CN111160778A - Outbound project auditing and evaluating method and system based on big data and computer equipment - Google Patents
Outbound project auditing and evaluating method and system based on big data and computer equipment Download PDFInfo
- Publication number
- CN111160778A CN111160778A CN201911396575.9A CN201911396575A CN111160778A CN 111160778 A CN111160778 A CN 111160778A CN 201911396575 A CN201911396575 A CN 201911396575A CN 111160778 A CN111160778 A CN 111160778A
- Authority
- CN
- China
- Prior art keywords
- project
- outbound
- text
- call
- audit
- 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
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
Abstract
The invention relates to a big data processing technology, in particular to a method, a system and a computer device for auditing and evaluating an outbound project based on big data, wherein the method comprises the following steps: acquiring a call text and call result data of a call-out project; processing the call text of each outbound project, and acquiring text characteristics such as dialect expression, spoken language capability, reaction capability, client feedback and the like from the call text as a first part of project audit evaluation indexes; processing the outbound result data of each outbound project, acquiring indexes such as human efficiency, energy efficiency and input-output ratio from the outbound result data, and using the indexes as a second part of project audit evaluation indexes; determining the weights of the first part and the second part of the project audit evaluation index, and obtaining the audit result of the outbound project according to the first part, the second part and the respective weights. The invention carries out scientific and normative evaluation on the outbound project, and avoids the defects of complicated process and subjectivity of the current project review.
Description
Technical Field
The invention relates to a big data processing technology, in particular to a method, a system and computer equipment for auditing and evaluating outbound projects based on big data.
Background
The outbound project data has many typical characteristics of big data, for example, the data type includes structured data and unstructured data, and the data index is complex.
Currently, the examination of the outbound item adopts a manual examination mode, and the examination content mainly includes: the dialing amount, the receiving rate, the success amount, the success rate, the number of outbound people and other indexes of the project calling trial. The audit index data is complex and scattered, different auditors know different data, and project audit results are different. Meanwhile, after the project is audited, no method for evaluating the profit condition of the project exists. The problems that the project auditing process is too complex, the auditing efficiency is low, the auditing result is influenced by the subjective consciousness of the auditors, the project evaluation mechanism is incomplete and the like are caused. The objectivity and comprehensiveness of the examination and evaluation mechanism of the outbound item need to be improved.
Disclosure of Invention
The invention aims to solve the technical problems that the existing outbound project audit is complex and is influenced by subjective consciousness and the like, and provides the outbound project audit evaluation method, the outbound project audit evaluation system and the computer equipment based on big data.
The invention can be realized by adopting the following technical scheme: the outbound project auditing and evaluating method based on big data comprises the following steps:
step S01, acquiring the call text and the call result data of the call-out project;
step S02, processing the call text of each outbound project, and acquiring text characteristics from the call text as a first part of project audit evaluation indexes; the text features comprise a verbal expression, a spoken language capability, a reaction capability and a client feedback;
step S03, the outbound result data of each outbound project is processed, and indexes are obtained from the outbound result data and are used as a second part of project audit evaluation indexes; the indexes comprise human efficiency, energy efficiency and input-output ratio;
and step S04, determining the weights of the first part and the second part of the project audit evaluation index, and obtaining the audit result of the outbound project according to the first part, the second part and the respective weights.
In a preferred embodiment, the evaluation method of the present invention can evaluate the profit margin of the project, and further comprises:
and step S05, evaluating the profit condition of the project according to the first part, the second part and the respective weights of the project audit evaluation indexes, returning the project evaluation result in a grading mode, and putting the project audit evaluation result into a project database.
The invention can also be realized by adopting the following technical scheme: the outbound project auditing and evaluating system based on big data comprises:
the data acquisition unit is used for acquiring the call text and the call result data of the call-out project;
the call text processing unit is used for processing the call text of each outbound project, acquiring text characteristics from the call text and using the text characteristics as a first part of a project audit evaluation index; the text features comprise a verbal expression, a spoken language capability, a reaction capability and a client feedback;
the outbound result data processing unit is used for processing the outbound result data of each outbound project, acquiring indexes from the outbound result data and using the indexes as a second part of the project audit evaluation indexes; the indexes comprise human efficiency, energy efficiency and input-output ratio;
the project audit evaluation unit is used for determining the weights of a first part and a second part of the project audit evaluation index and obtaining the audit result of the outbound project according to the first part, the second part and the respective weights;
and the project profit evaluation unit is used for evaluating the profit condition of the project according to the first part, the second part and the respective weights of the project audit evaluation indexes, returning the project evaluation result in a grading mode, and putting the project audit evaluation result into the project database.
