CN110210721B - Remote sign language online translation customer service distribution method and device - Google Patents
Remote sign language online translation customer service distribution method and device Download PDFInfo
- Publication number
- CN110210721B CN110210721B CN201910397814.6A CN201910397814A CN110210721B CN 110210721 B CN110210721 B CN 110210721B CN 201910397814 A CN201910397814 A CN 201910397814A CN 110210721 B CN110210721 B CN 110210721B
- Authority
- CN
- China
- Prior art keywords
- customer service
- sign language
- service
- translation
- terminal
- 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.)
- Active
Links
- 238000013519 translation Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012216 screening Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 3
- 230000004927 fusion Effects 0.000 abstract 1
- 230000006854 communication Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 11
- 230000006872 improvement Effects 0.000 description 7
- 230000004044 response Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Machine Translation (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a remote sign language online translation customer service distribution method and a device, wherein the method comprises the following steps: s1, receiving a translation request signal sent by a user terminal, and acquiring request information comprising service scene types and geographic positions to be translated according to the received translation request signal; s2, the acquired request information is respectively matched with the customer service information of each sign language customer service terminal, the customer service information comprises geographic positions and sign language translation capability information when different service scene types are adopted, and the matched target sign language customer service terminal is found and distributed to the user terminal for sign language online translation. The intelligent sign language customer service distribution method based on the multi-information fusion can achieve the effect of achieving the intelligent and optimized distribution of sign language customer service by considering the locality, the scene type and the translation capability, and has the advantages of being simple in implementation method, high in distribution efficiency, good in effect and the like.
Description
Technical Field
The invention relates to the technical field of remote sign language online translation, in particular to an intelligent distribution method and device for remote sign language translation customer service.
Background
The remote sign language online translation is that a user calls sign language translation customer service through mobile equipment, and a sign language translation center or a mechanism distributes sign language translation customer service to conduct real-time translation, so that real-time sign language translation crossing a space position can be achieved.
Aiming at customer service distribution of remote sign language online translation, currently, a sign language translation center or a mechanism generally selects currently idle customer service at random, and if the selected customer service cannot accept a current translation task and is refused to accept, other idle customer service is selected again until the customer service accepts the translation task, and an audio-video connection is established between a user terminal and a customer service terminal receiving the task. The sign language has territory and the same expression, the sign language of each region is different in typing, the sign language of different regions is larger in difference, the spoken language is serious in the actual communication process, the efficiency of the customer service distribution mode is low, one task may even need to go through multiple distribution processes, the translation response is prolonged, the distributed customer service is likely to belong to different regions, the translation process is unsmooth, and the problem of regional difference of the sign language exists.
In order to solve the above problems, practitioners propose to divide the customer service area according to the customer service IP address, and select the allocated customer service according to the customer service IP address, so that the customer service in the same area can be preferentially allocated, but whether the sign language translation is smooth or not, the quality of the sign language translation is also dependent on various factors such as the matching degree of the customer service, the sign language translation level of the customer service, etc., for example, the sign language translation has various service scene types, such as daily communication, medical consultation, banking finance, relatives and friends communication, etc., different scene types require the customer service personnel to have the translation background knowledge in the corresponding professional fields, so that smooth and high-quality translation can be provided, and different customer service types are good at and bad at each time, if the customer service is selected according to the scheme of the IP address, the corresponding customer service cannot be selected according to the different scene types, the translation task is likely to be allocated to the customer service of the scene type, the translation quality is not good, and the best customer service of the situation type cannot be considered on the basis of the different scene types, and the best customer service is difficult to be matched to the region and translation capability is met.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the technical problems existing in the prior art, the invention provides the intelligent remote sign language translation customer service distribution method and device which are simple in implementation method, high in distribution efficiency and good in effect, and can give consideration to territory, scene type and translation capability, and intelligent and optimized distribution of sign language customer service can be realized by fusing multiple information.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a remote sign language online translation customer service distribution method comprises the following steps:
s1, receiving a translation request signal sent by a user terminal, and acquiring request information comprising a service scene type and a geographic position to be translated according to the received translation request signal;
s2, the acquired request information is respectively matched with the customer service information of each sign language customer service terminal, the customer service information comprises geographic positions and sign language translation capability information in different service scene types, and a matched target sign language customer service terminal is found and distributed to the user terminal for sign language online translation.
In the step S2, the corresponding sign language service terminals are screened according to the service scene type in the request information, and then the acquired request information is matched with the service information of the screened sign language service terminals respectively, so as to find out matched target sign language service terminals.
