CN110866698A

CN110866698A - Device for assessing service score of service provider

Info

Publication number: CN110866698A
Application number: CN201911132574.3A
Authority: CN
Inventors: 黄建杰
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Priority date: 2019-11-14
Filing date: 2019-11-14
Publication date: 2020-03-06

Abstract

The present disclosure discloses an apparatus for assessing a service score of a service provider, comprising: a service score calculating component and a service score outputting component; a service score calculation component configured to calculate a service score for a service provider based on a dynamic scoring of the service provider's services and at least one of: a commitment score of a service provider and a service adaptation score of the service provider; the service dynamic score of the service provider is determined based on the original score of the service index of the service provider; the commitment score of the service provider is determined based on whether the service provider opens a service commitment; the service adaptation score of the service provider is determined based on adaptation data of the service provider to the service and the operation indexes of the platform; a service score output component configured to output a service score for the service provider. The service score of the service provider can be determined based on the service index score, the commitment score and the service adaptation score, and comprehensiveness and accuracy of the service score are improved.

Description

Device for assessing service score of service provider

Technical Field

The present disclosure relates to the field of computer technology, and more particularly to the field of computer network technology, and more particularly to an apparatus for assessing a service score of a service provider.

Background

The store service score is a very important index for measuring the good and bad operation of a merchant store, and mainly reflects the service level provided by the merchant for a customer, namely a method for supervising the merchant by a platform and a means for screening the merchant by the customer.

In the related art, the wind vane model is a set of model system for calculating the service level of a merchant, and comprehensively considers the service level provided by the merchant before, during and after sale. For the platform, the wind vane model is an important tool for supervising and urging the service level of merchants to be improved, and merchants with excellent service have more development space and obtain more flow and resources by butting a search ranking and activity reporting system. Whether the wind vane score is accurate or not is a precondition of service supervision, and the wind vane score is a key index of service value proposition.

Currently, obtaining a wind vane score is mainly obtained through the following steps:

first, raw data is acquired.

The wind vane model firstly carries out data summarization according to a merchant id (hereinafter, referred to as a sender _ id), and analyzes service related indexes of the merchant by a big data method: the system comprises 5 evaluation indexes and 7 monitoring indexes, wherein the evaluation indexes comprise commodity quality satisfaction, commodity description satisfaction, logistics speed satisfaction, service attitude satisfaction and refund satisfaction, and the service monitoring indexes comprise after-sale processing time, a customer service question-answering system 30s response rate, a customer service question-answering system average response time, a 48-hour piece collecting and timely rate, an alternate day reaching rate, a transaction dispute rate and a refund repair rate.

And secondly, acquiring the scores of the single indexes.

After the original data are obtained, the wind vane model processes each data index so as to eliminate the difference of the indexes. Monitoring evaluation data for 180 days for 5 evaluation indexes, corresponding 1-5 star evaluation to each 1-5 star, recording n evaluations corresponding to a certain vender _ id, and recording each evaluation as X_t，t∈[1,n]Each evaluation class index score is calculated as follows:

monitoring 30-day merchant operation data for 7 service monitoring indexes, and recording the original value of the monitoring index as X₀The industry average level is u, the industry index variance is σ, and the score of each monitoring index is calculated as follows:

X＝9.55+(X₀-u)/σ

record the 12 index scores as Y₁～Y₁₂And proceeds to the next stage.

And thirdly, determining the wind vane score.

The business side of the wind vane model respectively configures weights for 12 indexes, and the weights are recorded as w₁～w₁₂The sum of the index weights is 1, and the weighted average score is calculated

Y＝w₁Y₁+w₂Y₂+w₃Y₃+···+w₁₂Y₁₂

And then carrying out sigmoid transformation, adjusting the distribution condition of the merchant scores, and when Y is more than 8.55, standardizing Y and recording as Yr having

Z＝9.55+1.4×(S-0.5)

Then, a DSR score Q is obtained:

finally, obtaining a wind vane score:

FXB＝Q×(1+θ)

where θ is the accelerator coefficient, and the value of the accelerator is given by the business rules.

Disclosure of Invention

Embodiments of the present disclosure provide an apparatus for assessing a service score of a service provider.

In a first aspect, embodiments of the present disclosure provide an apparatus for assessing a service score of a service provider, comprising: a service score calculating component and a service score outputting component; a service score calculation component configured to calculate a service score for a service provider based on a dynamic scoring of the service provider's services and at least one of: a commitment score of a service provider and a service adaptation score of the service provider; the service dynamic score of the service provider is determined based on the original score of the service index of the service provider; the commitment score of the service provider is determined based on whether the service provider opens a service commitment; the service adaptation score of the service provider is determined based on adaptation data of the service provider to the service and the operation indexes of the platform; a service score output component configured to output a service score for the service provider.

In some embodiments, the service dynamic score of a service provider is determined based on the raw score of the service provider's service metrics via the following functional layers: an input layer configured to obtain a raw score of a service index of a service provider; an index scoring layer configured to determine a single index score for a service provider based on a raw score of a service index for the service provider; the comprehensive index layer is configured to determine the substantive factor score of the service provider by adopting a dimension reduction analysis method based on the single index score of the service provider; an output layer configured to determine a service dynamic score for the service provider based on the substantive factor score for the service provider.

In some embodiments, the metric score layer comprises: the comparison index screening unit is configured to screen comparison indexes of various industry categories from service indexes of a service provider; the sample level correcting unit is configured to correct the original score of the comparison index of the service provider based on the blank sample level of the comparison index of the industry category to which the service provider belongs to obtain the corrected score of the comparison index of the service provider; the index ranking rate conversion unit is configured to calculate the ranking rate of the comparative indexes of the service provider in the industry category after removing extreme values based on the corrected values of the comparative indexes of the service provider; a score distribution projection unit configured to project the ranking rate of the service provider at the comparison index of the industry category to which the service provider belongs as a score distribution conforming to the original distribution; and the score distribution correcting unit is configured to correct the score distribution which accords with the original distribution based on a preset score boundary, and complement the corrected score of the removed comparative index of the service provider to obtain the single index score of the service provider.

In some embodiments, the sample level correction unit is further configured to: eliminating extreme values in the original scores of the comparative indexes of various industry categories; and marking the median of the original scores of the comparative indexes of all the industry categories after the extreme values are removed as blank sample levels of the comparative indexes of all the industry categories.

In some embodiments, the sample level correction unit is further configured to: and correcting the original score of the comparative index of the service provider by adopting the following formula to obtain a corrected score X1 of the comparative index of the service provider:

wherein, X₀Original score, n, being a comparative indicator of the service provider₀The number of samples used for the comparison index of the service provider, P is the blank sample level of the industry category to which the service provider belongs, m_cA fill sample size that is the original score of the comparative index of the correction service provider;

in some embodiments, the index ranking ratio conversion unit is further configured to: determining a ranking of the service provider's comparison indicators in the industry category to which the service provider belongs based on the following constraints: if the correction score of the comparison index is higher, the ranking of the comparison index is lower; when the correction scores of a plurality of service providers are the same, the ranking of the comparison index of the service provider with larger number of samples is smaller; ranking of the comparison indexes of the plurality of service providers with the same corrected score and the same sample number in parallel, wherein the ranking of the parallel comparison indexes is as follows: the minimum value of the rank of the selectable comparison indicator corresponding to the revised score.

In some embodiments, the index ranking ratio conversion unit is further configured to: calculating the ranking rate X2 of the comparative indexes of the service provider in the industry category by adopting the following formula:

wherein the content of the first and second substances,

the ranking rate X of the comparative indexes is directly assigned according to the definition of the comparative indexes when the original score of the comparative indexes of the service provider is the eliminated extreme value₂Is 0 or 1.

In some embodiments, the score distribution projection unit is further configured to: projecting the ranking rate of the service provider's comparison index in the industry category as a bell-shaped distribution curve-logic curve inverse function X3:

wherein 0.7 is a density adjustment coefficient, X₃The following constraints are satisfied: x1 is X of service provider of extreme value₃Is NULL.

In some embodiments, the score distribution correction unit is further configured to: the service provider's one-way index score, X4, is determined via the following formula:

and, in response to the ranking rate of the comparative index of the service provider being 1, setting a one-way index score of 2; in response to the ranking rate of the comparison index of the service provider being 0, a one-way index score of-2 is set.