The technical scheme of the invention also can be computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the outbound project auditing and evaluating method is realized.
Compared with the prior art, the outbound project auditing and evaluating method based on big data has the following beneficial effects: the method comprises the steps of obtaining a first part of outbound project audit evaluation by obtaining call texts of various projects, obtaining outbound result data of the various projects to obtain a second part of the outbound project audit evaluation, and obtaining an index value of the outbound project audit evaluation according to the first part, the second part and respective weights of the first part and the second part. The outbound project is scientifically and normatively evaluated, and a project auditing mode in the prior art for auditing a plurality of indexes is simplified; meanwhile, the personnel calling out the project can also refer to the standard for reviewing and evaluating the project for reference to further comprehensively and carefully know the specific situation of the project in charge. The defects of complicated process and subjectivity of the current project audit are avoided, and therefore the efficiency and quality of project audit evaluation are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, 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 invention, 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 flowchart of a big data-based outbound project audit evaluation method according to an embodiment of the present invention;
FIG. 2 is a detailed flowchart of the embodiment of the present invention, in which the call text and the outbound result data of the outbound project are obtained, and the outbound project database is established according to the obtained data;
FIG. 3 is a flowchart illustrating the steps of processing call texts and extracting text features according to the embodiment of the present invention;
FIG. 4 is a flowchart illustrating a specific process of processing outbound data of each item and obtaining indicators such as human efficiency, energy efficiency, input-output ratio, and the like according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating an embodiment of determining weights of a first portion and a second portion of an outbound project audit evaluation indicator, and obtaining an outbound project audit result according to the first portion, the second portion, and the respective weights;
fig. 6 is a specific flowchart of evaluating profit of the project according to the first part, the second part and their respective weights, returning a project evaluation result in a graded manner, and putting the project review evaluation result into a project database according to the embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any inventive step, are intended to be within the scope of the present invention as defined by the appended claims.
In this embodiment, a flow of a big data-based outbound project audit evaluation method is shown in fig. 1, and the method includes the following steps:
step S01, acquiring the call text and the call result data of the call-out project;
in this step, the call text and the data of the outbound result of the outbound project, that is, the data of the new outbound project, are obtained. The details of how to specifically obtain the outbound project call text and the outbound and result data will be described later.
Step S02, processing the call text of each outbound project, and acquiring text characteristics such as dialectical expression, spoken language capability, reaction capability, client feedback and the like from the call text as a first part of project audit evaluation indexes;
firstly, carrying out text processing on a call text of each outbound project, processing the call text by combining text cleaning, text word segmentation, text de-noising and a Kmeans clustering algorithm, and extracting text characteristics of the call text, such as a conversational expression, a spoken language capability, a reaction capability, customer feedback and the like; then, quantifying the extracted text features by text analysis methods such as word frequency statistics, word embedding and the like to obtain a first part of project audit evaluation; and finally, determining the weight of each text feature by an entropy method. Therefore, the method realizes the preprocessing of the calling text of the outbound project and the objective text analysis of the text feature extraction.
Step S03, the outbound result data of each outbound project are processed, and indexes such as human efficiency, energy efficiency and input-output ratio are obtained from the outbound result data and are used as a second part of project audit evaluation indexes;
in the step, the outbound result data of each outbound project is obtained, the main information of the outbound result data is the outbound volume, the call completing rate, the work completing volume, the success rate and the number of seats of the outbound project, the method belongs to structured data mining, after the outbound result data is cleaned, the outbound result data is further calculated to obtain the human efficiency, the energy efficiency and the input-output ratio, and the second part of the project audit evaluation index is obtained, so that the outbound result data of the outbound project are processed and the index calculation is realized.