As a further improvement of the present invention, the step of step S2 includes:
s21, constructing a customer service pool: a plurality of customer service pools corresponding to different service scene types are built in advance, and information of a plurality of sign language customer service terminals with sign language translation capability meeting the required requirements under the corresponding service scene types is stored in each customer service pool;
s22, screening a customer service pool: screening the matched customer service pools according to the service scene types in the request information;
s23, customer service matching: and respectively matching the request information with each sign language customer service terminal in the screened customer service pool, and searching out a matched target sign language customer service terminal to be distributed to a user terminal.
As a further improvement of the present invention, when the customer service pool is constructed in step S21, all sign language customer service terminals are ranked according to sign language translation capability under the corresponding service scene type, and a plurality of sign language customer service terminals with specified number and/or sign language translation capability values within a preset range after the ranking are selected to form the customer service pool.
As a further improvement of the present invention, in the step S22, the customer service pool with the same service scene type as the request information is preferentially selected, and if no free customer service exists in the selected customer service pool, other customer service pools are selected according to the correlation values among different service scene types.
As a further improvement of the present invention, the step of step S23 includes: and respectively calculating one or more of a geographic position matching value, a sign language capability matching value, a call history factor and a customer service quality factor between the request information and each sign language customer service terminal in the customer service pool, weighting to obtain a final matching value, determining a matched target sign language customer service terminal according to the size of the final matching value, wherein the geographic position matching value is obtained according to the matching degree between the geographic position in the request information and the geographic position of the sign language customer service terminal, the sign language capability matching value is obtained according to the sign language standardization degree and/or the sign language level grade of the sign language customer service terminal, the call history factor is obtained according to the interval time between two adjacent times of calling of the sign language customer service terminal, and the customer service quality factor is obtained according to the score of a user on the sign language customer service terminal.
As a further improvement of the present invention, each time the service is completed, an updating step is further included, the updating step including: the scores of the users and the sign language customer service terminals are obtained, the obtained scores of the users are used for updating the customer service information and each customer service pool of the corresponding sign language customer service terminals, and the weight of each weighting factor during weighting is updated; the weight updating value of each weighting factor is specifically determined according to the obtained user score and the calculated final matching value.
As a further improvement of the invention, if the currently selected customer service pool is a nearby customer service pool corresponding to the service scene type related to the target service scene type in the request information, the correlation value between the target service scene type and the selected related service scene type is updated by using the score of the sign language customer service terminal after each service is completed.
As a further improvement of the present invention, the step S2 includes: and respectively calculating one or more of a geographic position matching value, a sign language capability matching value, a call history factor and a customer service quality factor between the request information and each sign language customer service terminal, weighting to obtain a final matching value, determining a matched target sign language customer service terminal according to the size of the final matching value, wherein the geographic position matching value is obtained according to the matching degree between the geographic position in the request information and the geographic position of the sign language customer service terminal, the sign language capability matching value is obtained according to the sign language standardization degree of a user and the sign language level grade of the sign language customer service terminal, the call history factor is obtained according to the interval time between two adjacent called times of the sign language customer service terminal, and the customer service quality factor is obtained according to the score of the user on the sign language customer service terminal.
A remote sign language online translation customer service distribution device, comprising a computer readable storage medium storing a computer program, wherein the computer program when executed implements a method as described above.
Compared with the prior art, the invention has the advantages that:
1. according to the remote sign language online translation customer service distribution method and device, when the translation request signal sent by the user terminal is received, request information such as service scene type, geographic position and the like in the request signal is obtained, the request information is comprehensively matched with various customer service information such as geographic position of each customer service terminal and sign language translation capability and the like in different service scene types, regional, scene type and translation capability can be considered, and intelligent and optimal distribution of sign language customer service can be realized by fusing the various information such as region, service scene type and translation capability, so that reasonable and effective distribution of customer service can be effectively improved, translation quality is improved, distribution efficiency is ensured, and online translation response delay is reduced.
2. According to the remote sign language online translation customer service distribution method and device, the searching range is rapidly located by initial screening according to the service scene type, and then accurate matching is performed according to the geographic position, the translation capacity and other information in the request information, so that the matching time can be effectively shortened, the matching performance is ensured, the optimal sign language customer service terminal meeting the requirements can be rapidly found, and the service quality is improved.
