CN110796322A

CN110796322A - System and method for scoring translation translator

Info

Publication number: CN110796322A
Application number: CN201810866028.1A
Authority: CN
Inventors: 张运军
Original assignee: Shenzhen Double Monkey Technology Co Ltd
Current assignee: Shenzhen Double Monkey Technology Co Ltd
Priority date: 2018-08-01
Filing date: 2018-08-01
Publication date: 2020-02-14

Abstract

The invention discloses a scoring method for a translation translator, which comprises four steps of translator registration, comprehensive scoring and grading, user feedback and grade change. The translator registration process comprises the steps of identity verification, basic information input, language and translation related information input, auxiliary information input, accent scoring and the like. The invention provides two interpreter level change rules and supplementary rules for balancing user selection tendency. The scoring method provided by the invention has a self-optimization function, and can improve the scoring standard according to the feedback information of the user. The invention also provides a scoring system of the translation translator, which is used for realizing the scoring method. The invention is beneficial to perfecting the translator distribution system of the remote online translation service, improving the customer experience and promoting the benign development of the online translation market.

Description

System and method for scoring translation translator

Technical Field

The invention relates to a language translation and evaluation technology, in particular to a scoring system and a scoring method for a translator.

Background

International import and export trade and communication of various technologies, cultures, tourism and the like present increasingly frequent situations, and different languages as a gap seriously obstruct smooth communication between people. At present, over 1000 ten thousand foreign language clients are received internationally in hotels, shopping malls, scenic spots and the like with foreign language communication demands, and the foreign language communication demands are long-term, high-repeatability and continuous demands! The current artificial intelligent speech translation cannot meet the communication requirement, and in addition, the artificial translation auxiliary communication is more needed in some fields with stronger speciality and commercial fields. Compared with machine translation, manual translation has good translation quality, but also faces high cost, and the cost is not only from the service cost of a translator, but also from the food and sleeping cost, the air ticket cost, the ground transportation cost and other related costs of the translator. In summary, the cost is so high that the manual translation is a service which is difficult to popularize for a long time in the past, and the ordinary consumers cannot enjoy the convenience brought by the manual translation.

The coming of the internet era and the rapid development of the communication field greatly reduce the cost of remote communication among people, so that a translator can remotely provide translation services, and translation services based on communication modes such as a telephone and a 4G network are in a rapidly increasing trend. Under the condition of different application scenes, the requirements of people on the translation accuracy and the translation effectiveness are different, for example, in some important meeting places, the translation content is generally complex, qualified simultaneous interpretation personnel are needed to ensure the translation quality and the real-time performance, the translation cost is also high and generally exceeds 1 ten thousand yuan per hour; in tourist attractions and environments such as hotels and shopping malls, only relatively simple communication is needed, the requirement on translation real-time performance is relatively low, simultaneous interpretation is not needed, translators at a primary level can be competent, and the translation fee is low. Therefore, how to match translators with different translation levels according to application scenes and customer requirements enables customers to spend more reasonably on the premise of meeting the translation requirements, the customer experience level can be improved, the online translation market benign development is facilitated, and optimal allocation of translator resources can be ensured under the market environment with supply and demand weaker.

To achieve the goal, the system is based on a translator scoring system, namely scoring is carried out according to the translation level of a translator, so that translation tasks with different difficulties are distributed according to the scoring level. At present, scoring standards of some existing interpreter scoring systems are often one-sided, scoring is only carried out according to user feedback results, grading is not fine enough, and the overall effect is poor.

Disclosure of Invention

In view of the above-mentioned shortcomings of the existing translator scoring system, which cannot meet the more detailed translator matching requirements, the present invention aims to provide an evaluation method of a translator, so as to improve the translator distribution system of the remote online translation service, improve the customer experience, and promote the benign development of the online translation market.

To achieve the above and other related objects, the present invention provides a scoring method for a translation translator, comprising at least the steps of:

step S001: the translator registers and inputs the registration information;

step S002: scoring and grading the translators according to the translator registration information and a preset scoring standard;

step S003: dispatching an order to a translator according to the user requirement, receiving the order by the translator and executing a translation instruction, and scoring the translator according to the satisfaction degree by the user after the translation is finished;

step S004: carrying out grade change on the interpreter according to the user feedback information;

the step S004 of changing the grade of the interpreter at least comprises the following steps:

step S200: obtaining an evaluation index of a translator, wherein the evaluation index at least comprises one of a good evaluation rate, a good evaluation quantity, a poor evaluation rate and a poor evaluation quantity;

step S201: judging whether the evaluation index of the translator reaches a preset upgrading standard value or a preset degrading standard value, if the evaluation index of the translator is larger than the preset upgrading standard value, the translator can acquire the qualification of applying for upgrading, and executing the step S202 to the step S204; if the evaluation index of the translator is larger than the preset degradation standard value, the translator needs to be degraded, and the steps S205 to S206 are skipped to be executed;

step S202: prompting an interpreter with application upgrading qualification to apply for upgrading;

step S203: if the translator applies for upgrading, the translator enters a trial period for confirming whether the upgrading can be carried out; if the translator does not apply for upgrading, the current process is ended;

step S204: if the evaluation index obtained by the translator in the trial period of the upgrade reaches the preset standard value, confirming the upgrade of the translator; and if the evaluation index obtained by the translator in the trial period of the upgrade does not reach the preset standard value, the translator is not allowed to upgrade.