Step S04, determining the weights of the first part and the second part of the project audit evaluation index, and obtaining the audit result of the outbound project according to the first part, the second part and the respective weights;
in the step, the weight is determined according to an entropy method, and then an outbound audit evaluation index value is obtained according to the first part, the second part and the respective weight, so that the audit of the project is completed. For convenience of description, in this embodiment, the first part and the second part are respectively labeled as P1 and P2, and then the weights of P1 and P2 are determined according to an entropy method, and finally an outbound audit evaluation index value and a project audit result are obtained.
Step S05, evaluating the profit condition of the project according to the first part, the second part and the respective weights, returning the project evaluation result in a grading mode, and putting the examination and evaluation result of the project into a project database;
in the step, index values of project audit evaluation are obtained according to the first part, the second part and respective weights, the profit situation of the project is evaluated, the magnitude of the index values of various types of project audit evaluation is sorted in an ascending order, the profit situation of various types of project outbound call is divided into ten grades, and after the project evaluation grade is obtained according to the project audit evaluation index value evaluation, the project evaluation result is put into a project database of various types.
In this embodiment, the higher the index value is, the higher the profit of project marketing is, through the project evaluation and review indexes obtained in steps S01-S05; obtaining the call text and the call result data of the call-out project through the step S01, and sorting and warehousing the call text and the call-out result data according to the project type; obtaining a first part and a second part of the project evaluation auditing indexes through steps S02 and S03; obtaining the weights of the first part and the second part and the item auditing result through the step S04; the profit assessment scenario for project marketing is obtained through step S05. Compared with a project expert rating mode in the prior art, the method has a quantitative rating system and a relatively objective evaluation standard when the outbound project is audited and evaluated, and the outbound project is audited and evaluated relatively objectively and comprehensively through quantitative scoring of two parts, namely the conversation text characteristics such as conversation expression, spoken language capability, reaction capability and client feedback, and the outbound result data characteristics such as outbound volume, call rate, work amount, success rate and the number of seats. The weights of the first part and the second part are determined according to an entropy method, scientific, objective and rigorous index weight assignment is further realized, and subjectivity and one-sidedness in current artificial evaluation are avoided, so that the function of perfecting an outbound project audit evaluation mechanism can be achieved.
For the present embodiment, the step S01 may be further refined, and a detailed flow after the refinement is shown in fig. 2.
Step S01 further includes:
step S11, obtaining the call text and the call result data of the call-out project: in the step, the call record is converted into the text to obtain a call text, and the call-out result data of the call-out item is obtained through call trial.
Step S12, dividing the call text and the outbound result data according to the project type, and storing the call text and the outbound result data into the outbound project database of the corresponding type: in the step, the call texts and the call result data of the historical call-out projects and the new projects are sorted and summarized according to the project types to obtain a database of each type of call-out project.
For the present embodiment, the step S02 may be further refined, and a detailed flow after the refinement is shown in fig. 3.
Step S02 further includes:
s21, acquiring call text data of various outbound projects to form a series of call text records of the various outbound projects, and using the call text records as first-type data of audit evaluation of the outbound projects;
in this step, the call text data of each outbound project is extracted from the outbound project database. The outbound item database is a database obtained by summarizing the historical outbound items, the call texts of the new items and the outbound result data, namely the database obtained in the step S12; and then extracting data in the aspect of the call text from the outbound project database to obtain the call text data of various outbound projects and form a series of call text records.
Step S22, respectively performing text preprocessing such as text cleaning, text word segmentation, text denoising and the like on the call text record of each outbound project;
in the step, the call text record of each outbound project is subjected to text cleaning, text word segmentation and text denoising, so that the call text preprocessing process is completed. The text cleaning specifically comprises the steps of Chinese numerical value conversion, case and case conversion, referring information replacement, disambiguation conversion, digital information reduction, symbol elimination and the like; the text word segmentation utilizes a word segmentation method based on statistics, and the frequency of common occurrence of adjacent characters is used as the credibility evaluation standard of adjacent character forming words, the specific method comprises the steps of firstly counting the frequency of combinations of each character which adjacently occurs in a text, calculating the mutual occurrence information of the characters, wherein the mutual occurrence information reflects the tightness of the combination relationship between Chinese characters, when the tightness is higher than a certain threshold value, the combination of the corresponding characters can be considered to possibly form a word, otherwise, the combination of the characters cannot be considered; the text denoising process mainly removes 'noise' data contained in a text, the denoising technology mainly adopted in the process of processing a call text is stop word filtering, the stop word filtering refers to filtering words which have high occurrence frequency but have no significant meaning in text information, and mainly refers to a series of virtual words and high-frequency words such as language atmosphere auxiliary words, prepositions, conjunctions and the like.