3. According to the remote sign language online translation customer service distribution method and device, the corresponding customer service pools are further constructed according to different service scene types, sign language customer service terminals with translation capacity meeting requirements under different service scene types are divided into the customer service pools in advance, the corresponding sign language customer service terminals are further screened out from the customer service pools after being positioned to the corresponding customer service pools according to the requested service scene types, customer service distribution efficiency can be further improved, and the best sign language customer service terminals meeting requirements can be distributed to user terminals as quickly as possible.
4. According to the remote sign language online translation customer service distribution method and device, when the matching range is determined, customer service pools with the same service scene type are preferentially selected, if no free customer service exists, other customer service pools are selected according to the correlation among the service scene types, the problem of insufficient customer service of a specific sign language caused by frequent calling of a common type or the call peak period can be avoided, and meanwhile, customer service with large translation background correlation can be distributed as much as possible.
5. According to the remote sign language online translation customer service distribution method and device, the factors such as the geographic position, the sign language level, the historical call and the quality are fully considered, and the optimal sign language customer service terminal meeting the requirements can be obtained by fusing the multiple information such as the geographic position, the sign language level, the historical call and the quality and distributed to the user terminal, so that the optimal sign language customer service distribution is realized.
6. The remote sign language online translation customer service distribution method and device further update customer service information of the user and the sign language customer service terminal, each customer service pool and weight of each weighting factor in weighting by using scores of the user and the sign language customer service terminal after each service is completed, the distribution can be updated and optimized continuously by each service state, and if the selected customer service pool is a nearby customer service pool of a related service scene type, the scores of the sign language customer service terminal are used for updating correlations among the scene types, and the correlations among different scene types can be updated by feedback of real-time service, so that distribution performance is optimized continuously.
Drawings
Fig. 1 is a schematic diagram of an implementation flow of the remote sign language online translation customer service allocation method in this embodiment.
Fig. 2 is a schematic flow chart of an implementation of remote sign language online translation customer service allocation in a specific application embodiment of the present invention.
Detailed Description
The invention is further described below in connection with the drawings and the specific preferred embodiments, but the scope of protection of the invention is not limited thereby.
Example 1:
as shown in fig. 1, the method for distributing online translation customer service of remote sign language in this embodiment includes the following steps:
s1, receiving a translation request signal sent by a user terminal, and acquiring request information comprising service scene types and geographic positions to be translated according to the received translation request signal;
s2, the acquired request information is respectively matched with the customer service information of each sign language customer service terminal, the customer service information comprises geographic positions and sign language translation capability information when different service scene types are adopted, and the matched target sign language customer service terminal is found and distributed to the user terminal for sign language online translation.
According to the method and the device, when the translation request signal sent by the user terminal is received, request information such as service scene type and geographic position in the request signal is obtained, comprehensive matching is carried out on the request information and various customer service information such as geographic position of each customer service terminal and sign language translation capability in different service scene types, regional, scene type and translation capability can be considered, and intelligent and optimal distribution of sign language customer service can be realized by fusing the multiple information such as regional, service scene type and translation capability, so that reasonable and effective distribution of customer service can be effectively improved, translation quality is improved, distribution efficiency is ensured, and online translation response delay is reduced.
In step S2 of this embodiment, each sign language customer service terminal according to the service scene type in the request information is screened out, and then the acquired request information is respectively matched with the customer service information of each screened sign language customer service terminal, so as to find out the matched target sign language customer service terminal. According to the embodiment, the initial screening is performed according to the service scene type, the searching range is rapidly located, and then the accurate matching is performed according to the geographic position, the translation capability and other information in the request information, so that the matching time can be effectively shortened, the matching performance is ensured, the optimal sign language customer service terminal meeting the requirements can be rapidly found, and the service quality is improved.
In this embodiment, the step of step S2 includes:
s21, constructing a customer service pool: a plurality of customer service pools corresponding to different service scene types are built in advance, and information of a plurality of sign language customer service terminals with sign language translation capability meeting the required requirements under the corresponding service scene types is stored in each customer service pool;
s22, screening a customer service pool: screening out matched customer service pools according to service scene types in the request information;
s23, customer service matching: and respectively matching the request information with each sign language customer service terminal in the screened customer service pool, and searching out a matched target sign language customer service terminal to be distributed to the user terminal.