In some embodiments, the integrated indicator layer comprises: the system comprises a substantial factor analysis unit, a service index analysis unit and a service index analysis unit, wherein the substantial factor analysis unit is configured to analyze representative and unrelated substantial factors corresponding to different service scenes from the service indexes of a service provider based on a dimension reduction analysis method; the single index weighting unit is configured to determine a weighted average value of the single indexes of the service providers based on the single index scores of the service providers corresponding to the substantial factors and predetermined single index weights; a substantive factor scoring unit configured to determine a weighted average of the individual indicators of the service provider as a score of the substantive factor of the service provider.

In some embodiments, the output layer comprises: a substantive factor weighting unit configured to determine a weighted average value of the substantive factors of the service provider based on the scores of the substantive factors of the service provider and preset weights of the substantive factors of each industry category; and a dynamic score determining unit configured to determine a weighted average of the substantive factors of the service provider as a service dynamic score of the service provider.

In some embodiments, the commitment score of the service provider is determined based on whether the service provider opens a service commitment via: an provisioning data acquisition unit configured to acquire a number of commitments provisioned by a service provider; a commitment score determining unit configured to determine a commitment score based on a number of commitments opened by the service provider, a preset commitment number threshold.

In some embodiments, the commitment score determination unit is further configured to: determining the ratio of the number of the commissions opened by the service provider to a preset committed number threshold as a committed coefficient; and determining the product of the commitment coefficient and a preset information entropy control coefficient as a commitment score.

In some embodiments, the service provider's service adaptation score is determined based on the service provider's adaptation data to the platform's service and operational metrics via: a factor coefficient determination unit configured to determine an acceleration factor coefficient of a service provider based on a preset acceleration factor calculation rule for a preset service adaptation factor; the total coefficient determining unit is configured to determine an accelerator total coefficient based on a preset acceleration factor weight and an acceleration factor coefficient of each service adaptation factor of the service provider; and the adaptive score determining unit is configured to determine a service adaptive score of the service provider based on the total accelerator coefficient and the service dynamic score of the service provider.

In some embodiments, the service metrics include: the system comprises commodity quality satisfaction, commodity description conformity, service attitude satisfaction, logistics speed satisfaction, inquiry average response time, response rate in inquiry preset time, condition acquisition timeliness rate in preset time, delivery order occupation ratio in preset time, returned goods repair rate, after-sale service time, returned goods processing satisfaction, transaction dispute rate, dispute autonomous completion rate and dispute processing compliance rate.

In some embodiments, the single indicator score comprises: the system comprises a commodity quality satisfaction degree score, a commodity description conformity degree score, a service attitude satisfaction degree score, a logistics speed satisfaction degree score, a query average response time length score, a response rate score within a query preset time length, a component collecting and time rate score within a preset time length, a delivery order proportion score within a preset time length, a return and exchange repair rate score, an after-sale service time length score, a return and exchange processing satisfaction degree score and a commodity dispute processing rate score.

In some embodiments, based on the dimension reduction analysis method, determining representative and unrelated substantial factors corresponding to different business scenarios from the service indexes of the service provider includes: based on a dimension reduction analysis method, determining the following representative and unrelated essential factors corresponding to different service scenes: determining an evaluation factor from the commodity quality satisfaction degree, the commodity description conformity degree, the service attitude satisfaction degree and the logistics speed satisfaction degree of a service provider; determining a consultation factor from the average response time of the inquiry of the service provider and the response rate within the preset inquiry time; determining logistics factors from a piece picking-up and time rate within a preset time length of a service provider and a delivery order occupation ratio within a preset time length; determining an after-sale factor from the return and replacement repair rate, the after-sale service duration and the return and replacement processing satisfaction degree of a service provider; and determining a dispute factor from the transaction dispute rate, the dispute autonomous completion rate and the dispute handling time-following rate of the service provider.

In some embodiments, the dimension reduction analysis method comprises one or more of: principal component analysis, factor analysis, and analytic hierarchy process.

In some embodiments, the traffic adaptation factor comprises: a commitment factor, a short video factor, an electronic invoice factor, a QCR factor, a repeat shop factor, and a store age factor.

In some embodiments, the means for assessing a service score of a service provider further comprises: a user information pushing component configured to push information to a user and/or a service provider based on a service score of the service provider.

In some embodiments, the user information pushing component is further configured to perform at least one of: in response to the service score of the service provider being lower than a threshold value, filtering out account and/or service information of the service provider with the service score lower than the threshold value from the information pushed to the user; and responding to the service score of the service provider lower than the threshold value, generating reminding information, and sending the reminding information to the service provider with the service score lower than the threshold value.

In a second aspect, an embodiment of the present disclosure provides an electronic device/terminal/server, including: one or more processors; storage means for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a service score calculation component as any one of above; and a service score output component for outputting the service score of the service provider calculated by the service score calculation component.

In a third aspect, embodiments of the present disclosure provide a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a service score calculation component as any one of the above.

An embodiment of the present disclosure provides an apparatus for assessing a service score of a service provider, including: a service score calculating component and a service score outputting component; a service score calculation component configured to calculate a service score for a service provider based on a dynamic scoring of the service provider's services and at least one of: a commitment score of a service provider and a service adaptation score of the service provider; the service dynamic score of the service provider is determined based on the original score of the service index of the service provider; the commitment score of the service provider is determined based on whether the service provider opens a service commitment; the service adaptation score of the service provider is determined based on adaptation data of the service provider to the service and the operation indexes of the platform; a service score output component configured to output a service score for the service provider. The device for evaluating the service score of the service provider provided by the embodiment determines the service score of the service provider based on the service index score, the commitment score and the service adaptation score, so that the comprehensiveness and the accuracy of the service score are improved, and the relevance of the service score and each single item of data is improved because the determination of the service index score based on the service score and the determination of the original score of the service index, the commitment score is determined based on whether the service provider opens the service commitment, and the service adaptation score is determined based on the adaptation data of the service provider to the service and the operation index of the platform.

In some embodiments, the scores of the single indexes are obviously differentiated after correction, and the differentiation is embodied; after the scores of the individual indexes are reduced to be the essential factors, the final service score can refer to the scores of all the essential factors, and the influence of the extremely low score of the individual indexes on the total score is avoided, so that the determination result of the service score is more reasonable. The method comprises the steps of determining the scores of the essential factors of the service provider by using a dimensionality reduction analysis method, determining the scores of the service indexes of the service provider based on the scores of the essential factors, eliminating the correlation among the essential factors, then matching weights, embodying the actual importance degree of weighting, and further improving the accuracy of the scores of the output service indexes.

Drawings

Other features, objects, and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which some embodiments of the present disclosure may be applied;

FIG. 2 is an exemplary block diagram of some embodiments of an apparatus for assessing a service provider's service score according to the present disclosure;

fig. 3 is an exemplary block diagram of an acquisition means of a dynamic score of a service in an apparatus for assessing a service score of a service provider according to an embodiment of the present disclosure;

FIG. 4 is a specific application scenario of an apparatus for assessing a service provider's service score applying embodiments of the present disclosure;

FIG. 5 is an exemplary block diagram of an index scoring layer for determining a dynamic scoring of services in an apparatus for assessing a service score of a service provider according to an embodiment of the present disclosure;

FIG. 6 is an exemplary block diagram of a comprehensive index layer for determining dynamic scoring of services in an apparatus for assessing service scores of service providers according to an embodiment of the present disclosure;

FIG. 7 is an exemplary diagram of a calculation result of a dynamic scoring of a service of an apparatus for assessing a service score of a service provider according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of an electronic device/terminal/server suitable for use in implementing embodiments of the present disclosure.

Detailed Description

The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

Fig. 1 illustrates an apparatus, an exemplary system architecture 100 of an apparatus, for assessing a service score of a service provider to which embodiments of the present disclosure may be applied.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have various communication client applications installed thereon, such as a browser application, a search-type application, a deep learning application, a shopping-type application, an instant messaging tool, a mailbox client, social platform software, and the like.

The

terminal apparatuses

101, 102, and 103 may be hardware or software. When the

terminal devices

101, 102, 103 are hardware, they may be various electronic devices supporting various client applications, including but not limited to tablet computers, laptop portable computers, desktop computers, and the like. When the

terminal apparatuses

101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.

The server 105 may be a server that provides various services, such as a background server that supports image acquisition requests made on the

terminal devices

101, 102, 103. The background server can analyze and process the received data such as the image acquisition request and feed back the processing result to the terminal equipment.

The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules, for example, to provide distributed services, or as a single piece of software or software module. And is not particularly limited herein.