Step S23, clustering the preprocessed call text records, performing feature selection, and respectively extracting text features such as dialectical expression, spoken language capability, reaction capability, customer feedback and the like in each item of call text;
in the step, text features of call text records are extracted through text analysis methods such as word frequency statistics, word embedding and the like, the text features are clustered through a Kmeans clustering algorithm, and text features influencing examination and evaluation of outbound projects, such as conversational expression, spoken language ability, reaction ability, customer feedback and the like are extracted.
Step S24, quantizing each extracted text feature, and determining the weight of each text feature respectively as a first part of an outbound project audit evaluation index;
in this step, text feature vectors are extracted from a call text, and the text feature vectors such as a mnemonic expression, a spoken language ability, a reaction ability, a client feedback and the like are respectively M1 ═ { M11, M12.. M1i. }, M2 ═ M21, M22.. M2i. }, M3 ═ M31, M32.. M3i. }, and M4 ═ M41, M42.. M4i. }; then, setting standards of text characteristics such as dialect expression, spoken language capability, reaction capability, customer feedback and the like according to the call text and the outbound result data of the historical outbound project, and expressing the standards in the form of vector space and respectively marking the standards as standard characteristic vectors S1, S2, S3 and S4; and finally, calculating the similarity of the text feature vectors M1, M2, M3 and M4 and the standard feature vectors S1, S2, S3 and S4, and realizing the quantization of each text feature according to the size of the similarity.
After quantization of text features is achieved, the weight of each text feature is determined according to an entropy method. The entropy method is to judge the influence degree of each text feature on the item audit evaluation index according to the discrete degree, namely, the larger the influence on the item audit evaluation index is, the larger the weight is. And after determining the weight of each quantized text feature, linearly combining each text feature to obtain a first part of the outbound project audit evaluation index.
For the present embodiment, the step S03 may be further refined, and a detailed flow after the refinement is shown in fig. 4.
Step S03 further includes:
step S31, obtaining the outbound result data of various outbound projects, cleaning the outbound result data to obtain second data about the outbound project audit evaluation;
in this step, the outbound result data of each outbound project is extracted from the outbound project database. The outbound item database is a database obtained by summarizing the historical outbound items, the call texts of the new items and the outbound result data, namely the database obtained in the step S12; then extracting data related to the outbound result part from the outbound project database to obtain outbound result data; and then cleaning the outbound result data, deleting the non-marketing service data, deleting the data with the number of seats of 0 to ensure that the outbound result data are marketing data and have no invalid data, and finally obtaining second data related to the outbound project audit evaluation.
Step S32, calculating the human effect of each outbound project according to the number of outbound persons and the dialing amount in the outbound result data of each outbound project;
in the step, the outbound number and the dialing amount of each outbound project are respectively obtained from the outbound result data of each outbound project, and the human effect index of each outbound project is calculated according to the index. The human effect of each outbound project is equal to the dialing amount compared with the number of outbound persons, and the marketing efficiency of the outbound persons in each outbound project is directly reflected.
Step S33, calculating the energy efficiency of each outbound project according to the number of outbound persons and success amount in the outbound result data of each outbound project;
in the step, the outbound number and the success amount are respectively obtained from the outbound result data of each outbound project, and the energy efficiency indexes of each outbound project are obtained through calculation according to the indexes. The energy efficiency of each outbound project is equal to the ratio of the success rate to the number of outbound persons, and the average marketing level of the outbound persons in each outbound project is directly reflected.
Step S34, calculating the input-output ratio of various outbound projects according to the project unit price and the project policy price in the outbound result data of each outbound project;
in the step, a project unit price and a project policy price are respectively obtained from the outbound result data of each outbound project, wherein the project unit price refers to the income obtained by the outbound personnel successfully marketing a bill, and the project policy price refers to the price of the project; the input-output ratio of each outbound item is equal to the item price per item policy price, indicating the input and output of a single item.