Specifically, the description is needed to ensure that when the good evaluation rate and the good evaluation quantity of a certain translator reach a certain standard, the translator can apply for upgrading. And the first few sheets after upgrading are trial periods, if the good evaluation rate in the trial periods meets the requirements, the upgrading can be finally confirmed, and otherwise, the original grade is returned. After returning to the original level, the translator can not apply for upgrading temporarily, and can apply for upgrading again if meeting the upgrading application condition after meeting a certain odd number. This is the upgrade rule under that rule. The degradation rule is that when the bad evaluation rate and the bad evaluation quantity of a certain translator reach certain standards, degradation prompt is given to the translator, a plurality of lists after the prompt are given are observation stages, and degradation processing is given if the bad evaluation rate is not obviously reduced;

specifically, it should be noted that each time the interpreter receives a good comment, the scoring of the interpreter is increased by a certain score; the scoring of each received Chinese bid is not changed; each time a bad score is received, the score is reduced by a certain score (if the user feedback score is more than three grades, different weight scores can be set for each grade, and then the total score of the translator is increased or reduced). As the number of the translator receiving orders increases, the total score of the translator is changed continuously, and when the total score is higher than the interval of the grade of the translator, the translator is upgraded, otherwise, when the total score is lower than the interval of the grade of the translator, the translator is downgraded.

The translator registration information of step S001 is at least:

the identity authentication is used for authenticating the legal identity of the interpreter, and the certificate which is required to be provided by the interpreter at least comprises one of an identity card, a driving license and a passport;

basic information input at least comprising the name, the gender, the age, the translation language and the adequacy field of the translator;

inputting language and translation related information, and inputting an information certificate capable of proving the translation level of a translator;

auxiliary information input at least comprising overseas tourism and living experiences of the translator, translation working time and qualification certificate or working experience of the adequacy field;

and the entry of the accent scoring at least comprises the step that the interpreter needs to finish the preset translation content within the specified time, and the accent scoring is scored by the accent evaluation software or professionals.

Preferably, the interpreter registration process of step S001 may be performed online by the interpreter providing a photograph/scan of the certificate or by himself carrying the certificate to a specific location.

Preferably, the legal identity of the interpreter is verified, and the certificate which the interpreter needs to provide comprises at least one of an identity card, a driving license and a passport.

Preferably, the information certificate for proving the translation level of the translator at least comprises one of a national translation professional qualification certificate, a national foreign language translation certificate, a Shanghai city foreign language interpretation post qualification certificate, a business English examination result and a professional English certificate.

Preferably, the supplementary information includes overseas schools, living experiences, translation practice time, and expertise or practice history relating to the field of excellence.

In the step S002, the scoring result of the translator includes at least two parts of scores, one part is a total field scoring, the other part is a component added to an individual field, the scoring result of the translator in a certain field is the sum of the total field scoring and the component added to the field, and the scoring of a translator in different fields may be different;

preferably, the ranking of the translators in step S002 is at least three, etc.

Preferably, step S004 further includes a supplementary rule for balancing the user selection tendency, where the supplementary rule includes the following steps:

step S004 a: the system counts the average evaluation rate of all users;

step S004 b: if the poor rating of a certain user is higher than 4 times of the average poor rating of the system, marking the user as a poor rating inclined user; if the poor rating of a certain user is lower than 0.25 time of the average poor rating of the system, marking the user as a user with a good rating tendency;

step S004 c: for users with poor evaluation tendency, the good evaluation weight is improved by 10-30%, and the poor evaluation weight is reduced by 20-50%; for users with a high tendency to evaluate, the poor evaluation weight is improved by 60-100%.

Preferably, the translator adept field in the step S001d includes at least one field among financial finance, life sciences, automobile engineering, legal court, scientific and technological network, fashion art, engineering and construction, sports music.

Preferably, the scoring criteria of the translator composite score in step S002 may be continuously self-optimized, and the self-optimization method includes:

s002 a: the system counts each characteristic of the high-rating interpreter and each characteristic of the poor-rating interpreter;

s002 b: the system performs at least one of the following two operations,

operation one: the scoring weight of the common characteristics of the translators with high scoring rate is improved;

and operation II: reducing the scoring weight of the common features of the high-poor scoring rate translators.

Preferably, the result of the accent scoring in step S001e establishes a qualified score line, and cancels the translator registration qualification when the interpreter' S accent score is lower than the non-qualified line.

Preferably, in the process of performing the comprehensive scoring of the translator in step S002, the scores of the language and translation-related registration information are not superimposed.

The invention also provides a scoring system of the translation translator, which comprises a translator terminal (10) and a server (20) and is characterized by comprising the scoring method of the translation translator.

The invention also provides a scoring system for the translation translator, which is characterized by at least comprising a translator terminal (10) and a server (20);

said interpreter terminal (10) comprising at least: the display module (11) is used for displaying input and output contents; a communication module (12) for communicating between internal modules of the translator terminal or communicating the translator terminal with the outside; a voice module (13) for inputting or outputting voice; the communication module (12) is electrically connected with the display module (11) and the voice module (13);

the server (20) comprises at least: a communication module (21) for communication between the internal modules of the server or communication between the server and the outside; a data storage module (22) for storing information generated between the server (20) modules or external information received; the scoring module (23) is used for calculating the received information and returning a scoring value and grade of the translator;

the communication module (21) is electrically connected with the data storage module (22) and the scoring module (23).