It should be noted that, in practice, the apparatus for assessing the service score of the service provider provided by the embodiment of the present disclosure may be disposed in the

terminal device

101, 102, 103 or the server 105. And is not particularly limited herein.

It should be understood that the number of terminals, networks, and servers in fig. 1 are merely illustrative. There may be any number of terminals, networks, and servers, as desired for an implementation.

With continued reference to FIG. 2, FIG. 2 shows a schematic flow diagram of an apparatus for assessing a service score of a service provider according to the present disclosure.

As shown in fig. 2, an apparatus 200 for assessing a service score of a service provider, comprises: a service score calculation component 210 and a service score output component 220.

A service score calculation component 210 configured to calculate a service score for a service provider based on a service dynamic score for the service provider and at least one of: a commitment score for the service provider and a business fit score for the service provider.

In this embodiment, the service provider refers to a party that provides virtual or physical services to the customer, that is, a merchant that provides goods to the customer. Dynamic service rating, which refers to the rating score for the service provider's service rating system, i.e., the dsr (detail roller rating) score. The dynamic service score of the service provider may be determined based on the raw score of the service provider's service metrics. The service index here refers to an index of a service provided to a client by a service provider.

In some specific examples, the service metrics may include: the system comprises commodity quality satisfaction, commodity description conformity, service attitude satisfaction, logistics speed satisfaction, inquiry average response time, response rate in inquiry preset time, condition acquisition timeliness rate in preset time, delivery order occupation ratio in preset time, returned goods repair rate, after-sale service time, returned goods processing satisfaction, transaction dispute rate, dispute autonomous completion rate and dispute processing compliance rate.

The commodity quality satisfaction refers to an evaluation of whether a customer is satisfied with the quality of the commodity; the commodity description conformity degree refers to the evaluation of whether the commodity in the order conforms to the description by the customer; the service attitude satisfaction degree refers to evaluation of the satisfaction degree of the customer on the service attitude of the order; the logistics speed satisfaction degree refers to an evaluation of the satisfaction degree of the customer on the logistics speed of the order; the query average response time length is the average response time length of the customer service corresponding to the service provider in the customer service response system; inquiring the response rate in the preset duration refers to the frequency of the duration of the first response of the customer service corresponding to the service provider in the preset duration; the item collecting time rate in the preset time refers to the frequency of the service provider for completing the item collecting link in the preset time; the delivery order occupation ratio in the preset time length refers to the frequency of receiving commodities in the preset time length after the customer confirms to place the order; the return goods repair rate refers to the frequency of the goods provided by the service provider to be returned and repaired; the after-sale service duration refers to the average time from the initiation of a client to the completion of the whole after-sale service flow; the return processing satisfaction refers to an evaluation of the satisfaction of the customer with the return service; the transaction dispute rate refers to the frequency of transaction dispute orders caused by problems of the service provider or the supply and demand parties; the dispute independent completion rate refers to the frequency of the service provider independently completing the dispute order; dispute handling time compliance rate refers to the frequency with which a service provider completes dispute handling within a prescribed dispute handling time.

In some optional implementations of this embodiment, as shown in fig. 3, the dynamic scoring of the service by the service provider is determined based on the raw score of the service index of the service provider via the following functional layers: an input layer 211 configured to obtain a raw score of a service index of a service provider; an index scoring layer 212 configured to determine a single index score for a service provider based on a raw score of the service index for the service provider; a comprehensive index layer 213 configured to determine a substantive factor score of the service provider by using a dimension reduction analysis method based on the individual index score of the service provider; an output layer 214 configured to determine a service dynamic score for the service provider based on the substantive factor score for the service provider.

In this implementation, the input layer 211, the index score layer 212, the comprehensive index layer 213, and the output layer 214 may be a functional layer in the apparatus 200 for assessing a service score of a service provider (e.g., a functional layer in or outside the service score calculation component 210), or may be an external functional layer for outputting a dynamic score of a service to the service score calculation component 210.

The original score of the service index input by the input layer 211 may be obtained by calculating original data according to preset rules, and the preset rules may be set by those skilled in the art according to experience or application scenarios; the original score of the service index may also be imported directly from a third-party system, which is not limited by this disclosure.

In some specific examples, the method for calculating the original score of the service index in the above examples may be determined as follows: the method for calculating the satisfaction degree of the quality of the commodity comprises the following steps: mean of all commercial quality scores x2 over 180 days. The method for calculating the commodity description conformity comprises the following steps: mean of all commodity description scores x2 over 180 days. The method for calculating the satisfaction degree of the service attitude comprises the following steps: mean of all service attitude scores x2 over 180 days. The method for calculating the satisfaction degree of the logistics speed comprises the following steps: mean of all stream velocity scores x2 over 180 days. The method for calculating the average response time of inquiry comprises the following steps: total response time/number of consultations within 30 days. The method for calculating the response rate in the inquiry preset time comprises the following steps: number of first response/total response completed within 30 days, within 30 s. The method for calculating the timely rate of collecting the items in the preset time length comprises the following steps: within 30 days, the order number/total order number of the item collecting link is completed within 48 hours. The calculation method of the ratio of the orders sent within the preset time comprises the following steps: within 30 days, the customer receives the order number/total order number of the goods within three days. The method for calculating the return and replacement repair rate comprises the following steps: within 30 days, the service unit number/order number is changed back. The method for calculating the after-sale service time length comprises the following steps: duration used per after-sales service order/total number of service orders within 30 days. The method for calculating the satisfaction degree of the goods returning and changing process comprises the following steps: mean of all fallback service order scores x2 over 180 days. The calculation method of the transaction dispute rate comprises the following steps: within 30 days, (merchant dispute order + double-merchant dispute order)/total order number. The dispute autonomous completion rate calculating method comprises the following steps: within 30 days, 1- (amount of dispute units/total dispute units transferred to the customer service of the e-commerce platform). The dispute handling time compliance rate calculation method comprises the following steps: within 30 days, 1- (non-overtime dispute single amount/total dispute single amount).

It should be understood by those skilled in the art that the method for calculating the original score of the service index in the above example is only an example and does not represent a limitation of the present disclosure. For example, the skilled person can set the calculation of the collected data and the period of collecting the data as required.

The index scoring layer 212 determines the score of a single index of the service provider based on the original score of the service index of the service provider, may directly determine the original score of the service index as the score of the single index, may also perform data cleaning, data analysis, and processing on the original score of the service index to obtain data that is more convenient for subsequent analysis, and may use the analyzed and processed data as the score of the single index.

In some specific examples, the single indicator score may include: the system comprises a commodity quality satisfaction degree score, a commodity description conformity degree score, a service attitude satisfaction degree score, a logistics speed satisfaction degree score, a query average response time length score, a response rate score within a query preset time length, a component collecting and time rate score within a preset time length, a delivery order proportion score within a preset time length, a return and exchange repair rate score, an after-sale service time length score, a return and exchange processing satisfaction degree score and a commodity dispute processing rate score.

For example, the commodity dispute handling rate score in the single index score may be determined by integrating the transaction dispute rate, the dispute autonomous completion rate, and the dispute handling time-keeping rate in the original score of the service index. When the commodity dispute handling rate score is determined, the transaction dispute rate, the dispute autonomous completion rate and the dispute handling time compliance rate are respectively multiplied by a certain weight to determine the commodity dispute handling rate score; the commodity dispute handling rate score may also be determined based on the transaction dispute rate, and assisted by the dispute autonomous completion rate and the dispute handling compliance rate, which is not limited by the disclosure.

The comprehensive index layer 213 determines the scores of the essential factors of the service providers by using a dimension reduction analysis method based on the scores of the individual indexes of the service providers. The dimension reduction analysis method herein refers to a method for obtaining data with reduced dimensions from multidimensional data, and a person skilled in the art can analyze representative and unrelated substantial factors corresponding to different business scenarios from the service indexes of the service provider by using the dimension reduction analysis method in the prior art or the technology developed in the future, which is not limited in this disclosure.

For example, the representative and unrelated substantial factors corresponding to different business scenes can be analyzed from the service indexes of the service provider by adopting at least one dimension reduction analysis method of a principal component analysis method, a factor analysis method and an analytic hierarchy method.

When the dimensionality reduction analysis method is adopted to determine the substantial factor score of the service provider, a dimensionality reduction analysis model can be adopted, the one-way index score sample is used as input, the substantial factor score of the corresponding one-way index score sample is used as expected output, and the dimensionality reduction analysis model is trained, so that the pre-trained dimensionality reduction analysis model is obtained. The dimension reduction analysis model may be a machine learning model suitable for performing dimension reduction analysis, and the present application does not limit this.

When the representative and unrelated substantial factors corresponding to different business scenes are required to be analyzed from the service indexes of the service provider, the single index score of the service provider can be input into the pre-trained dimension reduction analysis model, so that the substantial factor score of the service provider output by the pre-trained dimension reduction analysis model is obtained.

The output layer 214 determines a service dynamic score for the service provider based on the substantive factor score for the service provider. The dynamic service score may be obtained by directly using the scores of the virtual factors as the dynamic service score, or by analyzing and processing the scores of the virtual factors on the basis of the scores of the virtual factors.

In the above embodiments, the commitment score of the service provider for calculating the service score of the service provider may be determined based on whether the service provider opens the service commitment. The commitment score of a service provider may quantify the score of the commitment of the service provider.

In some specific examples, the commitment score may employ a plurality of commitment-related metrics, each commitment metric corresponding to a commitment of a customer by a specific service provider. Specifically, the number of promises opened by each merchant may be counted, and the number of promises opened determines the promises score of the service provider.

In some optional implementations, the commitment score of the service provider is determined based on whether the service provider opens a service commitment via the following units (not shown in the figure): an provisioning data acquisition unit configured to acquire a number of commitments provisioned by a service provider; a commitment score determining unit configured to determine a commitment score based on a number of commitments opened by the service provider, a preset commitment number threshold.

In this implementation manner, the number of promises opened by the service provider may be compared with a preset promises number threshold, and if the number of promises opened by the service provider is greater than or equal to the preset promises number threshold, it may be determined that the promises of the service provider score higher by a predetermined score, and the predetermined score is positively correlated with the number of promises, that is, the higher the number of promises opened, the higher the promises score is; if the number of the promises opened by the service provider is smaller than the preset promises number threshold, it may be determined that the promises score of the service provider is a lower predetermined score, but the predetermined score is positively correlated with the number of the promises, that is, the smaller the number of the promises opened, the lower the promises score. The commitment score is determined based on the number of commitments opened by the service provider and the preset commitment number threshold, so that the commitment score can be quantized, the analyzability of data is improved, a data base is provided for subsequent calculation, and the accuracy of calculating the service score of the service provider is improved.

In some optional implementations, the commitment score determination unit is further configured to: determining the ratio of the number of the commissions opened by the service provider to a preset committed number threshold as a committed coefficient; and determining the product of the commitment coefficient and a preset information entropy control coefficient as a commitment score.

In this implementation, the commitment coefficient is a ratio of the number of commitments opened by the service provider to a preset commitment number threshold, and the ratio is multiplied by a preset information entropy control coefficient, where the product is a commitment score of the service provider. And the preset information entropy control coefficient is obtained by reverse deduction according to the requirement of information expression.

In a specific example of this implementation, the e-commerce platform may use 7 commitment-related indicators, and the preset commitment coefficient is 5, so that the commitment score may be obtained by the following formula:

acceptance score is acceptance coefficient x 0.1

Wherein, 0.1 is the information entropy control coefficient of the commitment score.

In the implementation mode, the product of the commitment coefficient and the preset information entropy control coefficient is determined as the commitment score, so that the requirement of information expression of the commitment score can be refined, and the accuracy of finally calculating the service score of the service provider is improved.

In the above embodiment, the service adaptation score of the service provider for calculating the service score of the service provider may be determined based on the adaptation data of the service provider to the service and operation indexes of the platform.

In some optional implementations of the present embodiment, the service provider's service adaptation score is determined based on the service provider's adaptation data to the platform's service and operational metrics via: a factor coefficient determination unit configured to determine an acceleration factor coefficient of a service provider based on a preset acceleration factor calculation rule for a preset service adaptation factor; the total coefficient determining unit is configured to determine an accelerator total coefficient based on a preset acceleration factor weight and an acceleration factor coefficient of each service adaptation factor of the service provider; and the adaptive score determining unit is configured to determine a service adaptive score of the service provider based on the total accelerator coefficient and the service dynamic score of the service provider.

In this implementation, the business adaptation score is mainly used to quantify the degree of adaptation of the value view of the service provider and the e-commerce platform. Multiple business and operation related indexes of the e-commerce platform can be selected, and whether the service provider actively participates in the operation process of the Jingdong platform or not is measured.

In some specific examples, the traffic adaptation factor includes: a commitment factor, a short video factor, an electronic invoice factor, a Quality Control Reliability (QCR) factor, a repeat shop factor, and a store age factor.

The acceleration factor calculation rule refers to different acceleration factor calculation rules set by those skilled in the art for different service adaptation factors according to experience, application scenarios or information expression. The present disclosure is not limited thereto.

In a specific example, for the traffic adaptation factor in the above example, the following calculation may be used to determine the acceleration factor coefficient of the service provider:

commitment factor, merchant unopened commitment: the commitment score is 0, and the acceleration is not carried out; the merchant has opened a commitment: committed performance rate (committed): 0 score [0, 75%), 3 score [ 75%, 80%), 4 score [ 80%, 85%), 5 score [ 85%, 100%); the contract-drawing performance rate: 0 score [0, 75%), 6 score [ 75%, 80%), 7 score [ 80%, 85%), 9 score [ 85%, 100%); committed accuracy (committed): 0 to 0% for [0, 85%), 1 to [ 85%, 100% ]; adding the commitment score to the above three scores; data cycle: t +1, T is a natural number not less than 0.

Then the acceleration factor coefficient of the commitment factor is the commitment score/total score. Wherein, the total score is 15. The data period is preset T periods plus 1 period.

The video factor is 0.6 sku _ rate +0.4 grade _ score.

Calculating the ranking rate of the video factor score: if the number of the SKUs is larger than 100 and the SKU _ rate is larger than or equal to 0.1, calculating the ranking rate of the video _ score in the shop; if the number of SKUs is more than or equal to 30 and less than or equal to 100 and the SKU _ rate is more than or equal to 0.2, calculating the ranking rate of the video _ score in the shop; in other cases, the ranking rate is not calculated, and acceleration is not performed.

Acceleration factor coefficient of short video factor: can be calculated according to the ranking rate of the video factor score

The electronic invoice factor is activated, namely accelerated, and is not activated and not accelerated.

And the QCR factor is used for performing reduction processing on the merchants suspected of having quality problems according to the QCR model result. And on the QCR data side, a vender _ id and a ranking rate are given, a deceleration punishment is carried out on the merchants with the ranking rate of 0-0.2, and the ranking is not classified into secondary categories.

The acceleration factor coefficient of the QCR factor is equal to the ranking rate × 5-0.25.

And (4) repeating the goods laying factor, counting data within 30 days, and performing descending processing on the merchants with repeated goods laying behaviors. And the reward and punishment side gives a video _ id and repeated paving times, the reward and punishment side judges repeated paving results every week and updates the merchant service rating system side every day.

The store age factor is accelerated all year round, and the peak value is reached in five years.

Remarking: the age of the store (year) ∈ (0, ∞).

After calculating the acceleration factor coefficients of the service adaptation factors, the total coefficient of the accelerator may be obtained according to a preset acceleration factor weight and a weighted average of the acceleration factor coefficients of the service adaptation factors.

Specifically, the weighted average may be directly used as the total accelerator coefficient, or the total accelerator coefficient may be obtained by adjusting the weighted average. For example, in one example adapted to the adaptation factor in the above example, the following formula may be used to calculate the accelerator total coefficient:

wherein, the acceleration factor coefficient of each service adaptation factor (commitment factor, short video factor, electronic invoice factor, Quality Control Reliability (QCR) factor, repeat shop factor and shop age factor) is recorded as: x₁、X₂…X₆The acceleration factor weight is recorded as β₁、β₂…β₆，

For the weight adjustment coefficient, 0.04 is the information entropy control coefficient of the total coefficient of the accelerator.

After the total accelerator coefficient is determined, a service adaptation score of the service provider may be determined according to the total accelerator coefficient and a service dynamic score of the service provider. Specifically, a service dynamic scoring increment can be added on the basis of the service dynamic scoring, and the service dynamic scoring increment can be obtained based on the product of the service dynamic scoring and the total coefficient of the accelerator.

In some specific examples, a constraint may be introduced to the dynamic service score increment for modification based on the calculated dynamic service score increment, so as to obtain a modified dynamic service score increment. And then, determining the modified dynamic service score increment as a service adaptation score of the service provider.