According to the embodiment, the corresponding customer service pools are constructed according to different service scene types, the sign language customer service terminals with the translation capability meeting the requirements under different service scene types are divided into the customer service pools in advance, after the request signals sent by the user terminals are received, the corresponding customer service pools are positioned according to the requested service scene types, the sign language customer service terminals meeting the requirements are further screened out from the customer service pools, so that customer service distribution efficiency can be further improved, and the sign language customer service terminals meeting the requirements can be distributed to the user terminals as quickly as possible.
In this embodiment, when the customer service pool is constructed in step S21, all sign language customer service terminals are ordered according to sign language translation capability under the corresponding service scene type, and a plurality of sign language customer service terminals with assigned numbers or sign language translation capability values within a preset range after the ordering are selected to form the customer service pool.
In this embodiment, in step S22, a service pool with the same service scene type as the service scene type in the request information is preferentially selected, and if no idle service exists in the selected service pool, other service pools are selected according to the correlation between different service scene types. If the correlation between the two types is larger, the customer service of one type can usually meet the translation requirement of the other type, for example, the correlation between the daily communication type and the friendly communication type is larger, and under the condition that the customer service pool corresponding to the daily communication type does not have idle customer service, the customer service pool corresponding to the friendly communication type can also be selected to meet the translation requirement. The number of calls of a certain service scene type may be more than that of other types, or in a certain call peak period, there may be no idle sign language customer service terminals in a customer service pool of a certain service scene type.
In this embodiment, a correlation value R between different service scene types is calculated first, when a user request is received, no idle service exists in a service pool corresponding to the service scene type requested by the user, then a neighboring service pool with the largest correlation value with the service scene type is selected, if no idle service exists in the neighboring service pool, then other neighboring service pools are sequentially selected according to the correlation value, until a service pool with idle service is found.
In this embodiment, the step of step S23 includes: the method comprises the steps of respectively calculating geographic position matching values, sign language capability matching values, call history factors, customer service quality factors and the like between request information and each sign language customer service terminal in a customer service pool, weighting the geographic position matching values, the sign language capability matching values, the call history factors and the customer service quality factors and the like to obtain final matching values, determining matched target sign language customer service terminals according to the size of the final matching values, obtaining the geographic position matching values according to the matching degree between the geographic position in the request information and the geographic position of the sign language customer service terminals so as to represent the geographic position matching degree, obtaining the sign language capability matching values according to the sign language standardization degree of a user and the sign language level grade of the sign language customer service terminals so as to represent the sign language capability matching degree, obtaining call history factors according to the interval time between two adjacent times of the sign language customer service terminals so as to represent the history call influence degree, obtaining the customer service quality factors according to the score of the user on the sign language customer service terminals so as to represent the service quality, and fully considering the geographic position, the sign language level, the history call and the quality factors and the like, and matching the best sign language customer service terminals meeting requirements to be distributed to the user terminals.
In a specific application embodiment, each of the matching values, the factor value, is first calculated:
geographic position matching value V loc Specifically, the method can be determined according to the following formula:
i.e. when the two geographical locations are coincident, thenOtherwise 0 +.>The weight corresponding to the geographic position matching value can be set according to actual requirements.
The sign language capability matching degree is related to the sign language standardization degree and the sign language level, and in this embodiment, the sign language capability matching value is determined by the sign language standardization degree of the user and the sign language level of the customer service together, and the sign language capability matching value can be specifically expressed as follows: and calculating a sign language level grade value of the sign language standardization degree, wherein the beta is a weight corresponding to the sign language capability matching value.
If the same customer service is called again after completing one translation task, the matching degree of the customer service is higher, the shorter the interval between two calls is, the higher the corresponding matching degree is, the influence of the history call on the matching degree is fully considered, the influence of the history call time is considered, and the attenuation function based on the interval time between the two calls is used for determining the call history factor. In a specific application embodiment, if the previous call is the customer service, record according to formula (2):
wherein t is the interval time between two adjacent calls, if no customer service is called last time, the record is 0, and epsilon is the weight corresponding to the call history factor.
The customer service quality factor can be specifically calculated according to a formula q=γ, where γ is a weight corresponding to the customer service quality factor.
The final match value Score is then calculated as follows (3):
score=geographical location matching value+sign language ability matching value+call history factor+customer service quality factor (3)
And sorting the customer services in the customer service pool list according to the size of the final matching value Score, and distributing the customer service with the highest sorting to the user terminal to finish distribution.
The weighting factors can be determined specifically according to actual demands, and other weighting factors can be added to fuse more information to realize distribution.