Step S35, determining the weight of the human efficiency, the energy efficiency and the input-output ratio respectively to be used as a second part of the outbound project audit evaluation index;
in the step, the weights of the three indexes of human efficiency, energy efficiency and input-output ratio calculated in the step are determined according to an entropy method, namely the influence degree of each index on the comprehensive index of the outbound project audit evaluation is judged according to the discrete degree of each index. And then, linearly combining the human efficiency, the energy efficiency and the reciprocal of the input-output ratio to be used as a second part of the outbound project audit evaluation index.
For the present embodiment, the step S04 may be further refined, and a detailed flow after the refinement is shown in fig. 5.
Step S04 further includes:
step S41, determining the weight of the first part and the second part;
in this step, the weights of the first part and the second part of the outbound project audit evaluation index are respectively determined by using an entropy method, that is, the influence of the first part and the second part on the project audit evaluation index is judged according to the discrete degree of the first part and the second part.
Step S42, obtaining an outbound project audit evaluation index according to the first part, the second part and the respective weights thereof;
in this step, the first part and the second part after determining the respective weights are linearly combined to be used as a final outbound project audit evaluation index.
Step S43, the auditor directly uses the index to audit the new outbound project to obtain an audit result, namely an audit evaluation index value of the outbound project;
in this step, the project auditor directly audits the project according to the outbound project audit evaluation index obtained in step S42.
Step S44, placing the audited outbound project and the audited result into a project database;
in this step, the outbound project which passes the audit of the outbound project audit evaluation index and the audit evaluation index value of the outbound project are put into the outbound project database of the corresponding type.
For the present embodiment, the step S05 may be further refined, and the detailed flow after the refinement is shown in fig. 6.
Step S05 further includes:
step S51, evaluating the profit condition of the project according to the outbound project audit evaluation index values obtained by the first part, the second part and the respective weights thereof; namely, in the step, the profit situation of the project is evaluated according to the outbound project audit evaluation index value.
Step S52, sorting the outbound project database in ascending order according to the size of the outbound project audit evaluation index value, dividing the same type of outbound projects into different grades, and reflecting the evaluation of the project profit condition in a grade form;
in the step, the audit evaluation index values of all outbound projects are sorted in an ascending order, and the grades are classified according to the size of the audit evaluation index values in the outbound projects of the same type. The higher the audit evaluation index value, i.e., the higher the rating, the higher the profit of the project.
Step S53, respectively putting the estimated new project and the project profit estimation result into each type of outbound project database;
in the step, the outbound project and the project profit evaluation grade result of the profit grade situation obtained by dividing according to the audit evaluation index value are put into the outbound project database of the corresponding type, and then the project audit and the grade evaluation of the profit situation can be completed.
In short, in this embodiment, the project audit evaluation method performs audit evaluation on two parts of call text characteristics such as dialect expression, spoken language capability, response capability, and customer feedback in the outbound project and outbound result data characteristics such as outbound volume, call completion rate, success rate, and number of people in seats, excavates text characteristics from a large number of outbound project call texts by a text analysis method based on word frequency statistics and word embedding, and obtains indexes of judgment efficiency, capability, and income from outbound result data to make the composition of the outbound project audit evaluation indexes cover more comprehensive and important data as much as possible; meanwhile, the examination and evaluation of the outbound project is scientific, comprehensive, objective and reasonable as much as possible, the system accords with the actual situation, can serve the outbound center, reduces the complexity and subjectivity of the examination and evaluation of the outbound project, distributes project resources emphatically and efficiently, and improves the efficiency and quality of the examination and evaluation of the project. Compared with the original project audit evaluation method, the method has a quantitative evaluation system and relatively uniform evaluation standards for the outbound project audit evaluation, and relatively scientific and detailed audit evaluation is performed on the outbound project.