Preferably, the translation translator scoring system further comprises a specialist terminal (30);

the specialist terminal (30) comprises at least: a display module (31) for displaying input and output contents; a communication module (32) for communicating between internal modules of the translator terminal or communicating the translator terminal with the outside; the communication module (32) is electrically connected with the display module (31);

preferably, the specialist terminal (30) further comprises an accent scoring (33) module for receiving the voice information of the interpreter and scoring the accent;

the accent scoring module (33) is electrically connected with the communication module (32).

Preferably, said interpreter terminal (10) further comprises: a registration module (14) for receiving registration information input by the interpreter; the registration module (14) is electrically connected with the communication module (12), the display module (11) and the voice module (13);

preferably, the scoring system for translation interpreters further comprises a user terminal (40);

the user terminal (40) comprises at least: a display module (41) for displaying input and output contents; a communication module (42) for communicating between internal modules of the translator terminal or communicating the translator terminal with the outside; a registration module (43) for receiving registration information input by a user; a feedback module (44) for inputting user feedback information for the translator; the communication module (42) is electrically connected with the display module (41), the feedback module (44) and the registration module (43);

preferably, the data storage module (22) comprises at least one of a temporary database (22a), a translator registration information database (22b), a user registration information database (22c), a translator scoring database (22d), a user feedback information database (22 e);

a temporary database (22a) for storing temporary information generated in the processing process of each module of the server (20);

an interpreter registration information database (22b) for storing registration information of an interpreter;

a user registration information database (22c) for storing registration information of users;

the translator scoring database (22d) is used for storing scoring and grade information of each field of the translator;

a user feedback information database (22e) for storing feedback information of the user to the translator;

specifically, the interpreter terminal (10) of the interpreter scoring system at least comprises a processor (CPU), a memory (such as a hard disk, an SSD solid state disk, a DDR3, or a DDR4 memory), a camera, a communication chip (such as a Wifi module, a 4G module), and the like, and the chips may be integrated on one motherboard or may be integrated on multiple motherboards respectively. A Graphics Processing Unit (GPU) voice recognition chip, a sound card (voice input output chip), a microphone may also be included. More specifically, the device can be a current mobile phone, a computer, an intelligent wearable device, a game device and the like.

The server (20) may include a processor (CPU), a Graphics Processing Unit (GPU), a memory (e.g., a hard disk, an SSD solid state disk, a DDR3 or a DDR4 memory, etc.), a voice recognition chip, a sound card (a voice input/output chip), a text-to-speech conversion chip, a communication chip (e.g., a Wifi, 4G module), etc., which may be integrated on one motherboard or may be integrated on multiple motherboards respectively. Of course, the server may include only some of the chips, as long as the functions are satisfied.

The specialist terminal (30) comprises a processor (CPU), a Graphic Processing Unit (GPU), a memory (such as a hard disk, an SSD (solid state disk), a DDR3 or DDR4 memory and the like), a voice recognition chip, a sound card (voice input and output chip), a text voice conversion chip, a communication chip (such as a Wifi (wireless fidelity), 4G (fourth generation) module) and the like, wherein the chips can be integrated on one mainboard or a plurality of mainboards respectively.

The user terminal (40) comprises a processor (CPU), a Graphic Processing Unit (GPU), a memory (such as a hard disk, an SSD (solid state disk), a DDR3 or DDR4 memory and the like), a voice recognition chip, a sound card (a voice input and output chip), a text voice conversion chip, a communication chip (such as a Wifi (wireless fidelity), 4G (global) module) and the like, wherein the chips can be integrated on one mainboard or a plurality of mainboards.

As described above, the method and system for scoring a translation translator according to the present invention have the following advantageous effects:

(1) according to the invention, the translators are classified into classes and fields from two dimensions of translation level and adequacy field, so that the detailed translator matching requirement can be met, and the translators are reasonably distributed to the maximum extent;

(2) the invention scores the translators from a plurality of angles such as translation qualification, working time, accent and the like, thereby realizing accurate and objective evaluation of the translation level of the translators;

(3) according to the translator grade change rule provided by the invention, the user feedback information is acted on the initial scoring of the translator, so that the initial scoring result is corrected, the translator can be promoted to consciously improve the translation level of the translator, and the translator with poor translation quality can be eliminated in time;

(4) the translator grade change supplement detail provided by the invention can effectively balance the selection tendency when the user feeds back, and the feedback results among different translators are more fair and objective;

(5) the interpreter scoring method provided by the invention can continuously perform self-optimization according to the feedback result of the user, so that the evaluation accuracy of the newly registered member is continuously improved;

(6) the accent scoring item included in the interpreter scoring method provided by the invention comprises a qualified line, and the registration qualification of an unqualified interpreter is directly cancelled, so that the interpreter trying to obtain registration through the confusion of false certificates can be effectively eliminated, and the credit of an operator and the benefit of a client are ensured to be lost.

Drawings

FIG. 1 is a flowchart illustrating a translator scoring method according to the present invention;

FIG. 2 is a schematic diagram showing the rating results of the translators rating the fields according to the present invention;

FIG. 3 is a table showing scoring weight ratios statistics for different registration information of an interpreter according to the present invention;

FIG. 4 is a table showing scoring ranges and service category statistics for different translators according to the present invention;

FIG. 5 is a flowchart illustrating a first exemplary interpreter level transformation rule proposed in the present invention;

FIG. 6 is a flowchart illustrating a second exemplary interpreter level change rule proposed by the present invention;

FIG. 7 is a flowchart illustrating a supplement rule for the change rule of translator level according to the present invention;

FIG. 8 is a table showing detailed scoring rules statistics of different types of registration information of translators in embodiment 2 of the present invention;

FIG. 9 is a schematic diagram illustrating a translation translator scoring system according to the present invention;

FIG. 10 is a schematic diagram of the components of a data storage module of the interpreter scoring system according to the present invention.

Detailed Description

The following description of the embodiments of the present invention is provided for illustrative purposes, and other advantages and effects of the present invention will become apparent to those skilled in the art from the present disclosure.

It should be understood that the structures, ratios, sizes, and the like shown in the drawings and described in the specification are only used for matching with the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions under which the present invention can be implemented, so that the present invention has no technical significance, and any structural modification, ratio relationship change, or size adjustment should still fall within the scope of the present invention without affecting the efficacy and the achievable purpose of the present invention. In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms is not to be construed as a scope of the present invention.

Example 1:

the translator scoring method provided by the invention comprises four steps of registering an S001 translator, grading an S002 comprehensive score, feeding back by an S003 user and changing an S004 grade. Fig. 1 shows the relationship between the steps in the form of a flow chart.

Step S001, the translator must register the identity in the system. The registration process may be performed online by an interpreter providing a photograph/scan of the document or by oneself physically carrying the document to a particular location. During the registration process, the legal identity information of the translator, such as an identity card, a driving license, a passport and the like, needs to be verified, and the basic information of the name, the gender, the age, the type of proficient language, the field of adequacy and the like of the translator is input at the same time. Besides, the translator needs to provide other information certificates which can prove the translation level, such as academic degree certificates, interpretation certificates of all levels, national translation professional qualification certificates, English level certificates, alternative translation certificates, simultaneous translation certificates and the like. Meanwhile, the translator can also provide other information to assist in evaluating the translation level, such as overseas nomadicals, living experiences, translation working time, relevant field working resumes and the like. The translator must then complete the translation of the small segment within a specified time, and the accent, response time, and translation accuracy are scored by the accent assessment software or by a professional.

And S002, comprehensively scoring the translator according to the information input during the registration of the translator by the system, and grading the translator. The weights used by different registration information are different when scoring. The qualification certificate and the like with high correlation degree with the translation skills and high industry recognition degree occupy the largest weight during scoring, score the accent, the response time and the accuracy of the temporary translation during the registration of the translator, and occupy the smallest auxiliary information such as overseas tourism, life experience and the like provided for the translator. In addition, the total score of the translator also includes the addition of a part of other fields, i.e. the final composite score rule is "total field score" + "individual field plus component" - "composite score". According to the level of the comprehensive score, the translators are divided into four grades, namely primary grade, intermediate grade, high grade and special grade. Due to the existence of domain bonus, the ratings of the same translator may vary in different domains, as shown in FIG. 2. For example, Zhang Sanqi has a high grade score in its entire domain, and because it is well-versed in legal knowledge and has some legal qualifications, it has a high grade score in the legal and legal domain, so that it reaches the level of a special grade translator in this domain, and is still a high grade translator in other domains. Fig. 3 shows the scoring weight ratios of different registration information, wherein the scores of the language and translation related registration information (corresponding to the column of the language base score in fig. 3) are not superimposed when scoring. For example, if a translator has a first-level national translation professional qualification certificate, a high-level foreign language interpretation position qualification certificate and an eight-level english professional certificate in the column of basic language scoring, the scoring of the column is only the highest item, namely the first-level national translation professional qualification certificate, with a corresponding proportion of 83% -93%, and the scoring of the next column of auxiliary scoring can be superimposed, for example, if a translator has 5 years in the uk (with a corresponding scoring hypothesis of 2%), has 5 years in the translation work (with a corresponding scoring hypothesis of 4%), has the qualification certificate of the holder (with a corresponding scoring hypothesis of 5%), has a law term in the auxiliary scoring to obtain 6% of the whole domain addition, and has an additional 5% of the law term in the law and the law term in the auxiliary scoring. The third column of accent scoring plus scoring in FIG. 3 is obtained by the interpreter temporarily translating a small piece of content at registration and scoring its translated accent, reaction time, accuracy, etc. by the accent scoring software or professional. It is noted that the result of the accent scoring is a pass line, i.e., a score result that is lower than the pass line, does not yield any additional score and disqualifies the translator from being registered.

It should be noted that the strict proportion of each kind of information is not given in fig. 3, but only a range is illustrated, because in actual operation, the system may continuously optimize this weighting criterion according to professional evaluation and customer feedback, and the final optimization result may be out of the range illustrated in fig. 3. Therefore, fig. 3 is not intended to limit the weight ratio of each scoring item in the scoring system of the present invention.

The scoring ranges and the service categories corresponding to translators with different grades are shown in fig. 4, wherein the translation tasks corresponding to the primary translators are simple communication in places such as shopping malls, hotels and scenic spots; the translation task corresponding to the middle-level translator is explained in a human scenic spot, sold to the outside, exchanged by simple technology, handled by procedures of going out of the country, moving people and the like; the translation tasks corresponding to the high-level translators are business negotiation, high-level meetings, deep technical communication, legal consultation and the like; the translation tasks corresponding to the special level translators are international important meetings, high-level business negotiations and the like; it is worth emphasizing that the score ranges of interpreters at different levels are not constant and can be continuously improved in the subsequent optimization process of the system. The business categories in the table are merely illustrative and do not limit the translation of the translator.

And step S003, the user feeds back the score. When a user side generates a translation requirement, the system dispatches an order to a translator according to the user requirement, the translator receives the order and executes a translation instruction, and after the translation is finished, the user performs multi-file scoring on the translator according to the satisfaction degree. The gears can be selected from a second gear, a third gear, a fourth gear, a fifth gear and the like. Taking the third grade as an example, the evaluation can be divided into good evaluation, medium evaluation and bad evaluation. The feedback score of the user may affect the change in the interpreter level in subsequent steps.

Step S004, the rank is changed. In order to more reasonably classify the translators and encourage the translators to continuously improve the self level, the translator scoring method provided by the invention also comprises a change rule related to grade increase and decrease. One change rule is shown in FIG. 5: when the good evaluation rate and the good evaluation quantity of a certain interpreter both reach a certain standard, the interpreter can apply for upgrading. And the first few sheets after upgrading are trial periods, if the good evaluation rate in the trial periods meets the requirements, the upgrading can be finally confirmed, and otherwise, the original grade is returned. After returning to the original level, the translator can not apply for upgrading temporarily, and can apply for upgrading again if meeting the upgrading application condition after meeting a certain odd number. This is the upgrade rule under that rule. The degradation rule is that when the bad evaluation rate and the bad evaluation quantity of a certain translator reach certain standards, degradation prompt is given to the translator, a plurality of lists after the prompt are given are observation stages, and degradation processing is given if the bad evaluation rate is not obviously reduced.

The invention also provides a second change rule as shown in fig. 6, taking three grades of scores as an example, and adding a certain score, such as 0.01 score, to the score of a translator after receiving a good score; the scoring of each received Chinese bid is not changed; each time a bad score is received, its score is decreased by a certain score, such as 0.01 (if the user feedback score is more than three, different weight scores can be set for each score, and the total score of the translator is increased or decreased). As the number of the translator receiving orders increases, the total score of the translator is changed continuously, and when the total score is higher than the interval of the grade of the translator, the translator is upgraded, otherwise, when the total score is lower than the interval of the grade of the translator, the translator is downgraded.

In addition, the interpreter level change rule provided by the invention also comprises supplementary rules for balancing the selection tendency of the user. Because different users have different behavior habits, some users are more severe and often give poor comments, and some users give good comments on the contrary. Therefore, when the evaluation number of the user reaches a certain standard (with statistical value), the weight corresponding to the good evaluation and the bad evaluation can be modified according to the good evaluation rate and the bad evaluation rate given by the user. As shown in fig. 7, if the user often gives good comments and rarely gives bad comments, the weight of the bad comments is increased when the bad comments are counted, and the weight of the good comments can be appropriately reduced or not processed. On the contrary, if the user is very critical, often gives bad comments and rarely gives good comments, the weight of the user can be appropriately increased when the user counts the good comments, and the weight of the user can be appropriately decreased or the user does not perform processing when the user counts the bad comments. Therefore, the feedback scores of the users can be compensated to a certain extent according to the behavior tendency of the users, so that the influence of malicious poor scores and other phenomena on the fairness of the scoring system is reduced. It is emphasized that the weight change shown in fig. 7 is only a certain example and does not limit the application scope of the present invention.

The interpreter grading method also comprises a self-improvement scheme, namely the system can count various characteristics of the interpreter with high evaluation rate and various characteristics of the interpreter with high evaluation rate, then feeds back the statistical result, improves the basic grading rule of the system and applies the basic grading rule to the newly registered interpreter. For example, if the system originally gives the same basic score to the translators holding the high-level interpreted certificate and the translators holding the national foreign language translation secondary certificate, and then statistics of a large number of user feedback results shows that the favorable rating of the translators holding the national foreign language translation secondary certificate is obviously higher than that of the translators holding the high-level interpreted certificate (the translators holding the two certificates are not listed in the comparison range at the same time), the system can properly increase the basic score of the national foreign language translation secondary certificate or decrease the basic score of the high-level interpreted certificate. Therefore, the scoring standard of the translator is continuously improved through big data optimization, so that the scoring result can more accurately reflect the real translation level of the translator and the fit degree of the requirement of the user.

Example 2:

this example will show a detailed set of translator scoring methods based on example 1, and is used to illustrate specific embodiments of the present invention.

The first step is as follows: and (5) registering the identity of the translator. The registration process is divided into four subdivision steps:

1) and (3) identity authentication: the translator needs to provide an identification card or driver's license or passport to prove his legitimate identity;

2) basic information entry: the translator must enter his name and select his gender, age, translation language, and area of expertise based on the system prompts. Alternative areas of excellence include financial, life sciences, automotive engineering, legal court, scientific and technological internet, fashion art, engineering and construction, sports music, etc.;

3) language, translation related information entry: the translator needs to select and fill in the acquired certificate and level examination score information related to the selected language, including a national translation professional qualification certificate, a national foreign language translation certificate, a Shanghai city foreign language interpretation post qualification certificate, a national business English translation qualification examination score, a professional English eight-level certificate and the like, which is shown in detail in FIG. 8;

4) and (3) auxiliary information input: the translator needs to select and input whether the translator has overseas tourism and life experiences, translate the working time and provide related evidences, and upload the working resume or related qualification certificate of the translator in the field of excellence;

5) scoring the accents: the translator needs to finish the small segment of translation content within a specified time, the accent, the reaction time and the translation accuracy are scored by the accent evaluation software or professional, and the scoring result is recorded and stored by the system for the subsequent comprehensive scoring of the translator;

the second step is that: and scoring by the translator. The system carries out comprehensive grading according to the information input during translator registration and grades the translators. Specific scoring rules, detailed in fig. 8;

the third step: and (4) scoring the user feedback. When a user side generates a translation requirement, the system dispatches an order to a translator according to the user requirement, the translator receives the order and executes a translation instruction, and after the translation is finished, the user scores the translator in three grades according to the satisfaction degree and divides the scoring into good scoring, medium scoring and poor scoring;

the fourth step: and (6) changing the grade. When the total effective number of the receipts of a certain interpreter is more than 1000 and the goodness of evaluation is more than 95%, the goodness of evaluation and the goodness of evaluation both reach a certain standard, and the interpreter can apply for upgrading. The translator may apply for the upgrade. The first 100 after upgrading is a trial period, if the rating in the trial period is not less than 95%, the upgrading can be finally confirmed, otherwise, the original grade is returned. After returning to the original level, the translator can not apply for upgrading for a while, and can apply for upgrading again if meeting the upgrading application condition after meeting 100 sheets again; when the effective receiving number of a certain translator is larger than 200 and the bad evaluation rate reaches 20%, the system gives a degradation prompt to the translator, 50 units after the prompt is given are an observation stage, and degradation processing is carried out if the bad evaluation rate is not lower than 20%.

In addition, the level change rule includes additional rules for balancing the user selection tendency. The system counts the bad rating rate given by each user with the rating number more than 50 and the average bad rating rate of all users, if the bad rating rate of a certain user is more than 4 times of the average bad rating rate of the system, the user is marked as a bad rating inclined user; and if the bad rating of a certain user is lower than 0.25 time of the average bad rating of the system, marking the user as a user with a good rating tendency. For the users with poor evaluation tendency, the weight of good evaluation is improved by 20 percent, and the weight of poor evaluation is reduced by 50 percent, namely, each good evaluation is 1.2, and each poor evaluation is 0.5 when the good evaluation is counted; for the users with good tendency, the poor rating weight is improved by 80%, namely each poor rating is counted as 1.8 in the process of counting the poor ratings.

Specifically, it should be noted that the method of the present embodiment may be used in other scoring systems, and the scoring method may be designed as a computer program, embedded in a learning terminal or a server, or other schemes.

Example 3:

the embodiment provides a scoring system for a translation translator, which is used for realizing the scoring method for the translation translator. As shown in FIG. 9, the translator scoring system at least comprises a translator terminal (10), a server (20);

the interpreter terminal (10) comprises at least:

the display module (11) is used for displaying input and output contents; a communication module (12) for communicating between internal modules of the translator terminal or communicating the translator terminal with the outside; a voice module (13) for inputting or outputting voice; the communication module (12) is electrically connected with the display module (11) and the voice module (13);

the server (20) comprises at least: a communication module (21) for communication between the internal modules of the server or communication between the server and the outside; a data storage module (22) for storing information generated between the server (20) modules or external information received; the scoring module (23) is used for calculating the received information and returning a scoring value and grade of the translator; the communication module (21) is electrically connected with the data storage module (22) and the scoring module (23).

Specifically, the translation translator scoring system provided by the invention further comprises a specialist terminal (30);

specifically, the special member terminal (30) also comprises an accent scoring (33) module, which is used for receiving the voice information of the interpreter and scoring the accent of the interpreter; the accent scoring module (33) is electrically connected with the communication module (32).

In particular, said interpreter terminal (10) further comprises: a registration module (14) for receiving registration information input by the interpreter; the registration module (14) is electrically connected with the communication module (12), the display module (11) and the voice module (13);

specifically, the scoring system for the translation translator further comprises a user terminal (40);

specifically, the data storage module (22) includes at least one of a temporary database (22a), a translator registration information database (22b), a user registration information database (22c), a translator scoring database (22d), and a user feedback information database (22e), as shown in fig. 10; wherein,

when a system needs to print a certain translator, the translator needs to register through a registration module (14) of a translator terminal (10), the registration module (14) is connected with a display module (11), a communication module (12) and a voice module (13), the translator knows information required to be provided by registration through the display module (11) and inputs registration information through the registration module (14), and the registration information comprises identity information of the translator, such as an identity card, a driver's license, a passport and the like, professional level information of the translator, such as a translation level certificate, a language level certificate and the like, and auxiliary information of the translator, such as overseas study, living experiences, professional funds in other fields and the like. The registration module (14) communicates registration information entered by the interpreter to the communication module (12). During registration, a translator is required to translate a piece of content, and the voice module (13) records the sound record translated by the translator and converts the sound record into an electric signal form to be transmitted to the communication module (12). To this end, the communication module (12) receives all the registration information of the translator.

A communication module (12) of the translator terminal (10) transmits all the registration information of the translator to a communication module (21) in the server (20), and the communication module (21) transmits the registration information to a data storage module (22) and stores the registration information in a translator registration information database (22b) of the data storage module (22). A scoring module (23) in the server (20) retrieves the registration information of the interpreter from a sub-module interpreter registration information database (22b) of the data storage module (22) through a communication module (21), scores the registration information of the user according to an algorithm built in the scoring module, finally obtains initial each field score and grade of the interpreter, transmits the initial each field score and grade of the interpreter to the data storage module (22) through the communication module (21), and records the information in a sub-module interpreter scoring database (22d) of the data storage module (22).

It is emphasized that the scoring module (23) in the server (20) can process the voice information in the registration information of the translator through the built-in accent scoring software and give a score, or can directly give the voice information to a specialist for scoring. The specific process is as follows:

a communication module (21) in a server (20) calls the translation voice information input during the registration of the translator from a sub-module translator registration information database (22b) of a data storage module (22) and transmits the translation voice information to a communication module (32) in a special member terminal (30), the communication module (32) transmits the translation voice information to an accent scoring module (33), the accent scoring module (33) converts the voice information into sound by an electric signal and outputs the sound, after the special member listens to the output sound, the accent of the translator is scored, the scoring result is input into the accent scoring module (33), the accent scoring module (33) transmits the result to the communication module (32), the communication module (32) transmits the result to the communication module (21) in the server (20), the communication module (21) transmits the result to the scoring module (23), and after the scoring module (23) obtains the accent scoring result of the translator, the initial field scores and the grades of the translators are calculated by the aid of the translation data, and the final results are stored in a sub-module translator score database (22d) of the data storage module (22).

Before a user requests to acquire translation service of a translator, the user needs to register through a registration module (43) of a user terminal (40), the registration module (43) is connected with a display module (41) and a communication module (42), the user knows information required to be provided for registration through the display module (41) and inputs registration information through the registration module (43), and the registration information comprises personal login information of the user, such as a user name, a password and the like. The communication module (42) transmits the registration information of the user to the communication module (21) in the server (20), and the communication module (21) transmits the registration information to the data storage module (22) and stores the registration information in the user registration information database (22c) of the data storage module (22).

After the successful registration, a user can initiate a translation request to the system, the user performs interface operation on a display module (41) of a user terminal (40), request information is transmitted to a communication module (21) of the server (20) through a communication module (42), the communication module (21) screens proper order receiving translator information from a sub-module translator scoring database (22d) of a data storage module (22) according to the request information, and the communication module (12) of the translator terminal (10) sends information on the display module (11) to prompt a translator to receive an order. After the order is completed, the user scores the satisfaction degree of the translation result of the translator through a feedback module (44) of a single user (40), and the scoring result is transmitted to a communication module (21) in the server (20) through a communication module (42) and finally stored in a sub-module user feedback information database (22e) of the data storage module (22). When the user feedback information database (22e) receives newly added feedback information, a detection instruction is sent to the scoring module (23) through the communication module (21), the scoring module (23) calls information in the sub-module user feedback information database (22e) and the interpreter scoring database (22d) of the data storage module (22) through the communication module (21), the scoring module (23) analyzes whether an interpreter meets the upgrading or degrading condition according to the called information, if the upgrading condition is met, an upgrading prompt is sent to the interpreter through the communication module (21) and the communication module (12), the interpreter selects upgrading after receiving the upgrading prompt, and the upgrading information is transmitted to the sub-module interpreter scoring database (22d) of the data storage module (22) through the communication module (12) and the communication module (21) to modify interpreter grade information in the upgrading prompt. After the translator is upgraded, the translator enters a trial period, the trial period lasts for a plurality of single quantities, after the translator is full of the trial single quantities, a user feedback information database (22e) sends a detection instruction to a scoring module (23) through a communication module (21), the scoring module (23) calls information in a sub-module user feedback information database (22e) and a translator scoring database (22d) of a data storage module (22) through the communication module (21), the scoring module (23) detects whether the evaluation rate of the translator in the trial period is larger than a preset reference value of the system or not according to the called information, if the condition is met, the upgrade is finally confirmed, the scoring module (23) sends an instruction to the sub-module translator scoring database (22d) of the data storage module (22) through the communication module (21), the trial period is terminated, and the upgrade of the translator is confirmed.

If the grade information of the translator is analyzed by the grading module (23) according to the called information and meets the grade condition after a certain order is finished, a grade risk prompt is sent to the translator through the communication module (21) and the communication module (12), and meanwhile, the information is transmitted to a sub-module translator grade database (22d) of the data storage module (22) through the communication module (21), and the translator grade information is modified. When the translator runs into a demotion trial period, the trial period lasts for a plurality of single amounts, after the translator is full of the trial single amounts, a user feedback information database (22e) sends a detection instruction to a scoring module (23) through a communication module (21), the scoring module (23) calls information in a submodule user feedback information database (22e) and a translator scoring database (22d) of a data storage module (22) through the communication module (21), the scoring module (23) detects whether the poor scoring rate of the translator in the trial period is larger than a preset reference value of the system or not according to the called information, if the condition is met, degradation is finally confirmed, the scoring module (23) sends an instruction to the submodule translator scoring database (22d) of the data storage module (22) through the communication module (21), the trial period is terminated, and the demotion and upgrading are confirmed.

It is emphasized that the scoring method for a translation translator provided by the present invention can be implemented by the scoring system for a translation translator provided by the present invention, and can also be implemented by other systems.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims

1. A method for scoring a translation translator, comprising at least the steps of:

step S001: the translator registers and inputs the registration information;

Step S205: prompting the translator that the degradation risk exists, and the translator is in the trial period of the degradation stage;

step S206: if the evaluation index obtained by the translator in the degraded trial period reaches a preset standard value, the original grade of the translator is reserved; and if the evaluation index obtained by the translator in the trial period of degradation does not reach the preset standard value, performing degradation and upgrading on the translator.

2. A scoring method for translation translators as claimed in claim 1, wherein in said step S204, after the translator who has not obtained the upgrade permission needs to meet the preset singular number again, if the evaluation index of the translator reaches the preset standard value again, the translator can obtain the qualification for applying the upgrade again.

3. A scoring method for translation translators as claimed in claim 1, wherein the grade change rule of the translator of step S004 is further obtained by:

step S300: acquiring an initial score and an initial grade of an interpreter;

step S301: correspondingly increasing or decreasing the grade of the translator according to the good grade number, the bad grade number and the medium grade number received by the translator;

step S302: if the grade of the interpreter is larger than the grade interval of the current grade, upgrading the interpreter, and if the grade of the interpreter is smaller than the grade interval of the current grade, degrading the interpreter.

4. A scoring method for translation translators as claimed in claim 1, wherein said scoring result of translator in step S002 comprises at least two part scores: the total field score and the individual field plus components, and the scoring result of the translator in a certain field is the sum of the total field score and the field plus components.

5. A scoring method for an interpreter as recited in claim 1, wherein said interpreter registration process of step S001 is implemented by providing photos/scans of related certificates on the internet for on-line transaction or by carrying related certificates to a designated location by the interpreter.

6. A scoring method for translation translators as claimed in claim 1, wherein said step S002 is performed by ranking said translators into at least three.

7. A scoring method for translation translators as claimed in claim 1, wherein said step S004 further includes a supplementary rule for balancing the user' S preference, said supplementary rule including the steps of:

step S004 a: counting the average bad evaluation rate of all users;

step S004 b: if the poor rating of a certain user is higher than the average poor rating of a preset multiple, marking the user as a poor rating inclined user; if the poor rating of a certain user is lower than the preset multiple average poor rating, marking the user as a user with a good rating tendency;

step S004 c: for users with poor evaluation tendency, the good evaluation weight is improved, and the poor evaluation weight is reduced; for users with a tendency of good comment, the poor comment weight is improved, and the good comment weight is reduced or kept unchanged.

8. A scoring method for an interpreter according to claim 1, wherein said scoring criteria for comprehensive scoring of an interpreter in step S002 is self-optimized, and said self-optimization method comprises:

s002 a: counting the characteristics of the translators with the high evaluation rate higher than a preset standard value and the characteristics of the translators with the poor evaluation rate higher than the preset standard value;

s002 b: at least one of the following two operations is performed,

operation one: the scoring weight of the common characteristics of the translators with the scoring rate higher than the preset standard value is improved;

and operation II: and reducing the scoring weight of the common characteristics of the interpreters with the poor scoring rate higher than the preset standard value.

9. A scoring method for translation translators as claimed in claim 1, wherein in said step S002, the scores of the language and translation related registration information are not superimposed.

10. A scoring method for translation translators as claimed in claim 1, wherein said translator registration information of step S001 at least includes:

11. A scoring method for a translator according to claim 10, wherein said information documents proving the translation level of the translator include at least one of a national translation professional qualification certificate, a national foreign language translation certificate, a shanghai city foreign language interpretation post qualification certificate, a business english examination score and a professional english certificate.

12. A scoring method for an interpreter as recited in claim 10, wherein said entry of an accent score results in establishing a qualified score line, and canceling the translator registration qualification when the interpreter's accent score is lower than a non-qualified line.

13. A scoring method for an interpreter as recited in claim 10, wherein said translator areas of expertise include at least one of financial, life sciences, automotive engineering, law courts, scientific and technological networks, fashion arts, construction of projects, sports music.

14. A scoring method for translation translators as recited in claim 10, wherein said accent score results in a passing line, and wherein translators below said passing line are disqualified for registration.

15. A scoring system for translation translators, characterized by comprising at least a translator terminal (10) and a server (20);

16. A scoring system for a translation translator according to claim 15, wherein the scoring system further comprises a specialist terminal (30);

the specialist terminal (30) comprises at least: a display module (31) for displaying input and output contents; a communication module (32) for communicating between internal modules of the translator terminal or communicating the translator terminal with the outside; the communication module (32) is electrically connected with the display module (31).

17. A scoring system for translation translators as claimed in claim 16, wherein said specialist terminal (30) further comprises an accent scoring (33) module for receiving the translator's speech information and scoring the accent;

18. A scoring system for translation translators as claimed in claim 15, wherein said translator terminal (10) further comprises: a registration module (14) for receiving registration information input by the interpreter; the registration module (14) is electrically connected with the communication module (12), the display module (11) and the voice module (13).

19. A scoring system for a translation translator according to claim 15, wherein the scoring system for a translation translator further comprises a user terminal (40);

the user terminal (40) comprises at least: a display module (41) for displaying input and output contents; a communication module (42) for communicating between internal modules of the translator terminal or communicating the translator terminal with the outside; a registration module (43) for receiving registration information input by a user; a feedback module (44) for inputting user feedback information for the translator; the communication module (42) is electrically connected with the display module (41), the feedback module (44) and the registration module (43).

20. A scoring system for translation translators as claimed in claim 15, wherein said data storage module (22) comprises at least one of a temporary database (22a), a translator registration information database (22b), a user registration information database (22c), a translator scoring database (22d), a user feedback information database (22 e);

and the user feedback information database (22e) is used for storing the feedback information of the user to the interpreter.

21. A scoring system for translation translators as claimed in claim 15, characterized in that said server (20) is located in the translator terminal (10), or in the specialist terminal (30), or in the user terminal (40), or the server (20) is independent of each terminal; the server (20) is a local server or a cloud server.

22. A scoring system for a translation translator comprising a translator terminal (10) and a server (20), characterized in that it comprises the scoring method for a translation translator according to any one of claims 1 to 14.