In this embodiment, after each service is completed, the method further includes an updating step, where the updating step includes: and obtaining scores of the users and the sign language customer service terminals, updating customer service information of the corresponding sign language customer service terminals by using the obtained scores of the users, updating each customer service pool again, and updating weights of each weighting factor when weighting is performed, so that allocation can be updated and optimized continuously according to actual service quality conditions each time. Specifically, after each service is completed, a service score FB1 of the user for the service, a smoothness score FB2 of the sign language customer service for the translation, and a sign language standardization score FB3 of the user are obtained, user score and customer service quality information of the corresponding sign language customer service terminal are updated by using the service score FB1, sign language translation capability value of the corresponding sign language customer service terminal under the current service scene type is updated by using the score FB2, sign language standardization degree of the user is updated by using the score FB3, so that information of the user and the sign language customer service terminal can be updated continuously, and the updating can be specifically realized by adding the latest score value and then taking an average value.
In the updating step of the embodiment, the weight updating value of each weighting factor is determined according to the obtained user score and the final matching value obtained by calculation, and the weight of each piece of weighting information can be adaptively adjusted according to the actual quality of service state of each time, so that the matching performance is continuously optimized.
In a specific application embodiment, the updating of the weight parameters is performed according to the following formula:
B＝Β+α(Socre 2 –FB1*FB2) (5)
ε＝ε+α(Socre 2 –FB2 2 ) (6)
where α is the update factor.
In this embodiment, if the selected customer service pool is a neighboring customer service pool of a relevant service scene type, the method further includes a step of updating a correlation value between scene types by using a sign language customer service terminal to score FB2 for smoothness of the translation after each service is completed, and the correlation between different scene types can be updated by feedback of real-time service.
The update formula of the correlation value R is specifically:
R＝R+0.001(FB2-n) (7)
wherein n is a preset median value, which can be set according to actual requirements, and is preferably 4.
As shown in fig. 2, in a specific application embodiment of the present invention, a detailed flow for implementing online translation customer service allocation of remote sign language by using the method is as follows:
step 1: customer service pool division
Each sign language translation is provided for different sign language translation fields according to service scene typesDifferent scene sign language translation capability values V are set scene As shown in table 1.
Table 1: sign language translator different scene ability value statistics.
And selecting a designated number of sign language customer services according to the capability value of each sign language translation to form a customer service pool, and arranging according to the size of the capability value to form a customer service pool list, as shown in table 2.
Table 2: a customer service pool list.
Considering the situation that no idle sign language customer service exists when a corresponding customer service pool is called, calculating correlation parameters among different service scene types, wherein the calculated correlation value table is shown in table 3, so that when no idle sign language customer service exists in the customer service pool, sign language translators conforming to the adjacent customer service pool can be searched in sequence.
Table 3: correlation values for different service scenario types.
| Scene: | daily communication | Medical inquiry | Banking finance | Government police | Communication between relatives and friends | Other content |
| Daily communication | 1 | 0.76 | 0.84 | 0.85 | 0.92 | 0.86 |
| Medical inquiry | 0.76 | 1 | 0.52 | 0.62 | 0.53 | 0.42 |
| Banking finance | 0.84 | 0.52 | 1 | 0.71 | 0.56 | 0.57 |
| Government police | 0.85 | 0.62 | 0.71 | 1 | 0.67 | 0.67 |
| Communication between relatives and friends | 0.92 | 0.53 | 0.56 | 0.67 | 1 | 0.83 |
| Other content | 0.86 | 0.42 | 0.57 | 0.67 | 0.83 | 1 |
Step 2: service scenario type acquisition for a user
After the user terminal initiates a call request to the server, the server sends a scene list to the user terminal, such as communication with the corresponding relatives and friends, banking finance, medical consultation, government departments and the like, and the user clicks the corresponding service scene type according to the translation content of the user terminal to obtain the service scene type clicked by the user.
Step 3: customer service allocation based on customer service pool
Step 3.1: after the service scene type selected by the user is obtained, firstly inquiring a customer service pool corresponding to the service scene type selected by the user, judging whether the customer service pool has free customer service, if so, executing the step 3.2, otherwise, executing the step 3.3;
step 3.2: extracting a free customer service list from the current customer service pool for customer service distribution;
step 3.3: and selecting an adjacent customer service pool with a higher correlation value according to the correlation values among different service scene types, and extracting an idle customer service list from the adjacent customer service pool to perform customer service distribution.
When customer service distribution is carried out, the detailed steps are as follows:
the request information of the user and the customer service information of each sign language customer service terminal in the currently selected customer service pool are obtained, the request information table of a certain user is shown in table 4, and the customer service information table of a certain sign language customer service terminal is shown in table 5.
Table 4: a request information table of the user.
Table 5: customer service information list of sign language customer service terminal.
Respectively calculating each matching value between the user and the sign language customer service terminal:
geographic location matching value:
if the two geographic locations are consistent, the formula is +>Otherwise, 0;
sign language ability match value = beta-sign language normalization degree × sign language level;
if the last call is the customer service call history factorIf the customer service is not called last time, recording as 0;
customer service quality factor q=γ user score;
final match value Score = geographic location match value + sign language ability match value + call history factor + customer service quality factor
And sorting the customer services in the customer service pool list according to the Score, and distributing the customer service with the highest sorting.
Step 4: updating
Step 4.1: parameter update
After the service is finished, a score FB1 of the service, a score FB2 of the sign language customer service terminal for the smoothness of the translation, a score FB3 of the sign language standardization degree of the user are obtained, the average value is taken after the user score corresponding to the sign language customer service terminal is added with the latest feedback value FB1, the average value is taken after the user sign language standardization degree parameter is added with the latest feedback value FB3, the translation capacity value of the corresponding sign language customer service terminal under the current service scene type is added with the latest feedback value FB2, and the average value is taken for updating.
Step 4.2: weight update
And respectively updating the weight parameters of the geographic position matching value, the sign language capability matching value, the call history factor and the customer service quality factor by using the FB 1:
B＝Β+α(Socre 2 –FB1*FB2)
ε＝ε+α(Socre 2 –FB2 2 )
step 4.3: correlation parameter update
If the current customer service pool is a selected adjacent customer service pool, updating the correlation parameters again:
R＝R+0.001(FB2-4)
step 4.4: customer service pool update
And re-updating the customer service list in the customer service pool according to the updated capability value of the sign language customer service terminal under the service scene type.
The remote sign language online translation customer service distribution device of the embodiment comprises a computer readable storage medium storing a computer program, and the computer program realizes the method when being executed.
Example 2:
the difference from embodiment 1 is that the step S2 of this embodiment is as follows: and respectively calculating one or more of geographic position matching values, sign language capability matching values, call history factors and customer service quality factors between the request information and each sign language customer service terminal, weighting to obtain a final matching value, determining a matched target sign language customer service terminal according to the size of the final matching value, obtaining the geographic position matching value according to the matching degree between the geographic position in the request information and the geographic position of the sign language customer service terminal, obtaining the sign language capability matching value according to the sign language standardization degree of a user and the sign language level grade of the sign language customer service terminal, obtaining the call history factors according to the interval time between two adjacent times of calling of the sign language customer service terminal, and obtaining the customer service quality factors according to the grading of the user to the sign language customer service terminal. The embodiment directly calculates the matching value of each customer service terminal by using the weighted values of the factors such as the geographic position, the sign language level, the historical call and the quality, and the weighted implementation principle is basically the same as that of the embodiment 1, so that the implementation is simpler, the distribution can be realized by fusing multiple information such as the geographic position, the sign language level, the historical call and the quality, and the like, and the method can be suitable for scenes with loose requirements on real-time property and distribution efficiency.
The foregoing is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. While the invention has been described with reference to preferred embodiments, it is not intended to be limiting. Therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention shall fall within the scope of the technical solution of the present invention.
