14 | 2016-11-30 | 武汉斗鱼网络科技有限公司 | A kind of specific user's method for digging based on NB Algorithm and system |
| US20170060578A1 (en) * | 2015-09-01 | 2017-03-02 | Hcl Technologies Limited | System and method for evaluating human resources in a software development environment |
| CN107563633A (en) * | 2017-08-28 | 2018-01-09 | 平安科技（深圳）有限公司 | A kind of performance indicators examination appraisal procedure, equipment and storage medium |
| CN108876104A (en) * | 2018-05-07 | 2018-11-23 | 广东电网有限责任公司 | A kind of power factor wire examination method and device |
| CN109064023A (en) * | 2018-08-02 | 2018-12-21 | 锐思达(广州)信息科技有限公司 | A kind of method and apparatus of manpower potency management system |
| CN109146116A (en) * | 2018-06-13 | 2019-01-04 | 浙江大学 | A kind of construction method of ability to work model, its calculation method of parameters, and labour's assessment prediction device based on the model |
| CN109214446A (en) * | 2018-08-27 | 2019-01-15 | 平安科技（深圳）有限公司 | Potentiality good performance personnel kind identification method, system, terminal and computer readable storage medium |
| CN109284897A (en) * | 2018-08-20 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Employee performance wire examination method, device, computer equipment and storage medium |
| CN109523056A (en) * | 2018-10-12 | 2019-03-26 | 中国平安人寿保险股份有限公司 | Object ability classification prediction technique and device, electronic equipment, storage medium |
| CN110298472A (en) * | 2018-03-23 | 2019-10-01 | 国际商业机器公司 | Predict employee's performance metric |
| CN110458389A (en) * | 2019-06-28 | 2019-11-15 | 平安科技（深圳）有限公司 | User data processing method, device, computer installation and storage medium |
-
2020
- 2020-02-21 CN CN202010108589.2A patent/CN111428963B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170060578A1 (en) * | 2015-09-01 | 2017-03-02 | Hcl Technologies Limited | System and method for evaluating human resources in a software development environment |
| CN105869088A (en) * | 2016-04-18 | 2016-08-17 | 李隆帜 | Teaching quality evaluation system based on online education |
| CN106127634A (en) * | 2016-06-20 | 2016-11-16 | 山东师范大学 | A kind of Forecasting The Scores method and system based on model-naive Bayesian |
| CN106168976A (en) * | 2016-07-14 | 2016-11-30 | 武汉斗鱼网络科技有限公司 | A kind of specific user's method for digging based on NB Algorithm and system |
| CN107563633A (en) * | 2017-08-28 | 2018-01-09 | 平安科技（深圳）有限公司 | A kind of performance indicators examination appraisal procedure, equipment and storage medium |
| CN110298472A (en) * | 2018-03-23 | 2019-10-01 | 国际商业机器公司 | Predict employee's performance metric |
| CN108876104A (en) * | 2018-05-07 | 2018-11-23 | 广东电网有限责任公司 | A kind of power factor wire examination method and device |
| CN109146116A (en) * | 2018-06-13 | 2019-01-04 | 浙江大学 | A kind of construction method of ability to work model, its calculation method of parameters, and labour's assessment prediction device based on the model |
| CN109064023A (en) * | 2018-08-02 | 2018-12-21 | 锐思达(广州)信息科技有限公司 | A kind of method and apparatus of manpower potency management system |
| CN109284897A (en) * | 2018-08-20 | 2019-01-29 | 中国平安人寿保险股份有限公司 | Employee performance wire examination method, device, computer equipment and storage medium |
| CN109214446A (en) * | 2018-08-27 | 2019-01-15 | 平安科技（深圳）有限公司 | Potentiality good performance personnel kind identification method, system, terminal and computer readable storage medium |
| CN109523056A (en) * | 2018-10-12 | 2019-03-26 | 中国平安人寿保险股份有限公司 | Object ability classification prediction technique and device, electronic equipment, storage medium |
| CN110458389A (en) * | 2019-06-28 | 2019-11-15 | 平安科技（深圳）有限公司 | User data processing method, device, computer installation and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112163633A (en) * | 2020-10-14 | 2021-01-01 | 北京嘀嘀无限科技发展有限公司 | Test evaluation method and device, electronic equipment and storage medium |
| CN112396114A (en) * | 2020-11-20 | 2021-02-23 | 中国科学院深圳先进技术研究院 | Evaluation system, evaluation method and related product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111428963B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10776708B2 (en) | Analyzing behavior in light of social time | |
| US20170372351A1 (en) | Dynamic state-space modeling based on contextual and behavioral factors | |
| US20180308160A1 (en) | Risk assessment method and system | |
| CN111383101A (en) | Post-loan risk monitoring method, device, equipment and computer-readable storage medium | |
| CN112989332B (en) | Abnormal user behavior detection method and device | |
| US10860942B2 (en) | Analyzing behavior in light of social time | |
| CN111428963B (en) | Data processing method and device | |
| CN112765003B (en) | Risk prediction method based on APP behavior log | |
| CN111967655A (en) | Short-term load prediction method and system | |
| US11743281B1 (en) | Microservices anomaly detection | |
| CN111309706A (en) | Model training method and device, readable storage medium and electronic equipment | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN107357703B (en) | Terminal application power consumption detection method and server | |
| CN114090385A (en) | Monitoring and early warning method, device and equipment for service running state | |
| CN111431791B (en) | Instant communication message identification method and system | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN115438885A (en) | Method, device, equipment and storage medium for detecting abnormal fluctuation of service | |
| CN110688273B (en) | Classification model monitoring method and device, terminal and computer storage medium | |
| CN110458707B (en) | Behavior evaluation method and device based on classification model and terminal equipment | |
| CN112308294A (en) | Default probability prediction method and device | |
| Watanabe et al. | Failure prediction for cloud datacenter by hybrid message pattern learning | |
| CN110766544A (en) | Credit risk detection method and device, storage medium and electronic device | |
| CN117156466B (en) | Customized management evaluation system for short message service module | |
| Alberts et al. | Churn Prediction in the Mobile Telecommunications Industry | |
| CN114638534A (en) | Risk processing method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |