CN112766776A - Translation order pushing method and system - Google Patents
Translation order pushing method and system Download PDFInfo
- Publication number
- CN112766776A CN112766776A CN202110108531.2A CN202110108531A CN112766776A CN 112766776 A CN112766776 A CN 112766776A CN 202110108531 A CN202110108531 A CN 202110108531A CN 112766776 A CN112766776 A CN 112766776A
- Authority
- CN
- China
- Prior art keywords
- score
- alternative
- translator
- translation
- order
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a translation order pushing method and a translation order pushing system, wherein the method comprises the following steps: screening alternative translators matched with the user orders from the resource pool according to a preset filtering rule; obtaining a resource appropriate value of the alternative translator according to the document value, the service value, the translation speed value and the activity value of the alternative translator; and clustering the resource appropriate scores of the alternative translators, and pushing the user orders to the corresponding alternative translators in sequence from high to low of the clustering scores. According to the invention, the whole process from client ordering, resource filtering, proper value calculation, order dispatching and final translator receiving is completed by a machine, no manual intervention is needed in the whole process, and the time consumption from the whole process to the final translator order receiving is in the unit of second, so that the resource scheduling efficiency is greatly improved, the cost is reduced, and the core competitiveness of the whole platform is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a translation order pushing method and system.
Background
With the rise of the internet, the translation industry is developing towards a large-scale platform processing direction, online stream transfer of translation orders forms a mainstream, the translation orders need to efficiently and quickly reach proper translators, the platform needs to solve the problem of optimal utilization of translator resources, and therefore matching of the orders and the translators and pushing of the orders are the core of scheduling of each platform. At a certain moment, thousands of translation orders exist, and meanwhile, thousands of vacant translators exist, so that the optimal matching of the orders and the translators is completed, the matching rate and the transaction rate are improved to the maximum extent, and the problem that the existing large translation platforms are difficult to solve is always solved.
At present, two main ways of scheduling orders are provided, one way is manual identification scheduling, the requirement for people is high, translation documents can be analyzed and judged, due to subjectivity and limitation of reading and understanding capacity of people, efficiency of the method can be underground and not objective, results can generate large deviation due to judgment errors of people, and one person has certain upper limit on resource mastering of a translator, so that the method not only consumes time, but also consumes large manpower and material resources.
The second method is that a machine matches a translator through a similarity algorithm, efficiency is higher than that of manual identification, but the method cannot achieve effective utilization of resources, the translator matched by the method may have a situation that the translator is not on line currently or is inactive in the current time period, the translator may see that order push data refuses order taking, and even the matched translator has poor overall service evaluation, so that only in this way, the efficiency of platform order taking is reduced, and the risk of customer loss caused by customer experience on the platform is influenced finally by complaint rate increase.
Disclosure of Invention
The invention provides a translation order pushing method and system, which are used for solving the defect of low platform order receiving efficiency in the prior art and realizing efficient pushing of translation orders.
The invention provides a translation order pushing method, which comprises the following steps:
screening alternative translators matched with the user order from a resource pool according to a preset filtering rule, wherein the resource pool comprises personal information of a plurality of translators;
obtaining a resource appropriate value of the alternative translator according to the document value, the service value, the translation speed value and the activity value of the alternative translator;
and clustering the resource appropriate scores of the alternative translators, and pushing the user orders to the corresponding alternative translators in sequence from high to low of the clustering scores.
According to the translation order pushing method provided by the invention, the resource appropriateness score of the alternative translator is obtained according to the document score, the service score, the translation speed score and the activity score of the alternative translator, and the method comprises the following steps:
Y＝K1*Xspeed+K2*Xservice+K3*Xactive+K4*Xdocument；
wherein, Xspeed represents the translation speed score, Xservice represents the service score, Xactive represents the liveness score, Xdocument represents the document score, K1Expressing a first preset weight, K, corresponding to the translation speed score2A second preset weight, K, corresponding to said service score3A third preset weight, K, corresponding to the liveness score4And expressing a fourth preset weight corresponding to the document score.
According to the translation order pushing method provided by the invention, the translation speed score is obtained by the following method:
if the number of completed orders corresponding to the alternative translator exceeds a preset number threshold, calculating an actual translation speed corresponding to each completed order according to the translation time length of each completed order of the alternative translator and the translation word number of each completed order;
clustering actual translation speeds corresponding to each finished order of the alternative translators into a low gear speed, a middle gear speed and a high gear speed, and taking the average speed of the middle gear speed as the final translation speed of the alternative translators.
The translation order pushing method provided by the invention further comprises the following steps:
and if the number of the finished orders corresponding to the alternative translator does not exceed the preset number threshold value, taking a preset standard speed as the final translation speed of the alternative translator.
According to the translation order pushing method provided by the invention, the service score is obtained by the following method:
obtaining an evaluation score of each completed order according to the value of each completed order, the type of each completed order, the evaluation star level of each completed order, the evaluation content of each completed order and the evaluation label of each completed order corresponding to the alternative translator;
acquiring the weight corresponding to each different evaluation score according to the total proportion of the number of each different evaluation score in all the evaluation scores;
carrying out weighted average according to each different evaluation score and the weight corresponding to each different evaluation score to obtain the evaluation score corresponding to the alternative translator;
carrying out weighted average according to the service frequency of each finished order, the service quality of each finished order and the service response of each finished order to obtain a communication score corresponding to the alternative translator;
and obtaining a service score corresponding to the alternative translator according to the evaluation score corresponding to the alternative translator and the communication score corresponding to the alternative translator.
According to the translation order pushing method provided by the invention, the document score is obtained by the following method:
obtaining alternative manuscripts corresponding to the alternative translators from a history resource library through a document similarity algorithm, wherein the alternative manuscripts are the first N manuscripts of which the similarity with the text to be translated in the user order is higher than a preset similarity threshold, the history resource library is used for storing all the history manuscripts in the finished orders of the translators, and N is a positive integer and is greater than 0;
and acquiring the document score of the alternative translator according to the contribution score of each alternative contribution.
According to the translation order pushing method provided by the invention, the activity score is obtained by the following method:
acquiring the active times of the alternative translator in each preset time period according to the browsing times and the clicking times of the alternative translator in each preset time period;
acquiring a weight coefficient of each preset time period according to the active times of each preset time period and the maximum active times of all the preset time periods;
acquiring the active times of each day according to the active times of each preset time period and the weight coefficient of each preset time period;
and acquiring the active score of the alternative translator according to the active times of the alternative translator in M days and the active times of the alternative translator in Q hours, wherein M is greater than 0 and is a positive integer, Q is greater than 0, and Q is a positive integer.
The invention also provides a translation order pushing system, which comprises:
the system comprises a filtering module, a processing module and a processing module, wherein the filtering module is used for screening alternative translators matched with a user order from a resource pool according to a preset filtering rule, and the resource pool comprises personal information of a plurality of translators;
the score calculation module is used for acquiring the resource appropriate score of the alternative translator according to the document score, the service score, the translation speed score and the activity score of the alternative translator;
and the pushing module is used for clustering the resource appropriateness scores of the alternative translators and sequentially pushing the user orders to the corresponding alternative translators from high to low of the clustering scores.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the translation order pushing method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the translation order pushing method as described in any of the above.
According to the translation order pushing method and system provided by the invention, the whole process is completed by a machine from the client ordering, the resource filtering, the appropriate value calculation, the order dispatching and the translator obtaining, the whole process does not need manual intervention, and the time consumption from the whole process to the last translator order receiving process is in the second level, so that the resource scheduling efficiency is greatly improved, the cost is reduced, and the core competitiveness of the whole platform is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flowchart of a translation order pushing method according to the present invention;
FIG. 2 is a block diagram of a translation order pushing system according to the present invention using a translation order pushing method;
FIG. 3 is a schematic structural diagram of a translation order pushing system according to the present invention;
fig. 4 is a schematic physical structure diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention mainly aims to improve the efficiency of resource scheduling of the translation platform and efficiently and quickly deliver a proper order to a proper translator. Only when the proper resources are matched, the requirements of the customers can be met to the maximum extent. Therefore, the embodiment of the present invention introduces a concept of "resource appropriateness", and in the embodiment of the present invention, the high or low of the resource appropriateness score can represent the high or low degree of appropriateness of the current order.
An embodiment of the present invention provides a translation order pushing method, as shown in fig. 1, the method includes:
the embodiment of the invention mainly aims at a translation order pushing system, firstly, a user places an order on the system, fills contents such as translation texts, translation languages, translation time, professional degree and the like, and generates order data.
110, screening candidate translators matched with the user order from a resource pool according to a preset filtering rule, wherein the resource pool comprises personal information of a plurality of translators;
and the resource filtering module takes out order data from the order placing queue, and filters out resource data meeting the conditions from the resource pool according to preset filtering rules such as the capability of a translator, the state of the translator and the like, wherein the resource data meeting the conditions are alternative translators matched with the user orders.
The translator ability refers to the professional ability of the translator, and the translator is divided into a plurality of levels through the professional ability, so that the abstract translator ability is quantized; here, the translated text is classified into several levels by the professional degree corresponding to the professional degree of the translated text in the user order, and a translator having a high level of ability can translate the translated text having a low level of professional degree.
The state of the translator comprises states of the translator in translation state opening and translation state closing, wherein the translation state opening indicates that the translator is in a state of being capable of translating, namely, a state of being capable of receiving orders, and the translation state closing indicates that the translator is in a state of not being capable of translating, namely, indicates that the translator is not capable of receiving orders.
And screening alternative translators which can be compatible with the professional degree of the user order, the translation languages and the translation states of the user order from the resource pool according to a preset filtering rule.
120, obtaining a resource appropriateness score of the alternative translator according to the document score, the service score, the translation speed score and the activity score of the alternative translator;
evaluating each alternative translator from the aspects of document score, service score, translation speed score and activity score, wherein the document score represents the similarity of similar manuscripts once completed by the alternative translator, the service score represents the service quality of the alternative translator in the completed order, the translation speed score represents the translation speed of the alternative translator, and the activity score represents the online frequency of the alternative translator.
In a specific embodiment, the resource fitness score of the alternative translator is obtained by adding the document score, the service score, the translation speed score and the activity score.
In another embodiment, the resource fitness score for the candidate translator is obtained by a weighted average of the document score, the service score, the translation speed score, and the liveness score.
And 130, clustering the resource appropriateness scores of the alternative translators, and sequentially pushing the user orders to the corresponding alternative translators from high to low of the clustering scores.
The order dispatching engine is used for clustering alternative translators according to proper degree values, clustering aims to enable translators with similar values to be divided into a group, pushing is carried out once according to the group as a unit, clustering is carried out to form a plurality of groups, then pushing is carried out for several times, the pushing sequence is carried out according to the groups with high values to low values, the translators with high values have the opportunity of receiving orders preferentially, and the life cycle of the whole pushing thread is only up to the time when the translators receive orders.
And finally, the dispatching thread directly dispatches the order data in the dispatching queue to the resource terminal according to the corresponding rule.
The embodiment of the invention provides a translation order pushing method, which comprises the steps of ordering by a client, filtering resources, calculating appropriate scores, dispatching orders and obtaining by a translator, wherein the whole process is completed by a machine without manual intervention, and the time consumption from the whole process to the last translator is in second level, so that the efficiency of resource scheduling is greatly improved, the cost is reduced, and the core competitiveness of the whole platform is improved.
On the basis of the foregoing embodiment, preferably, the obtaining a resource appropriateness score of the candidate translator according to the document score, the service score, the translation speed score, and the activity score of the candidate translator includes:
Y＝K1*Xspeed+K2*Xservice+K3*Xactive+K4*Xdocument；
wherein, Xspeed represents the translation speed score, Xservice represents the service score, Xactive represents the liveness score, Xdocument represents the document score, K1Expressing a first preset weight, K, corresponding to the translation speed score2A second preset weight, K, corresponding to said service score3A third preset weight, K, corresponding to the liveness score4And expressing a fourth preset weight corresponding to the document score.
Analyzing according to the user order data of the translation platform to obtain K1To K4The specific gravity of the resource historical manuscript is 0.05, 0.30, 0.20 and 0.45, the document score is related to whether the resource historical manuscript makes a similar order or not, the service score is related to the quantification of the resource historical order service process, the translation speed score is related to the completion efficiency of the resource manuscript, the activity score is related to the activity degree of the resource in the current period of time, and the K can be sequentially adjusted according to the emphasis point of the translation platform to dispatch the order1To K4To achieve the desired effect of different platforms.
On the basis of the above embodiment, preferably, the translation speed score is obtained by:
in the embodiment of the invention, since the translation speed of a translator may fluctuate greatly between every two orders, the translation speed of the candidate translator may not be represented by the translation speed of one order, and the translation speed of the candidate translator is represented by averaging the translation speeds of a plurality of orders.
If the number of completed orders corresponding to the alternative translator exceeds a preset number threshold, calculating an actual translation speed corresponding to each completed order according to the translation time length of each completed order of the alternative translator and the translation word number of each completed order;
if the number of orders that the alternative translator has completed exceeds the preset number threshold, in the embodiment of the present invention, the preset number threshold is set to 20, that is, when the alternative translator has completed more than 20 orders, the actual translation speed of each completed order is calculated.
The specific calculation method is as follows:
1. and according to the language pair, the translation word number and the correction translation time length of each list of the alternative translator, dividing the correction translation time length by the translation word number to obtain the translation speed of each list of the alternative translator.
The corrected translation time length is the order submitting time minus the order getting time, and if the order submitting time and the order getting time are both within the working time period, the order submitting time minus the order getting time is the corrected translation time length.
If the order submission time and the order pickup time are within the non-working time period, then corrections to the times are needed.
Clustering actual translation speeds corresponding to each finished order of the alternative translators into a low gear speed, a middle gear speed and a high gear speed, and taking the average speed of the middle gear speed as the final translation speed of the alternative translators.
2. And clustering the actual translation speed of each list by using a K-means clustering algorithm, and dividing all the actual translation speeds into three types to obtain a high-grade speed, a medium-grade speed and a low-grade speed.
3. And taking the median value of the middle class speeds obtained in the step 2 as the final translation speed of the alternative translator.
On the basis of the foregoing embodiment, preferably, if the number of completed orders corresponding to the candidate translator does not exceed the preset number threshold, a preset standard speed is used as the final translation speed of the candidate translator.
And taking the preset standard speed as the final translation speed of the alternative translator when the number of the completed orders is less than 20.
The predetermined standard speed in this case is 200 words/hour when the translated language is four languages of chinese, japanese, and tai, and is 150 words/hour when the translated language is latin.
In summary, the translation speed score is calculated as follows:
wherein, XspeedRepresenting the final translation speed, S representing a preset standard speed, S representing the actual translation speed, a representing an adjustable constant, a>In the embodiment of the present invention, a is 1.
On the basis of the above embodiment, preferably, the service score is obtained by:
obtaining an evaluation score of each completed order according to the value of each completed order, the type of each completed order, the evaluation star level of each completed order, the evaluation content of each completed order and the evaluation label of each completed order corresponding to the alternative translator;
acquiring the weight corresponding to each different evaluation score according to the total proportion of the number of each different evaluation score in all the evaluation scores;
carrying out weighted average according to each different evaluation score and the weight corresponding to each different evaluation score to obtain the evaluation score corresponding to the alternative translator;
carrying out weighted average according to the service frequency of each finished order, the service quality of each finished order and the service response of each finished order to obtain a communication score corresponding to the alternative translator;
and obtaining a service score corresponding to the alternative translator according to the evaluation score corresponding to the alternative translator and the communication score corresponding to the alternative translator.
In the embodiment of the invention, Xservice is evaluation score + communication score.
The evaluation score was calculated as follows:
x1, value of order; x2, type of evaluation; x3, rating star rating; x4, rating content/length; x5, evaluation tag.
The idea of the computational logic: the high-value order should have a corresponding high-quality evaluation, and the calculation steps are as follows:
1. x3 (x2+ x4+ x5)/x1 is obtained, and the evaluation score Y is obtained after correction.
2. And obtaining the proportion Pi of the number of each Yi of each candidate translator to the total evaluation of the candidate translators.
3. Summary sum (Yi Pi) evaluate _ score, the mean of evaluate _ score was taken for candidate translators without evaluation scores.
The communication score comprises characteristics of three aspects of service frequency, service quality and service response, and the calculation steps are as follows:
1. service frequency: number of messages sent per order by the client/number of messages sent per order by the interpreter.
2. Quality of service: total words per message sent by the client/total words per message sent by the interpreter.
3. Service response: the time interval between the first communication and the last communication of each client/translator.
The calculation logic is as follows:
1. and respectively obtaining scores of the three characteristics compared with the average value of the characteristics.
2. Three feature scores were aggregated.
3. All the three features need to be compared with the average value of the feature to obtain proportions, and the weights of the three features are 4, 3 and 3 respectively.
On the basis of the above embodiment, preferably, the document score is obtained by:
obtaining alternative manuscripts corresponding to the alternative translators in a historical resource library through a document similarity algorithm, wherein the alternative manuscripts are the first N manuscripts of which the similarity with the text to be translated in the user order is higher than a preset similarity threshold value, and the historical resource library is used for storing the historical manuscripts in all completed orders of the translators;
and acquiring the document score of the alternative translator according to the contribution score of each alternative contribution.
The document score is calculated as follows:
Xdocument＝39*rank/(1-num)+100-39/(1-num)；
the specific algorithm is as follows:
1. and comparing the manuscripts of the order with resource history manuscripts in a history library by a document similarity algorithm, and taking out the first N manuscripts with the highest scores of the same resources.
2. The score of the whole document is controlled to be between 50 and 100, the score of no document is 50 at the lowest, namely the score of the resource with the document score can be controlled to be between [61,100 ].
3. rank is an alternative translator document ranking name, such as num 40, i.e., the top 40, Xdocument 100 when rank 1, Xdocument 61 when rank 40, and Xdocument 91 when rank 10. num 90, i.e., the above 90, x document 100 when rank 1, and x document 61 when rank 90; when rank is 10, Xdocument is 96.06.
On the basis of the above embodiment, preferably, the liveness score is obtained by:
acquiring the active times of the alternative translator in each preset time period according to the browsing times and the clicking times of the alternative translator in each preset time period;
acquiring a weight coefficient of each preset time period according to the active times of each preset time period and the maximum active times of all the preset time periods;
acquiring the active times of each day according to the active times of each preset time period and the weight coefficient of each preset time period;
and acquiring the active score of the alternative translator according to the active times of the alternative translator in M days and the active times of the alternative translator in Q hours, wherein M is greater than 0 and is a positive integer, Q is greater than 0, and Q is a positive integer.
The activity score is calculated as follows:
in the embodiment of the invention, the value of M is 30, the value of Q is 1, and according to the historical active data of the alternative translator in the previous 30 days, the hour _ active represents the real-time active data of the previous hour.
HF is 30, a1 is 0.5, and a2 is 0.5.
The specific algorithm is as follows:
1. the data source is as follows: browsing records and click record logs generated by the alternative translators on the platform are used as basic data sources, the importance of the browsing records is weaker than that of the click records, so that the weight of the browsing records is 0.4, the weight of the click records is 0.6, and the times of each hour and each time interval of the alternative translators are summarized respectively.
2. According to the distribution of the platform order time interval, the time interval is divided into 12 intervals:
23-2，2～9，9-10，10～11，11～12，12～14，14～15，15～16，16～17，17～18，18～19，19～23。
3. considering that each time interval is different and the distribution characteristics of orders are combined, taking the order in the maximum time interval as a reference, and calculating the ratio of orders in other time intervals to the order in the time interval to obtain a time interval proportion weight coefficient as follows:
ratio＝[0.2，0.1，0.4，0.8，0.9，0.8，0.8，1，0.9，0.8，0.5，1]。
4. calculating the total activity score of the alternative translators in the last 30 days:
fsum＝sum(Tday*fi)，i＝1：30；
tday exp (-K × Day), K represents an adjustable constant, resulting in a specific value K ═ e ^ -1;
day ═ 1.. 30], take the data of the last 30 days, the active times per Day f1... fi... f30 of the current period of nearly 30 days.
5. Activity reference of the current time interval: f ratio [ i ] r1, where r1 is set to 50.
On the basis of the method, the invention designs a translation order pushing system by utilizing the method, as shown in fig. 2, the system consists of two blocks, wherein one block is a matching engine and is mainly used for calculating the appropriate value of resources; the other block is a dispatching engine which mainly sorts, aggregates and groups the resources and dispatches the resources.
The matching engine is mainly used for calculating resource appropriateness scores, the current appropriateness scores are composed of four blocks including document scores, service scores, speed scores and liveness scores, and the four blocks of scores are summarized and then presented in a percentage mode.
The order dispatching engine performs the following operations:
1. taking the resource appropriate value array A from the matching queue by the dispatching engine, and sorting the values from high to low;
2. calculating the upper limit D of the dispatching number boundary to be B/C according to the dispatching number time boundary B and each resource time interval C set by the rule;
3. taking out the data of the boundary upper limit D from the array A to form a new score array E, carrying out ordered clustering on the score array E, and aggregating the data with similar scores into a group;
4. traversing each group of data, generating a dispatching task F aiming at each group of data, calculating dispatching time starting time H according to each dispatching resource time interval C and the current group resource length G, calculating dispatching ending time I according to B, and putting the data into a dispatching queue;
5. the dispatching thread takes out dispatching data from the dispatching queue, and if the dispatching finishing time I is less than the current time or the order is already picked up, the current dispatching task is directly terminated and deleted from the dispatching queue; if the starting time H of the dispatching time is less than or equal to the current time, the task is directly dispatched and deleted from the current thread and the queue; if the above conditions are not met, the dispatching thread puts the task into the dispatching queue again.
An embodiment of the present invention provides a translation order pushing system, as shown in fig. 3, the system includes a filtering module 301, a score calculating module 302, and a pushing module 303, where:
the filtering module 301 is configured to screen candidate translators matched with the user order from a resource pool according to a preset filtering rule, where the resource pool includes personal information of multiple translators;
the score calculation module 302 is configured to obtain a resource appropriateness score of the candidate translator according to the document score, the service score, the translation speed score and the activity score of the candidate translator;
the pushing module 303 is configured to cluster the resource appropriateness scores of the alternative translators, and sequentially push the user orders to the corresponding alternative translators from high to low of the cluster scores.
The present embodiment is a system embodiment corresponding to the above method, and please refer to the above method embodiment for details, which is not described herein again.
An embodiment of the present invention provides an electronic device, as shown in fig. 4, the electronic device may include: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. Processor 410 may invoke logic instructions in memory 430 to perform a translation order pushing method comprising:
screening alternative translators matched with the user order from a resource pool according to a preset filtering rule, wherein the resource pool comprises personal information of a plurality of translators;
obtaining a resource appropriate value of the alternative translator according to the document value, the service value, the translation speed value and the activity value of the alternative translator;
and clustering the resource appropriate scores of the alternative translators, and pushing the user orders to the corresponding alternative translators in sequence from high to low of the clustering scores.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, which when executed by a computer, enable the computer to perform a translation order pushing method provided by the above methods, the method comprising:
screening alternative translators matched with the user order from a resource pool according to a preset filtering rule, wherein the resource pool comprises personal information of a plurality of translators;
obtaining a resource appropriate value of the alternative translator according to the document value, the service value, the translation speed value and the activity value of the alternative translator;
and clustering the resource appropriate scores of the alternative translators, and pushing the user orders to the corresponding alternative translators in sequence from high to low of the clustering scores.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform a translation order pushing method provided in each of the above, the method comprising:
screening alternative translators matched with the user order from a resource pool according to a preset filtering rule, wherein the resource pool comprises personal information of a plurality of translators;
obtaining a resource appropriate value of the alternative translator according to the document value, the service value, the translation speed value and the activity value of the alternative translator;
and clustering the resource appropriate scores of the alternative translators, and pushing the user orders to the corresponding alternative translators in sequence from high to low of the clustering scores.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A translation order pushing method is characterized by comprising the following steps:
screening alternative translators matched with the user order from a resource pool according to a preset filtering rule, wherein the resource pool comprises personal information of a plurality of translators;
obtaining a resource appropriate value of the alternative translator according to the document value, the service value, the translation speed value and the activity value of the alternative translator;
and clustering the resource appropriate scores of the alternative translators, and pushing the user orders to the corresponding alternative translators in sequence from high to low of the clustering scores.
2. The translation order pushing method according to claim 1, wherein the obtaining resource appropriateness score of the candidate translator according to the document score, the service score, the translation speed score and the activity score of the candidate translator comprises:
Y＝K1*Xspeed+K2*Xservice+K3*Xactive+K4*Xdocument；
wherein, Xspeed represents the translation speed score, Xservice represents the service score, Xactive represents the liveness score, Xdocument represents the document score, K1Expressing a first preset weight, K, corresponding to the translation speed score2A second preset weight, K, corresponding to said service score3A third preset weight, K, corresponding to the liveness score4And expressing a fourth preset weight corresponding to the document score.
3. The translation order pushing method according to claim 1 or 2, wherein the translation speed score is obtained by:
if the number of completed orders corresponding to the alternative translator exceeds a preset number threshold, calculating an actual translation speed corresponding to each completed order according to the translation time length of each completed order of the alternative translator and the translation word number of each completed order;
clustering actual translation speeds corresponding to each finished order of the alternative translators into a low gear speed, a middle gear speed and a high gear speed, and taking the average speed of the middle gear speed as the final translation speed of the alternative translators.
4. The translation order pushing method according to claim 3, further comprising:
and if the number of the finished orders corresponding to the alternative translator does not exceed the preset number threshold value, taking a preset standard speed as the final translation speed of the alternative translator.
5. The translation order pushing method according to claim 1 or 2, wherein said service score is obtained by:
obtaining an evaluation score of each completed order according to the value of each completed order, the type of each completed order, the evaluation star level of each completed order, the evaluation content of each completed order and the evaluation label of each completed order corresponding to the alternative translator;
acquiring the weight corresponding to each different evaluation score according to the total proportion of the number of each different evaluation score in all the evaluation scores;
carrying out weighted average according to each different evaluation score and the weight corresponding to each different evaluation score to obtain the evaluation score corresponding to the alternative translator;
carrying out weighted average according to the service frequency of each finished order, the service quality of each finished order and the service response of each finished order to obtain a communication score corresponding to the alternative translator;
and obtaining a service score corresponding to the alternative translator according to the evaluation score corresponding to the alternative translator and the communication score corresponding to the alternative translator.
6. The translation order pushing method according to claim 1 or 2, wherein said document score is obtained by:
obtaining alternative manuscripts corresponding to the alternative translators from a history resource library through a document similarity algorithm, wherein the alternative manuscripts are the first N manuscripts of which the similarity with the text to be translated in the user order is higher than a preset similarity threshold, the history resource library is used for storing all the history manuscripts in the finished orders of the translators, and N is a positive integer and is greater than 0;
and acquiring the document score of the alternative translator according to the contribution score of each alternative contribution.
7. The translation order pushing method according to claim 1 or 2, wherein said liveness score is obtained by:
acquiring the active times of the alternative translator in each preset time period according to the browsing times and the clicking times of the alternative translator in each preset time period;
acquiring a weight coefficient of each preset time period according to the active times of each preset time period and the maximum active times of all the preset time periods;
acquiring the active times of each day according to the active times of each preset time period and the weight coefficient of each preset time period;
and acquiring the active score of the alternative translator according to the active times of the alternative translator in M days and the active times of the alternative translator in Q hours, wherein M is greater than 0 and is a positive integer, Q is greater than 0, and Q is a positive integer.
8. A translation order pushing system, comprising:
the system comprises a filtering module, a processing module and a processing module, wherein the filtering module is used for screening alternative translators matched with a user order from a resource pool according to a preset filtering rule, and the resource pool comprises personal information of a plurality of translators;
the score calculation module is used for acquiring the resource appropriate score of the alternative translator according to the document score, the service score, the translation speed score and the activity score of the alternative translator;
and the pushing module is used for clustering the resource appropriateness scores of the alternative translators and sequentially pushing the user orders to the corresponding alternative translators from high to low of the clustering scores.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the translation order pushing method according to any of claims 1 to 7 are implemented when the processor executes the program.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the translation order pushing method according to any of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110108531.2A CN112766776A (en) | 2021-01-27 | 2021-01-27 | Translation order pushing method and system |
| PCT/CN2021/126650 WO2022160817A1 (en) | 2021-01-27 | 2021-10-27 | Translation order pushing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110108531.2A CN112766776A (en) | 2021-01-27 | 2021-01-27 | Translation order pushing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112766776A true CN112766776A (en) | 2021-05-07 |
Family
ID=75705960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110108531.2A Pending CN112766776A (en) | 2021-01-27 | 2021-01-27 | Translation order pushing method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112766776A (en) |
| WO (1) | WO2022160817A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022160817A1 (en) * | 2021-01-27 | 2022-08-04 | 语联网（武汉）信息技术有限公司 | Translation order pushing method and system |
| CN117057365A (en) * | 2023-08-11 | 2023-11-14 | 深圳市台电实业有限公司 | Mixed conference translation method, device, electronic equipment and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290099B (en) * | 2023-09-22 | 2024-05-31 | 深圳市金证科技股份有限公司 | Computing resource adjustment method and device for cloud platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030008323A (en) * | 2001-07-20 | 2003-01-25 | 임홍균 | Method for mediating translation service between a client and a translator |
| CN103092827A (en) * | 2012-12-31 | 2013-05-08 | 武汉传神信息技术有限公司 | Method for multi-strategy interpreter manuscript automatic matching |
| CN108846590A (en) * | 2018-07-10 | 2018-11-20 | 广州市联普翻译有限公司 | A kind of translation on line order matching process, system, storage medium and terminal |
| CN110033144A (en) * | 2017-10-31 | 2019-07-19 | 语联网（武汉）信息技术有限公司 | A kind of the dynamic self-adapting appraisal procedure and system of translation project risk |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110066469A1 (en) * | 2009-09-15 | 2011-03-17 | Albert Kadosh | Method and system for translation workflow management across the internet |
| CN105138521B (en) * | 2015-08-27 | 2017-12-22 | 武汉传神信息技术有限公司 | A kind of translation industry risk project general recommendations interpreter's method |
| CN112766776A (en) * | 2021-01-27 | 2021-05-07 | 语联网（武汉）信息技术有限公司 | Translation order pushing method and system |
-
2021
- 2021-01-27 CN CN202110108531.2A patent/CN112766776A/en active Pending
- 2021-10-27 WO PCT/CN2021/126650 patent/WO2022160817A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030008323A (en) * | 2001-07-20 | 2003-01-25 | 임홍균 | Method for mediating translation service between a client and a translator |
| CN103092827A (en) * | 2012-12-31 | 2013-05-08 | 武汉传神信息技术有限公司 | Method for multi-strategy interpreter manuscript automatic matching |
| CN110033144A (en) * | 2017-10-31 | 2019-07-19 | 语联网（武汉）信息技术有限公司 | A kind of the dynamic self-adapting appraisal procedure and system of translation project risk |
| CN108846590A (en) * | 2018-07-10 | 2018-11-20 | 广州市联普翻译有限公司 | A kind of translation on line order matching process, system, storage medium and terminal |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022160817A1 (en) * | 2021-01-27 | 2022-08-04 | 语联网（武汉）信息技术有限公司 | Translation order pushing method and system |
| CN117057365A (en) * | 2023-08-11 | 2023-11-14 | 深圳市台电实业有限公司 | Mixed conference translation method, device, electronic equipment and storage medium |
| CN117057365B (en) * | 2023-08-11 | 2024-04-05 | 深圳市台电实业有限公司 | Mixed conference translation method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022160817A1 (en) | 2022-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112766776A (en) | Translation order pushing method and system | |
| US9854098B2 (en) | Electronic communication routing based data accuracy | |
| CN111464583B (en) | Computing resource allocation method, device, server and storage medium | |
| García Rodríguez et al. | Public procurement announcements in spain: regulations, data analysis, and award price estimator using machine learning | |
| CN105225135B (en) | Potential customer identification method and device | |
| CN111352962A (en) | Client portrait construction method and device | |
| US10191985B1 (en) | System and method for auto-curation of Q and A websites for search engine optimization | |
| CN111489201A (en) | Method, device and storage medium for analyzing customer value | |
| CN107247728B (en) | Text processing method and device and computer storage medium | |
| CN115812209A (en) | Machine learning feature recommendation | |
| CN107958270A (en) | Classification recognition methods, device, electronic equipment and computer-readable recording medium | |
| CN115202847A (en) | Task scheduling method and device | |
| CN111310843A (en) | Mass streaming data clustering method and system based on K-means | |
| CN104077288B (en) | Web page contents recommend method and web page contents recommendation apparatus | |
| CN111160699A (en) | Expert recommendation method and system | |
| CN113362102A (en) | Client cable distribution method, system and storage medium | |
| CN112231299A (en) | Method and device for dynamically adjusting feature library | |
| CN116342137A (en) | Client data recycling allocation method, device, computer equipment and storage medium | |
| CN113568739B (en) | User resource quota allocation method and device and electronic equipment | |
| CN115238676A (en) | Method and device for identifying hot spots of bidding demands, storage medium and electronic equipment | |
| CN115114073A (en) | Alarm information processing method and device, storage medium and electronic equipment | |
| CN113269610A (en) | Bank product recommendation method and device and storage medium | |
| KR102078541B1 (en) | Issue interest based news value evaluation apparatus and method, storage media storing the same | |
| CN115968478A (en) | Machine learning feature recommendation | |
| CN113177613A (en) | System resource data distribution method and device |
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 |