Claims (5)
1. The remote sign language online translation customer service distribution method is characterized by comprising the following steps:
s1, receiving a translation request signal sent by a user terminal, and acquiring request information comprising a service scene type and a geographic position to be translated according to the received translation request signal;
s2, matching the acquired request information with customer service information of each sign language customer service terminal respectively, wherein the customer service information comprises geographic positions and sign language translation capability information in different service scene types, and finding out a matched target sign language customer service terminal and distributing the matched target sign language customer service terminal to a user terminal for sign language online translation;
in the step S2, firstly, according to the service scene type in the request information, selecting the corresponding sign language customer service terminals, then, respectively matching the acquired request information with the customer service information of the selected sign language customer service terminals, and searching for a matched target sign language customer service terminal;
the step S2 includes:
s21, constructing a customer service pool: a plurality of customer service pools corresponding to different service scene types are built in advance, and information of a plurality of sign language customer service terminals with sign language translation capability meeting the required requirements under the corresponding service scene types is stored in each customer service pool;
s22, screening a customer service pool: screening out the matched customer service pools according to the service scene types in the request information, preferentially selecting the customer service pools with the same service scene types as the service scene types in the request information, and sequentially selecting other adjacent customer service pools according to the correlation values among different service scene types if no free customer service exists in the selected customer service pools;
s23, customer service matching: matching the request information with each sign language customer service terminal in the screened customer service pool respectively, and finding out a matched target sign language customer service terminal to be distributed to a user terminal;
the step S23 includes: the geographic position matching value, the sign language capability matching value, the call history factor and the customer service quality factor between the request information and each sign language customer service terminal in the customer service pool are calculated respectively, a final matching value is obtained after weighting, a matched target sign language customer service terminal is determined according to the size of the final matching value, the geographic position matching value is obtained according to the matching degree between the geographic position in the request information and the geographic position of the sign language customer service terminal, the sign language capability matching value is obtained according to the sign language standardization degree and/or the sign language level grade of the sign language customer service terminal, the call history factor is obtained according to the interval time between two adjacent times of calling of the sign language customer service terminal, and the customer service quality factor is obtained according to the score of a user on the sign language customer service terminal.
2. The method for distributing remote sign language online translation customer service according to claim 1, wherein when the customer service pool is constructed in step S21, all sign language customer service terminals are ordered according to sign language translation capability under the corresponding service scene type, and a plurality of sign language customer service terminals with assigned quantity/sign language translation capability values within a preset range after the ordering are selected to form the customer service pool.
3. The remote sign language online translation customer service distribution method according to claim 1, further comprising an updating step after each service is completed, wherein the updating step comprises: the scores of the users and the sign language customer service terminals are obtained, the obtained scores of the users are used for updating the customer service information and each customer service pool of the corresponding sign language customer service terminals, and the weight of each weighting factor during weighting is updated; the weight updating value of each weighting factor is specifically determined according to the obtained user score and the calculated final matching value.
4. The remote sign language online translation customer service distribution method according to claim 3, wherein the updating step further comprises: if the currently selected customer service pool is a nearby customer service pool corresponding to the service scene type related to the target service scene type in the request information, updating a correlation value between the target service scene type and the selected related service scene type by using the score of the sign language customer service terminal after each service is completed.
5. A remote sign language online translation customer service distribution device comprising a computer readable storage medium storing a computer program, wherein the computer program when executed implements the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910397814.6A CN110210721B (en) | 2019-05-14 | 2019-05-14 | Remote sign language online translation customer service distribution method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910397814.6A CN110210721B (en) | 2019-05-14 | 2019-05-14 | Remote sign language online translation customer service distribution method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110210721A CN110210721A (en) | 2019-09-06 |
| CN110210721B true CN110210721B (en) | 2023-11-21 |
Family