For example, in an example adapted to the total accelerator coefficient in the above example, the following formula may be used to determine the service dynamic score increment, that is, obtain the service adaptation score of the service provider:

service adaptation score △ DSR₀＝DSR₀×Y₀；

Wherein the DSR₀And dynamically scoring the service of the service provider before acceleration.

Thereafter, the service provider's traffic adaptation score and accelerator total coefficient may be output:

accelerated total score for service provider after considering service adaptation score (DSR)₀+△DSR₁(ii) a Total accelerator coefficient: y is₀。

In the implementation mode, the service adaptation score of the service provider is determined based on the total coefficient of the accelerator and the service dynamic score of the service provider, the adaptation degree of a merchant and a Jingdong value pipe is introduced into the final service adaptation score, and the reasonability and the accuracy of the service adaptation score are improved.

In the above embodiment, after determining the service dynamic score, the commitment score and the service adaptation score, respectively, the service score of the service provider may be determined based on the service dynamic score of the service provider, the commitment score of the service provider and the service adaptation score of the service provider. When each item of service dynamic score, commitment score and service adaptation score is quantized, the service dynamic score, the commitment score and the service adaptation score have model additivity, and a final score representing the service level of a merchant, namely a service score of a service provider can be obtained and used as a service score output by a final wind vane:

service provider's service score × (1+ total acceleration factor) + commitment score.

In the present embodiment, the service score output component 220 is configured to output a service score of the service provider.

In some specific examples, the service score output component may be a display device, a storage device, or an output interface connected with other third parties, and is configured to output the service score of the service provider to the display device, the storage device, or the third party for viewing by a user or subsequent invocation by the third party.

The device for evaluating the service score of the service provider according to the embodiment of the disclosure determines the service score of the service provider based on the service index score, the commitment score and the service adaptation score, so that the comprehensiveness and accuracy of the service score are improved, and the relevance of the service score and each single item of data is improved because the determination of the service index score based on the service score and the determination of the original score of the service index, the commitment score is determined based on whether the service provider opens the service commitment, and the service adaptation score is determined based on the adaptation data of the service provider to the service and the operation index of the platform.

In some optional implementations of the above embodiments, the means for assessing a service score of the service provider may further comprise: a user information pushing component configured to push information to a user and/or a service provider based on a service score of the service provider.

In this implementation, the user information pushing component included in the means for assessing the service score of the service provider may push information to the user and/or the service provider based on the service score of the service provider.

In particular, the means for assessing the service score of the service provider may push the service score of the service provider directly to the user and/or the service provider; or determining push information according with the service score of the service provider based on the service score of the service provider, and then pushing the determined push information to the user and/or the service provider.

For example, when the service score of the service provider is lower than a threshold value, account and/or service information of the service provider with the service score lower than the threshold value is filtered out from the information pushed to the user; alternatively or additionally, in response to the service provider's service score being below a threshold, generating an alert and sending the alert to the service provider whose service score is below the threshold.

In this implementation manner, since the service score of the service provider evaluated by the apparatus is more comprehensive, accurate and relevant, the information pushed to the service provider is also more comprehensive, accurate, relevant and rich in pertinence.

Referring to fig. 4, fig. 4 is a specific application scenario of the apparatus for assessing a service score of a service provider applying an embodiment of the present disclosure.

As shown in fig. 4, the device for assessing the service score of the service provider can be applied to an O2O platform (online/offline/online-offline, which means that offline business opportunities are combined with the internet to make the internet a platform for offline transactions) or an e-commerce platform, and the platform 410 manages the accounts of the

service providers

420, 430, 440, and 450 according to the service scores of the

service providers

420, 430, 440, and 450. Specifically, if the service score is within a preset threshold interval, the account permissions will be changed.

The authority of the account to be changed here may be a service display authority, that is, whether the commodity information sent by the service provider can be displayed at each user side, or whether the account information or the commodity information related to the account is displayed in the user search result.

For example, when the service score 9.8 of the service provider 420 (account ID001) is in the threshold interval of the first level, the account authority of the service provider 420 may be the AAA authority, and the service provider 420 may display the account information of the service provider at an exhibition location located in the first area among the user search results and display a predetermined number of goods information of the service provider.

When the service score of 8.6 for service provider 430 (account ID002) is within the second level of threshold interval, the account privileges of service provider 430 may be BBB privileges. The service provider 430 may display account information of the service provider at the exhibitor located in the second area among the user search results and display commodity information of a preset number of the service provider. And the maximum value of the threshold interval of the second grade is smaller than or equal to the minimum value of the threshold interval of the first grade.

And by analogy, when the service score of the service provider is in the unqualified threshold interval, the account permission of the service provider can be NNN permission. The service provider is limited not to show account information of the service provider in the user search result or not to show account information or commodity information related to the account in the user search result.

In one particular example, when the user 460 of the platform enters a search keyword at the terminal 470 to search for a service, the platform retrieves the search request, then searches in a service database (keyword matching, etc.), and then filters based on the service scores of the various service providers. For example, if the service score of a service provider is lower than a threshold value, filtering out the account and/or the provided service of the service provider from the search result returned by the user; alternatively or additionally, if the service score of the service provider is below a threshold, generating a reminder message and sending the reminder message to the service provider.

Referring to fig. 5, fig. 5 is an exemplary structural diagram of an index score layer for determining a dynamic scoring of a service in an apparatus for assessing a service score of a service provider according to an embodiment of the present disclosure.

As shown in fig. 5, the index scoring layer 212 for determining the dynamic service score according to the present embodiment may include: a comparison index screening unit 2121, a sample level correction unit 2122, an index ranking rate conversion unit 2123, a score distribution projection unit 2124, and a score distribution correction unit 2125.

The comparison index screening unit 2121 is configured to screen comparison indexes of various industry categories from service indexes of the service provider.

In this embodiment, since the differences of the service indexes under different industry categories are huge, and the same set of service indexes cannot be used as a scoring basis among different industry categories, a method of comparing service indexes within the industry categories is used to calculate the score of a single service index.

In order to ensure that the comparison indexes selected under the industry category are actually comparable, whether the number of effective merchants corresponding to a certain service index under the industry category is greater than a preset merchant number threshold (for example, greater than or equal to 10) can be judged; if not, the index score of the merchant is not calculated, and the index score of the merchant under the industry category is NULL. In addition, the service indexes with extremely poor original scores of the service indexes of the merchants under the industry category can be removed, namely the service indexes meet certain screening conditions when the comparison indexes of all the industry categories are screened out. For example: the original score max-min of the service index is more than or equal to 0.01, and the variance sigma 2 is more than or equal to 0.0001; if not, the index score of the merchant is not calculated, and the index score of the merchant under the industry is NULL.

The sample level correcting unit 2122 is configured to correct the original score of the comparison index of the service provider based on a blank sample level of the comparison index of the industry category to which the service provider belongs, to obtain a corrected score of the comparison index of the service provider.

In this embodiment, since there are many very small samples in the actual production environment, the reliability of such data is low, and the accidental degree is high, which will cause serious interference to the accuracy of the model if left alone. Therefore, the sample level of the comparative index needs to be corrected, so that the index performance level is more stable and more suitable for the actual situation.

In order to correct the extreme value condition of the small sample, so that the extreme value condition of the small sample has stability and conforms to the actual condition, a blank sample level of a comparison index can be searched first, wherein the blank sample level of the comparison index refers to a reference sample level which can be used as an original score of the comparison index of a correction service provider, and can be determined by a person skilled in the art according to experience or application scenarios or can be determined based on statistics of big data.

For example, the sample level modification unit 2122 may be further configured to: eliminating extreme values in the original scores of the comparative indexes of various industry categories; and marking the median of the original scores of the comparative indexes of all the industry categories after the extreme values are removed as blank sample levels of the comparative indexes of all the industry categories.

After determining the blank sample level of the comparison index, sample correction methods in the prior art or in future developed technologies may be employed to correct for boundary effects and small sample size problems, which are not limited by this disclosure. For example, filters are employed to correct for boundary effects of samples, conversion and expansion of samples are employed to solve the problem of small sample sizes, and so on.

In some optional implementations of this embodiment, the sample level modification unit 2122 is further configured to: correcting the original score of the comparative index of the service provider by adopting the following formula to obtain a corrected score X of the comparative index of the service provider₁：

in the method for obtaining the corrected score of the comparative index of the service provider in the implementation manner, the reliability of data can be improved by correcting the sample number and the filling sample amount adopted by the comparative index of the service provider, so that the expression level of the corrected score of the comparative index is more stable, and the method is more in line with the actual situation.

And the index ranking rate conversion unit 2123 is configured to calculate the ranking rate of the comparative index of the service provider in the industry category to which the service provider belongs after removing the extreme value based on the corrected score of the comparative index of the service provider.

In this embodiment, since abnormal data inevitably exists in the production environment, and the data distribution exhibits trailing and thick trailing states, if a simple normalization and normalization method is adopted to eliminate the difference between the indexes, data distortion and misalignment may be caused, and the data is easily interfered by individual extreme value data. Therefore, based on comparing the differences of the merchant indexes within the industry category, index rankings under the industry category need to be calculated.

In some optional implementations of this embodiment, the index ranking rate conversion unit 2123 is further configured to: determining a ranking of the service provider's comparison indicators in the industry category to which the service provider belongs based on the following constraints: if the correction score of the comparison index is higher, the ranking of the comparison index is lower; when the correction scores of a plurality of service providers are the same, the ranking of the comparison index of the service provider with larger number of samples is smaller; ranking of the comparison indexes of the plurality of service providers with the same corrected score and the same sample number in parallel, wherein the ranking of the parallel comparison indexes is as follows: the minimum value of the rank of the selectable comparison indicator corresponding to the revised score.

In this implementation manner, the higher the correction score of the comparison index is, the better the performance of the merchant is, so the smaller the ranking is, that is, the ranking is more advanced; when the correction scores of the comparison indexes of a plurality of merchants are the same, the number n of merchant samples can be referred to₀，n₀The larger the correction score of the comparison index is, the more difficult the correction score is, so that the ranking is smaller, namely the ranking is more advanced; the corrected scores of the comparison indexes of the multiple merchants are the same, and the number of the samples is the same, so that the service degrees of the comparison indexes of the various merchants are basically equal, the comparison indexes are ranked in parallel, and the lowest feasible value is selected.

In the implementation mode, when the ranking of the service provider in the comparison indexes of the industry categories is determined, a plurality of constraints are introduced, so that the stability of the ranking result can be improved.

In some optional implementations of this embodiment, the index ranking rate conversion unit 2123 is further configured to: the ranking rate X of the comparative indexes of the service provider in the industry category is calculated by adopting the following formula₂：

Wherein the content of the first and second substances,

In the implementation mode, when the index level of the merchant is an extreme value, the ranking process is not started; according to the index definition, the ranking rate of the direct assignment comparison index is 0 or 1.

In the implementation mode, the ranking rate of the service provider in the comparative indexes of the industry categories is calculated, and a stable rank statistical method can be adopted to design a frame, so that the model is stable and reliable in a production environment.

A score distribution projection unit 2124 configured to project the ranking rate of the service provider at the comparison index of the industry category to a score distribution conforming to the original distribution.

In this embodiment, when the projection is a score distribution conforming to the original distribution, the ranking rate of the comparison index of the service provider in the industry category to which the service provider belongs may be projected as the score distribution conforming to the original distribution. The original distribution here is a distribution state of the original data.

The score distribution conforming to the original distribution can be realized by adopting a distribution mode capable of projecting to the original distribution in the prior art or the future developed technology, and the disclosure does not limit the score distribution. For example, the ranking rate of the service provider's comparison indicators for the industry category may be projected as the abscissa of a Sigmoid distribution, an exponential distribution, a poisson distribution, or a chi-square distribution (chisquare) to achieve a score distribution that conforms to the original distribution.

Taking Sigmoid distribution as an example, in some specific examples, the score distribution projection unit 2124 is further configured to: projecting the ranking rate of the service provider in the comparison index of the industry category to a bell-shaped distribution curve-logic curve inverse function X₃：

Wherein 0.7 is a density adjustment coefficient, X₃The following constraints are satisfied: x₁X of service provider being extreme₃Is NULL.

In these examples, the ranking rate projection of the service provider's comparison index for the industry category is projected onto a bell-shaped distribution curve-logic curve inverse. Under this process, X₁X of extreme merchant₃For NULL, redefinition is required in the next step. Parameter 0.7 is to adjust the ranking rate X₂The density of (c).

In the ranking rate projection method in this example, the ranking rate of the comparison index under the industry category is essentially a rank statistic, which approaches to uniform distribution, and this is different from the original distribution of data, and inevitably has large information loss. In order to make up for the loss, a distributed projection mode is adopted, the ranking rate is projected to the ordinate value of Sigmoid distribution, the data distribution obtained after projection is closer to the original distribution, the robustness is good, and the additivity of each index in the model is also ensured.

And a score distribution correcting unit 2125 configured to correct the score distribution conforming to the original distribution based on a preset score boundary, and complement the corrected score of the removed comparative index of the service provider to obtain a single index score of the service provider.

In this embodiment, after the projection is completed, in order to better fit the data distribution of the actual scene and ensure the stability of the model, a score boundary needs to be set for the score distribution, so as to correct the score distribution conforming to the original distribution, and then complement the corrected score (i.e., the previous extreme data) of the removed comparison index of the service provider to obtain the single index score of the service provider.

In some optional implementations of this embodiment, the score distribution correcting unit 2125 is further configured to: determining a one-way index score X for a service provider via the following formula₄：

In the implementation mode, due to the special property of Sigmoid distribution, data can tend to be infinite, and more according to the related knowledge of quantiles, data larger than 2 can tend to 2, and data smaller than-2 can tend to-2, so that only 10% of data is limited, but the stability of the model is greatly improved, and abnormal results of the model cannot occur due to certain extreme value data.

In addition, for the extremum value data, a complement number is required. According to the actual situation of the indexes, the ranking rate is 1 in the excellent situation and 0 in the poor situation. Outputting the score X of the single index₄According to the interaction result with the business parties (including merchants and operations) using the device for assessing the service score of the service provider in the practical application scenario, the score correspondence business concept is as follows:

service provider's one-way index score X₄-2, indicating that the service provider performs very badly on the service with the one-way index score;

service provider's one-way index score-2<X₄<-1, representing that the service provider performs poorly for the business for which the one-way indicator scores;

service provider's one-way index score-1<＝X₄<1, indicating that the service provider has moderate business performance corresponding to the one-way index score;

service provider's one-way index score 1<＝X₄<2, the service provider is shown to have good performance on the service with the one-way index score;

service provider's one-way index score X₄2, the service provider is shown to perform excellently for the service that should score the one-way indicator.

In the embodiment shown in fig. 5 of the present disclosure, the index scoring layer for determining the dynamic service score may determine the score of a single index of the service provider by using the comparative index screening unit 2121, the sample level correcting unit 2122, the index ranking rate converting unit 2123, the score distribution projecting unit 2124, and the score distribution correcting unit 2125, where the score of the single index is obviously differentiated after correction, and the score differentiation of the one-way index is improved.

With further reference to fig. 6, fig. 6 is an exemplary block diagram of a comprehensive index layer for determining dynamic scoring of services in an apparatus for assessing service scores of service providers according to an embodiment of the present disclosure.

As shown in fig. 6, the comprehensive index layer 213 for determining dynamic scores of services according to the present embodiment may include: a substantial factor analyzing unit 2131, configured to analyze, based on a dimension reduction analysis method, substantial factors that correspond to different service scenarios and are representative and unrelated from service indexes of a service provider; a single index weighting unit 2132 configured to determine a weighted average of the single indexes of the service providers based on the single index scores of the service providers corresponding to the respective substantive factors and a predetermined single index weight; a figure of merit scoring unit 2133 configured to determine a weighted average of the individual indicators of the service provider as a score of the figure of merit for the service provider.

In this embodiment, the dimension reduction analysis method refers to a method for obtaining data with reduced dimensions from multidimensional data, and a person skilled in the art may analyze representative and unrelated substantial factors corresponding to different service scenarios from service indexes of a service provider by using a dimension reduction analysis method in the prior art or a technology developed in the future, which is not limited in this disclosure. For example, the representative and unrelated substantial factors corresponding to different business scenes can be analyzed from the service indexes of the service provider by adopting at least one dimension reduction analysis method of a principal component analysis method, a factor analysis method and an analytic hierarchy method.

In some optional implementation manners of this embodiment, based on a dimension reduction analysis method, determining representative and unrelated substantial factors corresponding to different service scenarios from the service indexes of the service provider includes: based on a dimension reduction analysis method, determining the following representative and unrelated essential factors corresponding to different service scenes: determining an evaluation factor from the commodity quality satisfaction degree, the commodity description conformity degree, the service attitude satisfaction degree and the logistics speed satisfaction degree of a service provider; determining a consultation factor from the average response time of the inquiry of the service provider and the response rate within the preset inquiry time; determining logistics factors from a piece picking-up and time rate within a preset time length of a service provider and a delivery order occupation ratio within a preset time length; determining an after-sale factor from the return and replacement repair rate, the after-sale service duration and the return and replacement processing satisfaction degree of a service provider; and determining a dispute factor from the transaction dispute rate, the dispute autonomous completion rate and the dispute handling time-following rate of the service provider.

In this implementation manner, by using the dimension reduction analysis method, it can be found that there are 5 representative and unrelated substantial factors that are independent from each other, correspond to different service scenarios: the evaluation factor (corresponding to the evaluation service scene), the consultation factor (corresponding to the consultation service scene), the logistics factor (corresponding to the logistics service scene), the after-sales factor (corresponding to the after-sales service scene) and the dispute factor (corresponding to the dispute service scene). These 5 factors can well characterize the main information of the original data set. Each factor is calculated by 12 one-way index scores corresponding to 14 service indexes according to different weight ratios.

Alternatively or additionally, the output layer 214 for determining the dynamic scoring of the services comprises (not shown in the figures): a substantive factor weighting unit configured to determine a weighted average value of the substantive factors of the service provider based on the scores of the substantive factors of the service provider and preset weights of the substantive factors of each industry category; and a dynamic score determining unit configured to determine a weighted average of the substantive factors of the service provider as a service dynamic score of the service provider.

Here, the intrinsic correlation of the original data is eliminated, 5 independent essential factors which are independent and additive are established, and then the weight configuration is carried out according to the service scene. And the service personnel labels the importance degree of the one-way index scores in different service scenes according to different industry categories, and then the dimensionality reduction analysis model automatically calculates the scores of all the essential factors and the weight of the essential factors.

In the configuration process, under the condition that each industry category is set by business personnel, the importance of each business scene to the service level of a merchant can be divided into 1-5 levels, the most important mark is 5, the least important mark is 1, and the default level is 3. After the importance degree of each essential factor is labeled, the weight of each preset essential factor of each industry category is calculated to be the importance of a single essential factor/the importance of each essential factor.

After the scores of the output essential factors and the weights of the corresponding essential factors are calculated, the data results output by the index score layer have robustness and additivity, and the essential factors extracted by the dimension reduction analysis method also have robustness and additivity, so that the final DSR score can be obtained by directly carrying out weighted average.

DSR score-coefficient value of each real factor x real factor weight

The result has robustness, the cliff-breaking type sudden rising and falling cannot occur, the accuracy is high, the influence of each service scene on the service level is objectively reflected, and the influence degree of each specific index is strictly limited.

In the comprehensive index layer for determining dynamic service scores in this embodiment, after the scores of the individual indexes are reduced to the substantial factors, the final service score may refer to the scores of all the substantial factors, so that the influence of the extremely low score of the individual index on the total score is avoided, and the determination result of the service score is more reasonable. And moreover, the substantive factor score of the service provider is determined by adopting a dimensionality reduction analysis method, the service index score of the service provider is determined based on the substantive factor score, the matching weight is obtained after the correlation among the substantive factors is eliminated, the actual importance degree of the empowerment is embodied, and the accuracy of the output service index score is improved.

An exemplary graph of the calculation result of the dynamic service score of the apparatus for assessing a service score of a service provider of the present disclosure is described below with reference to fig. 7.

As shown in fig. 7, the service provider _ ID is a merchant 102100, the industry category ID is 1345, and the original scores of the service indexes provided by the service provider 102100 are as follows: satisfaction degree of commodity quality: 9.541 points; commodity description compliance: 9.191 points; service attitude satisfaction degree: 9.150 points; satisfaction degree of material flow speed: 9.087 points; consultation average response duration: 16.80 s; consult 30s response rate: 63.66 percent; collecting the time rate of the items in 48H: 100 percent; every other day order ratio: 61.11 percent; return and replacement repair rate: 0.26 percent; length of after-sale service: 290.0 h; satisfaction of return and exchange treatment: 6.333 min; transaction dispute rate: 0.37 percent; dispute autonomous completion rate: 33.33 percent; dispute handling time-following rate: 100 percent.

The scores of the single indexes obtained by calculation according to the original scores of the service indexes are respectively as follows: the commodity quality satisfaction degree score is as follows: -1.3640; product description compliance score: -0.8918; service attitude satisfaction score: -1.2832; and (3) scoring the satisfaction degree of the logistics speed: -1.2038; consult average response duration score: 2.0000; consult 30s response rate score: 0.7293, respectively; collecting the items in 48H and scoring the time rate: 2.0000; every other day order percentage score: 1.4070, respectively; return and replacement repair rate score: 0.0000; after-market service duration score: -0.8132; return processing satisfaction score: -1.9729; corresponding to the transaction dispute rate, dispute autonomous completion rate and dispute handling time-honoring rate score: -0.3628.

The scores of the essential factors obtained after the dimensionality reduction analysis is carried out according to the scores of the single indexes are as follows: the score for the evaluation factor was 8.4186; the score of the advisory factors is: 9.624, respectively; the logistic factors score: 9.8257, respectively; the after-market factors score as: 8.3206, respectively; the dispute factor score is: 9.6371.

the dynamic service score (DSR score) of the service provider obtained from the scores of the substantive factors and the preset weights of the substantive factors for the respective industry categories is 9.1652.

It should be understood that the application scenarios of the apparatus for rating a service score of a service provider illustrated in fig. 2-7 above are merely exemplary descriptions of the apparatus for rating a service score of a service provider and do not represent a limitation on the method. For example, the above-described means may also be combined in different functional layers or units depending on the functions implemented. The present disclosure is not limited thereto.

Referring now to fig. 8, a schematic diagram of an electronic device (e.g., a server or terminal device of fig. 1) 800 suitable for use in implementing embodiments of the present disclosure is shown. Terminal devices in embodiments of the present disclosure may include, but are not limited to, devices such as notebook computers, desktop computers, and the like. The terminal device/server shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 8, an electronic device 800 may include a processing means (e.g., central processing unit, graphics processor, etc.) 801 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage means 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data necessary for the operation of the electronic apparatus 800 are also stored. The processing apparatus 801, the ROM802, and the RAM803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

Generally, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage 808 including, for example, magnetic tape, hard disk, etc.; and a communication device 809. The communication means 809 may allow the electronic device 800 to communicate wirelessly or by wire with other devices to exchange data. While fig. 8 illustrates an electronic device 800 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 8 may represent one device or may represent multiple devices as desired.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 809, or installed from the storage means 808, or installed from the ROM 802. The computer program, when executed by the processing apparatus 801, performs the above-described functions defined in the methods of the embodiments of the present disclosure. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement a service score calculation component in an apparatus for assessing a service score of a service provider, the service score calculation component configured to calculate the service score of the service provider based on a dynamic score of the service provider and at least one of: a commitment score of a service provider and a service adaptation score of the service provider; the service dynamic score of the service provider is determined based on the original score of the service index of the service provider; the commitment score of the service provider is determined based on whether the service provider opens a service commitment; the service provider's service adaptation score is determined based on the service provider's adaptation data to the platform's service and operational metrics.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes a service score output component. Where the names of these components do not in some cases constitute a limitation on the unit itself, for example, the service score output component may also be described as a "component for calculating a service score for a service provider based on the service dynamic score of the service provider and at least one of the following.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept as defined above. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. An apparatus for assessing a service score of a service provider, comprising: a service score calculating component and a service score outputting component;

the service score calculation component configured to calculate a service score for a service provider based on a dynamic scoring of the service provider and at least one of: a commitment score of a service provider and a service adaptation score of the service provider;

wherein the dynamic service score of the service provider is determined based on a raw score of a service index of the service provider; the commitment score of the service provider is determined based on whether the service provider opens a service commitment; the service adaptation score of the service provider is determined based on adaptation data of the service provider to the service and the operation indexes of the platform;

the service score output component configured to output a service score for the service provider.

2. An apparatus for assessing a service score of a service provider as recited in claim 1, wherein the service provider's dynamic score for a service is determined based on a raw score of a service provider's service metrics via the following functional layers:

an input layer configured to obtain a raw score of a service index of a service provider;

an index scoring layer configured to determine a single index score for a service provider based on a raw score of a service index for the service provider;

a comprehensive index layer configured to determine a substantive factor score of a service provider by a dimension reduction analysis method based on the individual index score of the service provider;

an output layer configured to determine a service dynamic score for a service provider based on the substantive factor score for the service provider.

3. The apparatus for assessing a service score of a service provider of claim 2, wherein the index score layer comprises:

the comparison index screening unit is configured to screen out comparison indexes of various industry classes from the service indexes of the service provider;

the sample level correcting unit is configured to correct the original score of the comparison index of the service provider based on the blank sample level of the comparison index of the industry category to which the service provider belongs to obtain the corrected score of the comparison index of the service provider;

the index ranking rate conversion unit is configured to calculate the ranking rate of the comparative indexes of the service provider in the industry category after removing extreme values based on the corrected values of the comparative indexes of the service provider;

a score distribution projection unit configured to project the ranking rate of the service provider at the comparison index of the industry category to a score distribution conforming to an original distribution;

and the score distribution correcting unit is configured to correct the score distribution which accords with the original distribution based on a preset score boundary, and complement the corrected score of the removed comparative index of the service provider to obtain the single index score of the service provider.

4. The apparatus for assessing a service score of a service provider of claim 3, wherein the sample level correction unit is further configured to:

eliminating extreme values in the original scores of the comparative indexes of various industry categories;

and marking the median of the original scores of the comparative indexes of all the industry categories after the extreme values are removed as blank sample levels of the comparative indexes of all the industry categories.

5. The apparatus for assessing a service score of a service provider of claim 4, wherein the sample level correction unit is further configured to:

correcting the original score of the comparative index of the service provider by adopting the following formula to obtain a corrected score X of the comparative index of the service provider₁：

6. the apparatus for assessing a service score of a service provider of claim 5, wherein the index rank ratio conversion unit is further configured to:

determining a ranking of the service provider's comparison indicators in the industry category to which the service provider belongs based on the following constraints:

if the correction score of the comparison index is higher, the ranking of the comparison index is lower;

when the correction scores of a plurality of service providers are the same, the ranking of the comparison index of the service provider with larger number of samples is smaller;

ranking of the comparison indexes of the plurality of service providers with the same corrected score and the same sample number in parallel, wherein the ranking of the parallel comparison indexes is as follows: the minimum value of the rank of the selectable comparison indicator corresponding to the revised score.

7. The apparatus for assessing a service score of a service provider of claim 6, wherein the index rank ratio conversion unit is further configured to:

the ranking rate X of the comparative indexes of the service provider in the industry category is calculated by adopting the following formula₂：

Wherein the content of the first and second substances,

8. The apparatus for assessing a service score of a service provider of claim 7, wherein the score distribution projection unit is further configured to:

projecting the ranking rate of the service provider in the comparison index of the industry category to be a bell-shaped distribution curve-logic curve inverse function X₃：

9. The apparatus for assessing a service score of a service provider of claim 8, wherein the score distribution modification unit is further configured to:

determining a one-way indicator score X for the service provider via the following formula₄：

10. The apparatus for assessing a service score of a service provider of claim 2, wherein the composite index layer comprises:

the substantive factor analysis unit is configured to analyze representative substantive factors which correspond to different business scenes and are not related to each other from the service indexes of the service provider based on a dimension reduction analysis method;

the single index weighting unit is configured to determine a weighted average value of the single indexes of the service providers based on the single index scores of the service providers corresponding to the substantial factors and predetermined single index weights;

a substantive factor scoring unit configured to determine a weighted average of the individual indicators of the service provider as a score of the substantive factor of the service provider.

11. The apparatus for assessing a service score of a service provider according to any one of claims 2 or 10, wherein the output layer comprises:

a substantive factor weighting unit configured to determine a weighted average value of the substantive factors of the service provider based on the scores of the substantive factors of the service provider and preset weights of the substantive factors of various industry categories;

a dynamic score determining unit configured to determine a weighted average of the substantive factors of the service provider as a service dynamic score of the service provider.

12. The apparatus for assessing a service score of a service provider of claim 1, wherein the commitment score of the service provider is determined based on whether the service provider opens a service commitment via:

an provisioning data acquisition unit configured to acquire a number of commitments provisioned by a service provider;

a commitment score determining unit configured to determine a commitment score based on a number of commitments opened by the service provider, a preset commitment number threshold.

13. The apparatus for assessing a service score of a service provider of claim 12, wherein the commitment score determination unit is further configured to:

determining the ratio of the number of the commissions opened by the service provider to a preset committed number threshold as a committed coefficient;

and determining the product of the commitment coefficient and a preset information entropy control coefficient as a commitment score.

14. An apparatus for assessing a service provider's service score as claimed in claim 1, wherein the service provider's service adaptation score is determined based on service provider's adaptation data to platform's service and operational metrics via:

a factor coefficient determination unit configured to determine an acceleration factor coefficient of a service provider based on a preset acceleration factor calculation rule for a preset service adaptation factor;

the total coefficient determining unit is configured to determine an accelerator total coefficient based on a preset acceleration factor weight and an acceleration factor coefficient of each service adaptation factor of the service provider;

and the adaptive score determining unit is configured to determine a service adaptive score of the service provider based on the total accelerator coefficient and the service dynamic score of the service provider.

15. The apparatus for assessing a service score of a service provider of claim 1, wherein the service indicator comprises: the system comprises commodity quality satisfaction, commodity description conformity, service attitude satisfaction, logistics speed satisfaction, inquiry average response time, response rate in inquiry preset time, condition acquisition timeliness rate in preset time, delivery order occupation ratio in preset time, returned goods repair rate, after-sale service time, returned goods processing satisfaction, transaction dispute rate, dispute autonomous completion rate and dispute processing compliance rate.

16. The apparatus for assessing a service score of a service provider of claim 2, wherein the single indicator score comprises: the system comprises a commodity quality satisfaction degree score, a commodity description conformity degree score, a service attitude satisfaction degree score, a logistics speed satisfaction degree score, a query average response time length score, a response rate score within a query preset time length, a component collecting and time rate score within a preset time length, a delivery order proportion score within a preset time length, a return and exchange repair rate score, an after-sale service time length score, a return and exchange processing satisfaction degree score and a commodity dispute processing rate score.

17. An apparatus for assessing a service score of a service provider as recited in claim 10, wherein the determining representative and uncorrelated substantial factors corresponding to different business scenarios from the service metrics of the service provider based on a dimension reduction analysis method comprises:

based on a dimension reduction analysis method, determining the following representative and unrelated essential factors corresponding to different service scenes:

determining an evaluation factor from the commodity quality satisfaction degree, the commodity description compliance degree, the service attitude satisfaction degree and the logistics speed satisfaction degree of the service provider;

determining a consultation factor from the average response time length of the inquiry of the service provider and the response rate within the preset inquiry time length;

determining logistics factors from the acquisition of a piece timeliness rate within a preset time length and a delivery order proportion within a preset time length of the service provider;

determining an after-sale factor from the return repair rate, the after-sale service duration and the return processing satisfaction of the service provider;

and determining a dispute factor from the transaction dispute rate, the dispute autonomous completion rate and the dispute handling time-following rate of the service provider.

18. The apparatus for assessing a service score of a service provider according to any one of claims 10 or 17, wherein the dimension reduction analysis comprises one or more of: principal component analysis, factor analysis, and analytic hierarchy process.

19. The apparatus for assessing a service score of a service provider of claim 14, wherein the business adaptation factor comprises: a commitment factor, a short video factor, an electronic invoice factor, a QCR factor, a repeat shop factor, and a store age factor.

20. The means for assessing a service provider's service score according to any one of claims 1-19, wherein the means for assessing a service provider's service score further comprises:

a user information pushing component configured to push information to a user and/or a service provider based on a service score of the service provider.

21. The apparatus for assessing a service score of a service provider of claim 20, wherein the user information push component is further configured to perform at least one of:

in response to the service score of the service provider being lower than a threshold value, filtering out account and/or service information of the service provider with the service score lower than the threshold value from the information pushed to the user; and

and responding to the condition that the service score of the service provider is lower than the threshold value, generating reminding information, and sending the reminding information to the service provider with the service score lower than the threshold value.

22. An electronic device/terminal/server comprising: one or more processors; storage means for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a service score calculation component as claimed in any one of claims 1-21; and the service score output component is used for outputting the service score of the service provider calculated by the service score calculation component.

23. A computer-readable storage medium, having stored thereon a computer program which, when executed by one or more processors, implements a service score calculation component as claimed in any one of claims 1-21.