The invention is based on the same conception, and also provides a system for auditing and evaluating the outbound project based on big data, which comprises the following steps:
the data acquisition unit is used for acquiring the call text and the call result data of the call-out project; to implement the above step S01;
the call text processing unit is used for processing the call text of each outbound project, acquiring text characteristics from the call text and using the text characteristics as a first part of a project audit evaluation index; the text features comprise a verbal expression, a spoken language capability, a reaction capability and a client feedback; to implement the above step S02;
the outbound result data processing unit is used for processing the outbound result data of each outbound project, acquiring indexes from the outbound result data and using the indexes as a second part of the project audit evaluation indexes; the indexes comprise human efficiency, energy efficiency and input-output ratio; to implement the above step S03;
the project audit evaluation unit is used for determining the weights of a first part and a second part of the project audit evaluation index and obtaining the audit result of the outbound project according to the first part, the second part and the respective weights; to implement the above step S04;
the project profit evaluation unit is used for evaluating the profit condition of the project according to the first part and the second part of the project audit evaluation index and respective weight, returning the project evaluation result in a grading mode, and putting the project audit evaluation result into a project database; to implement step S05 described above.
The technical solution for solving the problem proposed by the present invention may also be a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the outbound project audit evaluation method of the present invention is implemented.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. The outbound project auditing and evaluating method based on big data is characterized by comprising the following steps:
step S01, acquiring the call text and the call result data of the call-out project;
step S02, processing the call text of each outbound project, and acquiring text characteristics from the call text as a first part of project audit evaluation indexes; the text features comprise a verbal expression, a spoken language capability, a reaction capability and a client feedback;
step S03, the outbound result data of each outbound project is processed, and indexes are obtained from the outbound result data and are used as a second part of project audit evaluation indexes; the indexes comprise human efficiency, energy efficiency and input-output ratio;
and step S04, determining the weights of the first part and the second part of the project audit evaluation index, and obtaining the audit result of the outbound project according to the first part, the second part and the respective weights.
2. The big-data-based outbound project audit evaluation method according to claim 1, further comprising:
and step S05, evaluating the profit condition of the project according to the first part, the second part and the respective weights of the project audit evaluation indexes, returning the project evaluation result in a grading mode, and putting the project audit evaluation result into a project database.
3. The big-data-based outbound project audit trail assessment method according to claim 1, wherein step S01 includes:
step S11, converting the call record into a text to obtain a call text, and obtaining the outbound result data of the outbound project through call trial;
and step S12, dividing the call text and the outbound result data according to the project type, and storing the call text and the outbound result data into the outbound project database of the corresponding type.
4. The big-data-based outbound project audit trail assessment method according to claim 1, wherein step S02 includes:
step S21, obtaining the call text data of various outbound projects, forming a series of call text records of various outbound projects as the first type of data for auditing and evaluating the outbound projects;
step S22, respectively performing text cleaning, text word segmentation and text denoising pretreatment on the call text record of each outbound project;
step S23, clustering the preprocessed call text records, performing feature selection, and respectively extracting text features in the call text of each outbound project;
and step S24, quantifying each extracted text feature, and respectively determining the weight of each text feature as a first part of the outbound project audit evaluation index.
5. The big-data-based outbound project audit evaluation method according to claim 4, wherein in step S24, each text feature extracted from the call text is first vectorized, and the text feature vectors of the tokenization expression, the spoken language ability, the reaction ability, and the client feedback are respectively M1 ═ M11, M12.. M1i. }, M2 ═ M21, M22.. M2i. }, M3 ═ M31, M32.. M3i. }, M4 ═ M41, M42.. M4i. }; then, setting standards of dialect expression, spoken language capability, reaction capability and customer feedback according to the call text and the outbound result data of the historical outbound project, and representing the standards in the form of vector space and respectively marking the standards as standard characteristic vectors S1, S2, S3 and S4; finally, calculating the similarity of the text feature vectors M1, M2, M3 and M4 and the standard feature vectors S1, S2, S3 and S4, and realizing the quantization of each text feature according to the size of the similarity;
after the quantization of the text features is realized, determining the weight of each text feature according to an entropy method; and after determining the weight of each quantized text feature, linearly combining each text feature to obtain a first part of the outbound project audit evaluation index.
6. The big-data-based outbound project audit trail assessment method according to claim 1, wherein step S03 includes:
step S31, obtaining the outbound result data of various outbound projects, cleaning the outbound result data to obtain second data about the outbound project audit evaluation;
step S32, calculating the human effect of each outbound project according to the number of outbound persons and the dialing amount in the outbound result data of each outbound project;
step S33, calculating the energy efficiency of each outbound project according to the number of outbound persons and success amount in the outbound result data of each outbound project;
step S34, calculating the input-output ratio of various outbound projects according to the project unit price and the project policy price in the outbound result data of each outbound project;
and step S35, determining the weight of the human efficiency, the energy efficiency and the input-output ratio respectively to be used as a second part of the outbound project audit evaluation index.
7. The big-data-based outbound project audit trail assessment method according to claim 1, wherein step S04 includes:
step S41, determining the weights of the first part and the second part of the project audit evaluation index;
step S42, in the step, linearly combining the first part and the second part of the project audit evaluation index after determining the respective weight, and using the first part and the second part as the final outbound project audit evaluation index;
step S43, the new outbound project is audited by directly using the outbound project audit evaluation index, and an audit result, namely the audit evaluation index value of the outbound project, is obtained;
and step S44, placing the audited outbound item and the audited result into the outbound item database of the corresponding type.
8. The big-data-based outbound project audit trail assessment method according to claim 2, wherein step S05 includes:
step S51, evaluating the profit condition of the project according to the outbound project audit evaluation index values obtained by the first part and the second part of the project audit evaluation index and the respective weights thereof;
step S52, sorting the outbound project database in ascending order according to the size of the outbound project audit evaluation index value, dividing the same type of outbound projects into different grades, and reflecting the evaluation of the project profit condition in a grade form;
and step S53, respectively putting the evaluated new project and the project profit evaluation result into the outbound project databases of various types.
9. Outbound project audit evaluation system based on big data, characterized by comprising:
the data acquisition unit is used for acquiring the call text and the call result data of the call-out project;
the call text processing unit is used for processing the call text of each outbound project, acquiring text characteristics from the call text and using the text characteristics as a first part of a project audit evaluation index; the text features comprise a verbal expression, a spoken language capability, a reaction capability and a client feedback;
the outbound result data processing unit is used for processing the outbound result data of each outbound project, acquiring indexes from the outbound result data and using the indexes as a second part of the project audit evaluation indexes; the indexes comprise human efficiency, energy efficiency and input-output ratio;
the project audit evaluation unit is used for determining the weights of a first part and a second part of the project audit evaluation index and obtaining the audit result of the outbound project according to the first part, the second part and the respective weights;
and the project profit evaluation unit is used for evaluating the profit condition of the project according to the first part, the second part and the respective weights of the project audit evaluation indexes, returning the project evaluation result in a grading mode, and putting the project audit evaluation result into the project database.
10. Computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the outbound project audit evaluation method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396575.9A CN111160778A (en) | 2019-12-30 | 2019-12-30 | Outbound project auditing and evaluating method and system based on big data and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911396575.9A CN111160778A (en) | 2019-12-30 | 2019-12-30 | Outbound project auditing and evaluating method and system based on big data and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111160778A true CN111160778A (en) | 2020-05-15 |
Family
ID=70559101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911396575.9A Pending CN111160778A (en) | 2019-12-30 | 2019-12-30 | Outbound project auditing and evaluating method and system based on big data and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160778A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116384947A (en) * | 2023-06-01 | 2023-07-04 | 威海海洋职业学院 | Publication issuing monitoring management system and method based on big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1788517A1 (en) * | 2005-11-21 | 2007-05-23 | Accenture Global Services GmbH | System and method for analyzing customer profitability |
| CN103455596A (en) * | 2013-09-02 | 2013-12-18 | 广东省计算中心 | Science and technology project establishment evaluation method based on big data |
| CN105139220A (en) * | 2015-10-10 | 2015-12-09 | 福建麦格数码科技有限公司 | Entity credit assessment system based on big data |
| CN106875076A (en) * | 2015-12-10 | 2017-06-20 | 中国移动通信集团公司 | Set up the method and system that outgoing call quality model, outgoing call model and outgoing call are evaluated |
| CN108924369A (en) * | 2018-06-27 | 2018-11-30 | 中国联合网络通信集团有限公司 | NPS assessment method for running, systems and management platform based on telephone poll |
| CN109151218A (en) * | 2018-08-21 | 2019-01-04 | 平安科技（深圳）有限公司 | Call voice quality detecting method, device, computer equipment and storage medium |
| CN109246322A (en) * | 2018-07-31 | 2019-01-18 | 平安科技（深圳）有限公司 | A kind of information processing method and system |
| CN109816106A (en) * | 2017-11-20 | 2019-05-28 | 北京智合大方科技有限公司 | One kind carrying out call center's customer service knowledge class response quality evaluation system based on speech recognition and natural language processing technique |
| CN110472017A (en) * | 2019-08-21 | 2019-11-19 | 佰聆数据股份有限公司 | A kind of analysis of words art and topic point identify matched method and system |
-
2019
- 2019-12-30 CN CN201911396575.9A patent/CN111160778A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1788517A1 (en) * | 2005-11-21 | 2007-05-23 | Accenture Global Services GmbH | System and method for analyzing customer profitability |
| CN103455596A (en) * | 2013-09-02 | 2013-12-18 | 广东省计算中心 | Science and technology project establishment evaluation method based on big data |
| CN105139220A (en) * | 2015-10-10 | 2015-12-09 | 福建麦格数码科技有限公司 | Entity credit assessment system based on big data |
| CN106875076A (en) * | 2015-12-10 | 2017-06-20 | 中国移动通信集团公司 | Set up the method and system that outgoing call quality model, outgoing call model and outgoing call are evaluated |
| CN109816106A (en) * | 2017-11-20 | 2019-05-28 | 北京智合大方科技有限公司 | One kind carrying out call center's customer service knowledge class response quality evaluation system based on speech recognition and natural language processing technique |
| CN108924369A (en) * | 2018-06-27 | 2018-11-30 | 中国联合网络通信集团有限公司 | NPS assessment method for running, systems and management platform based on telephone poll |
| CN109246322A (en) * | 2018-07-31 | 2019-01-18 | 平安科技（深圳）有限公司 | A kind of information processing method and system |
| CN109151218A (en) * | 2018-08-21 | 2019-01-04 | 平安科技（深圳）有限公司 | Call voice quality detecting method, device, computer equipment and storage medium |
| CN110472017A (en) * | 2019-08-21 | 2019-11-19 | 佰聆数据股份有限公司 | A kind of analysis of words art and topic point identify matched method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116384947A (en) * | 2023-06-01 | 2023-07-04 | 威海海洋职业学院 | Publication issuing monitoring management system and method based on big data |
| CN116384947B (en) * | 2023-06-01 | 2023-08-15 | 威海海洋职业学院 | Publication issuing monitoring management system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110910901B (en) | Emotion recognition method and device, electronic equipment and readable storage medium | |
| CN109783639B (en) | Mediated case intelligent dispatching method and system based on feature extraction | |
| CN101662550A (en) | Method and system for service quality detection for call center | |
| CN110555101A (en) | customer service knowledge base updating method, device, equipment and storage medium | |
| CN113435627A (en) | Work order track information-based electric power customer complaint prediction method and device | |
| CN111160778A (en) | Outbound project auditing and evaluating method and system based on big data and computer equipment | |
| CN114140013A (en) | Scoring card generation method, device and equipment based on xgboost | |
| CN117196402A (en) | Target object determination method and device, storage medium and electronic equipment | |
| CN116663890A (en) | Power supply customer satisfaction evaluation method and system based on machine learning model | |
| CN115423600B (en) | Data screening method, device, medium and electronic equipment | |
| CN111489736A (en) | Automatic seat speech technology scoring device and method | |
| CN116828109A (en) | Intelligent evaluation method and system for telephone customer service quality | |
| CN116579640A (en) | Power marketing service channel user experience assessment method and system | |
| CN114881130A (en) | Bagging model-based relay protection defect text grading method | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN114579751A (en) | Emotion analysis method and device, electronic equipment and storage medium | |
| CN115080732A (en) | Complaint work order processing method and device, electronic equipment and storage medium | |
| CN111178982B (en) | Customer satisfaction analysis method, storage medium and computer device | |
| CN113064944A (en) | Data processing method and device | |
| KR102518859B1 (en) | Method and apparatus for artificial intelligence based customer complaint management | |
| Rusydiana et al. | Advancement and Setback in Islamic Banking Productivity in Asean: Do Technological Changes Matter? | |
| CN115438101B (en) | Data feature construction system and method based on feature morphology and data relationship | |
| CN117291563B (en) | Comprehensive management method and system for automatic office work | |
| CN107798480B (en) | Service quality evaluation method and system for customer service | |
| CN112819205B (en) | Method, device and system for predicting working hours |
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 |