ID=67787193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910397814.6A Active CN110210721B (en) | 2019-05-14 | 2019-05-14 | Remote sign language online translation customer service distribution method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210721B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112256827A (en) * | 2020-10-20 | 2021-01-22 | 平安科技（深圳）有限公司 | Sign language translation method and device, computer equipment and storage medium |
| CN112866494B (en) * | 2020-12-16 | 2023-01-24 | 华人运通(上海)云计算科技有限公司 | Intelligent customer service cooperation system and method for vehicle |
| CN112581008A (en) * | 2020-12-25 | 2021-03-30 | 上海高顿教育科技有限公司 | Enterprise-level question-answering automatic distribution system based on shift-scheduling weighting |
| CN112668464B (en) * | 2020-12-25 | 2022-12-02 | 株洲手之声信息科技有限公司 | Chinese sign language translation model construction method and device fusing scene matching |
| CN113158694B (en) * | 2021-04-23 | 2023-01-13 | 深圳鸿祥源科技有限公司 | Online translation terminal system based on 5G network and method thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004282134A (en) * | 2003-03-12 | 2004-10-07 | Seiko Epson Corp | Sign language translation system and sign language translation program |
| CN101742004A (en) * | 2009-12-23 | 2010-06-16 | 中兴通讯股份有限公司 | Call transfer method and device in multi-call central system |
| CN102609409A (en) * | 2012-02-13 | 2012-07-25 | 浙江飞常哆科技有限公司 | Online translation method, device, system and server |
| CN104539814A (en) * | 2014-11-26 | 2015-04-22 | 小米科技有限责任公司 | Customer service call forwarding method and device |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN107231374A (en) * | 2017-07-08 | 2017-10-03 | 长沙手之声信息科技有限公司 | Deaf person's remote chat method based on online sign language interpreter |
| CN107562738A (en) * | 2017-09-08 | 2018-01-09 | 合肥安华信息科技有限公司 | A kind of sign language interpretation method based on user's request |
| KR20180013820A (en) * | 2017-08-07 | 2018-02-07 | (주)씨제이텔레닉스 | System and method for analyzing customer type using speech analysis |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100332281A1 (en) * | 2009-06-26 | 2010-12-30 | Microsoft Corporation | Task allocation mechanisms and markets for acquiring and harnessing sets of human and computational resources for sensing, effecting, and problem solving |
-
2019
- 2019-05-14 CN CN201910397814.6A patent/CN110210721B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004282134A (en) * | 2003-03-12 | 2004-10-07 | Seiko Epson Corp | Sign language translation system and sign language translation program |
| CN101742004A (en) * | 2009-12-23 | 2010-06-16 | 中兴通讯股份有限公司 | Call transfer method and device in multi-call central system |
| CN102609409A (en) * | 2012-02-13 | 2012-07-25 | 浙江飞常哆科技有限公司 | Online translation method, device, system and server |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN104539814A (en) * | 2014-11-26 | 2015-04-22 | 小米科技有限责任公司 | Customer service call forwarding method and device |
| CN107231374A (en) * | 2017-07-08 | 2017-10-03 | 长沙手之声信息科技有限公司 | Deaf person's remote chat method based on online sign language interpreter |
| KR20180013820A (en) * | 2017-08-07 | 2018-02-07 | (주)씨제이텔레닉스 | System and method for analyzing customer type using speech analysis |
| CN107562738A (en) * | 2017-09-08 | 2018-01-09 | 合肥安华信息科技有限公司 | A kind of sign language interpretation method based on user's request |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110210721A (en) | 2019-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210721B (en) | Remote sign language online translation customer service distribution method and device | |
| CN105898823B (en) | It realizes the method for communication connection and matches card server-side | |
| CN110996116B (en) | Anchor information pushing method and device, computer equipment and storage medium | |
| CN105656876A (en) | Live video play method, device and system | |
| US8792631B2 (en) | System and method for matching service representatives with customers | |
| US9374462B2 (en) | Method and system for providing phone directory service for mobile communication subscriber | |
| CN101243704B (en) | Closest user terminal search method for a telecommunication network and service node applying such a method | |
| US20060023863A1 (en) | Method and system for mapping caller information to call center agent transactions | |
| JP2018500682A (en) | Seat information providing method and device | |
| US9003046B2 (en) | Network access method, terminal device, server, and communication system | |
| US8971313B2 (en) | Method, apparatus and system for updating location information of an IP address | |
| CN106658096A (en) | Method and device for pushing live program | |
| CN110086886B (en) | Dynamic session holding method and device | |
| CN1337129A (en) | System and method for providing targeted messages on wireless mobile location | |
| CN112328760B (en) | Service providing method, device and system | |
| CN106130972A (en) | Resource access control method and device | |
| CN113778286B (en) | Application control display method and device, storage medium and electronic equipment | |
| DE102010013575A1 (en) | Dynamic IVR dialog based on analytics data | |
| CN108848455A (en) | Acquisition methods, device, equipment and the computer readable storage medium of available network | |
| US11546821B2 (en) | Methods and systems for selecting a gateway node to support handover in a wireless communication network | |
| CN110241553A (en) | Reservation control method and device for laundry equipment, storage medium and server | |
| CN108038001B (en) | Junk file cleaning strategy generation method and device and server | |
| CN110490411A (en) | A kind of client management method, system and storage medium | |
| CN110213450B (en) | Multi-center-based sign language online customer service distribution management method, device and system | |
| CN106533816B (en) | A kind of method and device of adjustment DNS configuration |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231023 Address after: Zhuzhou Yandi University, 229 Shaoshan Road, Tianyuan District, Zhuzhou City, Hunan Province, 412007 Applicant after: Zhuzhou shouzhisheng Information Technology Co.,Ltd. Address before: Yandi University, 229 Shaoshan Road, Tianyuan District, Zhuzhou City, Hunan Province, 412007 Applicant before: CHANGSHA SHOUZHISHENG INFORMATION TECHNOLOGY CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |