TWM619067U - Business evaluation system - Google Patents

Abstract

The disclosure provides a business evaluation system. The business evaluation system includes a server, an input interface, a business evaluation computer. The server stores a plurality of evaluation factors, the evaluation factors are respectively corresponds to a plurality of weight values. The input interface communication connect to the server, and the input interface is configured to receive a plurality pieces of operation data, the pieces of operation data respectively correspond to the evaluation factors. The business evaluation computer communication connect to the server, the business evaluation computer stores a machine learning module. The machine learning module calculates the score of the business evaluation project according to the pieces of operation data and the weight values corresponding to the evaluation factors.

Description

Business evaluation system

The content of this case is about a business evaluation system, especially a business evaluation system with machine learning.

When a financial institution launches a new type of business or service, if it can accurately assess the type and timing of the launch of the business, it will promote the operation and management of the financial institution and increase its business. How to provide the best business category and time point is an important issue in this field.

This disclosure document provides a business evaluation system. The business evaluation system includes a server, an input interface, and a business evaluation host. The server stores a plurality of evaluation factors of the business evaluation item, and the evaluation factors respectively correspond to a plurality of weights. The input interface is connected to the server for communication, and the input interface is used to receive a plurality of operating data, and the operating data respectively correspond to some evaluation factors. The business evaluation host is communicatively connected to the server. The business evaluation host stores a machine learning model. The machine learning model calculates the business evaluation item based on the pieces of operation data corresponding to the evaluation factors and the weights corresponding to the evaluation factors Score, and this type of machine learning The model is further used to calculate the first rate of change based on one of the pieces of operation data and one piece of historical operation data corresponding to one of the evaluation factors, and calculate the second rate of change based on the score and the historical score, the machine The learning model adjusts the weights according to the difference between the first rate of change and the second rate of change.

In summary, the business evaluation system of this disclosure document can calculate the scores of credible business evaluation items, which can be used as business management as the direction of future profit strategy and layout of bank branches.

To enable the above and other purposes, features, advantages and implementation of this disclosure The examples can be more obvious and easy to understand, and the explanation of the attached symbols is as follows:

100: Business Evaluation System

110: Business Evaluation Host

112: processor

114: Internal memory

114a: machine learning model

116: External memory

120: input interface

130: server

S: Electronic device

S100: Business Evaluation Method

S110, S120, S130, S132, S134, S136, S137, S138, S140, S150, S160, S170, S180, S182, S184: steps

In order to make the above and other objectives, features, advantages and embodiments of the present disclosure more comprehensible, the description of the accompanying drawings is as follows: Figure 1 is a business evaluation system according to an embodiment of the present disclosure.

Figure 2 is a flowchart of a business evaluation method according to an embodiment of the present disclosure.

FIG. 3 is a flowchart of step S130 in the service evaluation method of FIG. 2 according to an embodiment of the present disclosure.

Figure 4 is a flowchart of a business evaluation method according to an embodiment of the present disclosure.

Figure 5 is a flowchart of a business evaluation method according to an embodiment of the present disclosure.

The following is a detailed description of the embodiments in conjunction with the accompanying drawings to better understand the aspect of the case, but the embodiments provided are not used to limit the scope of the case, and the description of the structure operation is not used to limit it. Smooth execution Foreword, any device with equal function produced by the recombination of components is the scope of this project.

In addition, the terms "include", "include", "have", "contain", etc. used in this article are all open terms, meaning "including but not limited to". In addition, the "and/or" used in this article includes any one of one or more of the related listed items and all combinations thereof.

Please refer to Figure 1. Figure 1 is a business evaluation system 100 according to an embodiment of the present disclosure. As shown in FIG. 1, the business evaluation system 100 includes an input interface 120 of a business evaluation host 110 and a server 130. The server 130 stores multiple business items. Business items can be adjusted according to the type of financial institution to be assessed. For example, the business project takes the enterprise credit granting as an example. The analysis and evaluation of enterprise financial credit can include multiple analysis categories. For example, the analytical categories of enterprise financial credit include overall business execution status, business customer financing status, and operation management status. Each analysis category can include multiple evaluation factors. For example, the overall business execution situation includes five evaluation factors, which are the average total financing balance, the average total amount, the average total number of households, the average total revenue, and the percentage of total revenue in the whole bank. Ratio, but not limited to this. Different evaluation factors have corresponding weights. The sum of the weights of all evaluation factors of the same analysis category is the weight of the analysis category. The dissimilarity analysis category can have dissimilarity weights. The sum of the weights of all analysis categories can be 100%. The above weights can be stored on the server.

The input interface 120 communicates with the business evaluation host 110 through a wired or wireless network, and the electronic device S and the input interface 120 can communicate with the business Evaluate the communication connection of the host 110. The electronic device S can be implemented by a personal computer, a mobile communication device or a tablet computer. The user can input the operating data associated with the business item to the business evaluation host 110 through the electronic device S and the input interface 120.

The business evaluation host 110 includes a processor 112, an internal memory 114 and an external memory 116. The internal memory 114 is used to store the machine learning model 114a, and the external memory 116 is used to store operating data. The machine learning model 114a includes neural network, mind-body language programming, fuzzy logic model, hidden Markov model, decision tree, Bayesian algorithm, conditional random domain or support vector machine.

The processor 112 is electrically coupled to the internal memory 114 and the external memory 116. The processor 112 communicates with the input interface 120 and the server 130 via a wired or wireless network.

Please also refer to FIG. 2. FIG. 2 is a flowchart of a business evaluation method S100 for implementing profit according to the present disclosure. The service evaluation method S100 includes steps S110 to S130. In step S110, a plurality of operation data is received through the input interface, and the operation data respectively correspond to a plurality of evaluation factors. In step S120, a plurality of weights corresponding to the evaluation factors are obtained by the business evaluation host. In step S130, the business evaluation host executes the machine learning model to adjust the weights, and calculates the adjustment score of the business evaluation item according to the adjusted weights.

In order to better understand this disclosure document, please refer to the following table 1 together. In step S110, a plurality of operating data D1 to D5 are received through the input interface 120, and the operating data D1 to D5 respectively correspond to a plurality of evaluations. Factors F11~F15. In some embodiments, the input interface 120 also receives a plurality of operating data D6 to D10, and the operating data D6 to D10 also correspond to a plurality of evaluation factors F11 to F15, respectively. In other embodiments, the operating data D6 to D10 are already stored in the external memory 116, and the processor 112 can retrieve the operating data D6 to D10 from the external memory 116. In addition, in step S120, the business evaluation host 110 obtains a plurality of weights corresponding to the evaluation factors F11 to F15, respectively.

As shown in Table 1, the evaluation factors F11~F15 covered by the overall business execution are the average total financing balance, average total amount, average total number of households, average total income, and the proportion of total income to the whole bank.

In some embodiments, the average total financing balance (assessment factor F11) represents the ratio of the total financing balance of the month to be evaluated (for example, the current month) to the average total financing balance of the past five years. Average total amount (assessment factor F12) representative It is the ratio of the total amount of the month to be evaluated (for example, the current month) to the average total amount of the past five years. The average total number of households (assessment factor F13) represents the ratio of the total number of households in the month to be assessed (for example, the current month) to the average total number of households in the past five years. The average total return (evaluation factor F14) represents the ratio of the total return in the month to be evaluated (for example, the current month) to the average total return in the past five years. The proportion of total income to the whole bank (assessment factor F15) represents the proportion of the total income of the whole bank in the month to be evaluated (for example, the current month) to the average total income of the past five years.

It should be noted that the operating data D1~D5 are the data of the month to be evaluated (for example, the current month). The operating data D6~D10 can be the numerical average of the multi-year data in the same month as the operating data D1~D5. In some embodiments, the operating data D6 to D10 may be the numerical average of the data in the last five years in the same month as the operating data D1 to D5. For example, the operating data D1~D5 are the operating data of January 2008, and the operating data D6~D10 are the operating data of January 104, January 105, January 106, January 107, and January 108. The numerical average of the data.

In some embodiments, the evaluation factors F11 to F15 each have a weight of 4%. The overall business execution of one of the three major categories of business evaluation items adds up to the respective weights of the evaluation factors F11 to F15, and the overall business execution situation will have a weight of 20%. the weight of.

In step S120, the business evaluation host 110 obtains multiple weights corresponding to the evaluation factors F11 to F15, respectively. For example, the business evaluation host 110 obtains multiple weights corresponding to the evaluation factors F11 to F15 from the server 130. For example, the multiple weights of the evaluation factors F11 to F15 are all 4%, as shown in Table 1.

In step S130, the business evaluation host 110 executes the machine learning model 114a to adjust the weight, and calculates the adjustment score of the business evaluation item according to the adjusted weight.

In order to better understand step S130, please refer to Fig. 3 together. FIG. 3 is a flowchart of step S130 in the service evaluation method of FIG. 2 according to an embodiment of the present disclosure. Step S130 includes steps S132 to S138. In step S132, the score of the business evaluation item is calculated according to the operation data and the weights by the machine learning model. In step S134, a machine learning model is used to calculate a first rate of change based on one of the pieces of operation data and a piece of historical operation data, and a second rate of change is calculated based on the score of the business evaluation item and a historical score. In step S134, it is determined whether the difference between the first rate of change and the second rate of change is greater than the expected value. In step S137, the machine learning model is used to adjust the weights with the highest value and the lowest value, so that the difference between the first rate of change and the second rate of change is smaller than the expected value. In step S138, these weights are not adjusted.

In step S132, the score of the business evaluation item is calculated by using the machine learning model according to the operating data D1 to D10 and the weight corresponding to the evaluation factors F11 to F15. Taking the evaluation factor F11 (average total financing balance) as an example, the operating data D1 of the total financing balance in January 2008 is 750,000, and the average operating data D6 of the total financing balance in January of 104 to 108 is 1.56 million. The ratio of the total financing balance in January 2008 to the average total financing balance in January of 104 to 108 is the operating data D1 divided by the operating data D6=75/156=0.4807, and the evaluation factor F11 (average total financing Balance) has a weight of 4%, so the score of the evaluation factor F11 (average total financing balance) in January 108 is 0.4807*4=1.92 points.

To give another example, take the evaluation factor F12 (average total amount) as an example, the operating data D2 of the total amount in January 2008 is 830,000, and the average operating data D7 of the total amount in each year from 104 to 108 in January is 1.14 million . The ratio of the total amount in January 108 to the average total amount in January of each year from 104 to 108 is the operating data D2 divided by the operating data D7=83/114=0.7280, and the evaluation factor F12 (average total amount) has 4% Therefore, the score of F12 (average total amount) in January 108 is 0.7280*4=2.91 points. By analogy, in January 108, the scores of evaluation factor F13 (average total number of households), evaluation factor F14 (average total income), and evaluation factor F15 (proportion of total income to the whole bank) were 3.91 points and 2.56 points in order. And 3.56 points.

It should be noted that when the average proportion of the current month exceeds the set value (for example, 1), the calculation will be performed with the set value (for example, 1).

In this way, when the highest score of the overall business execution situation is 20 points (that is, with a weight of 20%), the machine learning model 114a can calculate the overall business execution situation in January 108 based on the respective scores of the evaluation factors F11~F15 The score is 1.92+2.91+3.91+2.56+3.56=14.86 points.

In some embodiments, the other two categories of business evaluation items, the weights of business customer financing situation and operation management situation can be set at 36% and 44%, respectively. Please refer to Table 2 and Table 3.

As shown in Table 2, in the second largest category, in the financing situation of customers by business, the evaluation factors F21~F26 each have a weight of 6%. The financing situation of customers by business, one of the three major categories of business evaluation items, adds up the evaluation factors. The respective weights of F21~F26 and the financing situation of customers by business will have a weight of 36%. In addition, the operating data D11~D22 also correspond to the evaluation factors F21~F26 respectively. The calculation of the scores of the customer financing situation by business (assessment factors F21-F26) through steps S110-S132 is similar to the method of calculating the overall business execution situation (F11-F15) in steps S110-S132, which will not be repeated here.

In some embodiments, the average time cost of each service (assessment factor F21) represents the time required for the month to be evaluated (for example, the current month) for new customer development or quota application to start the quota approval. In some embodiments, the average time cost of each business (assessment factor F21) can be obtained from the highest time cost value in the past five years of time cost in the evaluation month (for example, the current month), and this value accounts for the average time cost of the past five years The ratio calculation.

In some embodiments, the average revenue of each business (assessment factor F22) represents the ratio of the revenue of the month to be evaluated (for example, the current month) to the average revenue of the past five years. The rate of change in the average number of households for each business (assessment factor F23) represents the rate of change in the number of households in the month to be evaluated (for example, the current month) as a percentage of the rate of change in the average number of households in the past five years. The change rate of the average quota of each business (assessment factor F24) represents the ratio of the change rate of the quota of the month to be evaluated (for example, the current month) to the average change rate of the quota in the past five years. The average amount allocated for each business (assessment factor F25) represents the ratio of the amount allocated for the month to be evaluated (for example, the current month) to the average amount allocated for the past five years. The average financing balance of each business (assessment factor F26) represents the ratio of the financing balance of the month to be evaluated (for example, the current month) to the average financing balance of the past five years.

Please refer to Table 2. The scores of the evaluation factors F21~F26 are 4.35 points, 5.35 points, 6 points, 4.47 points, 6 points and 6 points in order.

In this way, when the highest score for financing by business customers is 36 points (that is, with a weight of 36%), the machine learning model 114a can calculate the business customers in January 108 based on the respective scores of the evaluation factors F21~F26 The score for financing is 4.35+5.35+6+4.47+6+6=32.17 points.

As shown in Table 3, in the third category, in the operation and management situation, the evaluation factors F31~F34 each have a weight of 11%, and the financing situation of business customers in one of the three major categories of business evaluation items totals the evaluation factors F31~ The respective weights of F34 will have a weight of 44%. In addition, the operating data D23~D30 also correspond to the evaluation factors F31~F34, respectively. By step S110~S132 calculate the score of the operation management situation (assessment factors F31~F34) is similar to the way of calculating the overall business execution situation (F11~F15) in steps S110~S132, and will not be repeated here.

In some embodiments, the average risk main rating of each capital amount (assessment factor F31) represents the ratio of the risk main rating of the assessment month (for example, the current month) to the average risk main rating of the past five years. The average number of households with each capital (assessment factor F32) represents the ratio of the number of households in the month of assessment (for example, the current month) to the average number of households in the past five years. The average amount of capital for existing customer maintenance status/new customer development effectiveness quantitative self-rating (evaluation factor F33) represents the evaluation month (for example, the current month) existing customer (new customer) maintenance situation (development effectiveness) quantitative self-rating accounted for the past The five-year average existing customer (new customer) maintenance situation (development effectiveness) quantitative self-rating. The average future operation forecast self-score of each capital amount (assessment factor F34) represents the ratio of the self-score of the future operation forecast in the evaluation month (for example, the current month) to the average self-score of the future operation forecast in the past five years.

Please refer to Table 3. The scores of evaluation factors F31~F34 are 9.27 points, 8.45 points, 6.82 points and 7.30 points in order.

In this way, when the highest score for the operation and management situation is 44 points (that is, with a weight of 44%), the machine learning model 114a can calculate that the score for the operation and management situation in January 2008 is 9.27+8.45+6.82+7.30=31.84 point.

Therefore, the machine learning model 114a can calculate all evaluation factors covered by the overall business execution situation, business customer financing situation, and operation management situation in the business evaluation project of the month to be evaluated The sum of F11~F15, F21~F26 and F31~F34 is equal to 14.86+32.17+31.84=78.87 points.

In some embodiments, the machine learning model 114a can compare the score of the business item of the month to be evaluated (for example, 78.87 points) with the score of the business item of the month in the past five years to determine/evaluate the financial institution to be evaluated. Operating conditions in the same month of the current year and recent years.

Please refer to Figure 3 again. In step S134, the machine learning model 114a is used to calculate a piece of operating data D4 and a piece of historical operating data corresponding to the evaluation factor F14 (average total revenue) among the pieces of operating data D1-30. The first rate of change, and the second rate of change is calculated based on the score of the business evaluation item and a historical score.

The formula of the first rate of change is: (the score of the evaluation factor F14 of the current month-the score of the evaluation factor F14 of the previous month)/the score of the evaluation factor F14 of the previous month. In some embodiments, the score of the evaluation factor F14 last month may be stored in the server 130 or the external memory 116, and the processor 112 may retrieve the score of the evaluation factor F14 last month from the server 130 or the external memory 116, and execute the machine Learning model 114a. Moreover, since in step S132, the machine learning model 114a can calculate the score of the evaluation factor F14 of the current month from the operating data D4 and D9 corresponding to the evaluation item F14, and the first rate of change can be calculated. In some embodiments, the score of the evaluation factor F14 in the last month can be calculated from historical operation data, which can be the operation data corresponding to the evaluation factor F14 in the month before the month to be evaluated. For example, if the month to be evaluated is January, 108, the historical operating data may be the operating data of December 107 and corresponding to the evaluation factor F14. According to the calendar The method of calculating the evaluation factor F14 of the previous month by the historical operating data is similar to the aforementioned steps S110 to S132, and will not be repeated here. Because the score of the assessment factor F14 of the current month is calculated based on the operating data D4 corresponding to the assessment factor F14. In this way, the first rate of change can be calculated based on the operating data D4 corresponding to the evaluation factor F14 and the historical operating data.

In some embodiments, the formula of the second rate of change is: (average of scores of business evaluation items in the current month-average of scores of business evaluation items of the previous month)/average scores of business evaluation items of the previous month. The average score of the business evaluation item of the current month may be the average of the scores of the business evaluation items of the month to be evaluated over many years, for example, the average of the scores of the business evaluation items in January of each year from 104 to 108. In addition, the average score of the business evaluation item in the previous month may be the average score of the business evaluation item in the month prior to the month to be evaluated over many years, for example, the average of the business evaluation item scores in December of each year from 103 to 107. In other words, the average score of the business evaluation item in the previous month may be the average of the historical scores of the business evaluation item in the month to be evaluated in the calendar year.

In some other embodiments, the formula of the second rate of change is: (score of the business evaluation item of the current month-score of the business evaluation item of the previous month)/score of the business evaluation item of the previous month. The score of the business evaluation item of the previous month can be the score of the business evaluation item of the month before the month to be evaluated. For example, the month to be evaluated is January 108, the score of the business evaluation item of the current month is the score of January 108, and the business evaluation item of the previous month The score of the evaluation item is the score of the business evaluation item in December 2007. In other words, the score of the business evaluation item in the previous month may be the historical score of the month to be evaluated for the business evaluation item in the previous year. Since the score of the business evaluation item in the month to be evaluated (for example, the current month) is in the previous step The calculation method has been explained in detail in S110~S132. In this way, the second rate of change can be calculated based on the score of the business evaluation item of the current month and the score of the business evaluation item of the previous month.

In some embodiments, the average of the scores of the business evaluation items in the previous month and the scores of the business evaluation items of the month to be evaluated in the current year can also be stored in the server 130 or the external memory 116, and the processor 112 can be from the server 130 or external The memory 116 extracts the average scores of the business evaluation items of the previous month and the scores of the business evaluation items of the month to be evaluated in a non-current year, and executes the machine learning model 114a. Moreover, since in step S132, the machine learning model 114a can calculate the scores of the business evaluation items from the operating data D1~D30, in line with the average of the scores of the business evaluation items in the previous month and the business evaluation items of the month to be evaluated in the current year Score, you can calculate the second rate of change.

In step S136, it is determined whether the difference between the first rate of change and the second rate of change is greater than the expected value. In some embodiments, the expected value can be set at 5%.

In some embodiments, if the difference between the first rate of change and the second rate of change is greater than the expected value, step S137 is performed, and the machine learning model 114a preferentially adjusts the highest value and the lowest value of the aforementioned weights, so that the first The difference between the rate of change and the second rate of change is smaller than the expected value. Then, step S132 is performed, and the adjustment score of the business evaluation item is calculated by the machine learning model 114a according to the pieces of operation data D1 to D30 and the adjusted weights. And following steps S134~S136, it can be verified whether the difference between the first rate of change and the second rate of change is less than the expected value, so as to obtain business evaluation items A credible adjustment score for the month to be evaluated. In this way, the machine learning model 114a in the business evaluation system 100 adjusts the weights according to the first rate of change and the second rate of change, and can more accurately calculate and evaluate the scores of the business evaluation items in the month to be evaluated to correctly determine the best branch. Timing of business promotion. Specifically, through steps S110 to S130, multiple scores of the business evaluation item in each month can be calculated, and the highest of the multiple scores of the business evaluation item in each month can be used as the best business promotion opportunity for the branch.

In other embodiments, if the difference between the first rate of change and the second rate of change is greater than the expected value, the machine learning model 114a is based on the scores of the various evaluation factors F11~F15, F21~F26, and F31~F34 of each business evaluation item The highest one and the lowest one adjust the weights of the two evaluation factors.

If the difference between the first rate of change and the second rate of change is less than or equal to the expected value, proceed to step S138 without adjusting the weights.

Please refer to FIG. 4, which is a flowchart of a service evaluation method S100 according to an embodiment of the present disclosure. As shown in Figure 4, the service evaluation method S100 further includes steps S140 to S160. In step S140, a plurality of operation sub-data of each of the plurality of business types is received through the input interface, and the operation sub-data respectively corresponds to a part of the plurality of evaluation factors. In step S150, a machine learning model is used to calculate the scores of the business types according to the respective operation sub-data of the business types and the corresponding weights. In step S160, the machine learning model is used to determine the best of the business types according to the scores of the business types.

In step S140, a plurality of operation sub-data of each of the plurality of business types are received through the input interface 120, and the operation data respectively correspond to a part of the plurality of evaluation factors. Please refer to Table 4 below.

As shown in Table 4, business type A can be financing with a capital of less than 1 million. Business type B can provide financing ranging from RMB 1.01 to RMB 5 million. Business type C can provide financing ranging from RMB 5.01 to RMB 30 million. Business type D can provide financing ranging from RMB 30.01 million to RMB 100 million. Business type E can provide financing of more than 100 million yuan.

In step S150, the machine learning model 114a calculates the scores of the business types A to E according to the respective operating sub-data of the business types A to E and the corresponding weights. Take business type A (financing below 1 million) as an example. In January 108, the operating sub-data of business type A corresponding to the evaluation factor F21 (average time cost) is 83 hours, which corresponds to the evaluation factor F21 (average time) Cost) business type A~E of the operating sub-data combination It's 508 hours. The proportion of business type A corresponding to the evaluation factor F21 (average time cost) in business types A to E is 83 hours divided by 508 hours = 0.16. The proportion of the business type A corresponding to the evaluation factor F21 in the business types A to E multiplied by the score of the evaluation factor F21 is the score of the business type A in the evaluation factor F21 (ie, 0.16*4.35=0.71 points). Among all the evaluation factors F21~F26 in the financing situation of customers by business, the score of business type A is 0.71+0.95+6.32+0.84+0.69+0.93=10.44. The calculation method of business types B to E is similar to that of business type A, so I won't repeat them here.

In this way, the scores of all evaluation factors F21~F26 and business types A~E in the financing situation of different business customers are 10.44 points, 0.28 points, 15.14 points, 2.59 points, and 3.72 points in order.

In step S160, the machine learning model 114a is used to determine the best of the business types A to E according to the scores of the business types. For example, the respective scores of business types A to E are 10.44 points, 0.28 points, 15.14 points, 2.59 points, and 3.72 points in order. The machine learning model 114a can determine the business type C with the highest score among the business types A to E. The best of January 108.

In other embodiments, the machine learning model 114a aims at all the evaluation factors F21~F26 of the financing situation of customers by business, and compares the evaluation factors F14 (average total return) and F14 (average total revenue) of the overall business execution situation according to each business type A~E. The evaluation factor F15 (the proportion of total revenue to the whole bank), and the evaluation factor F34 (average future operation forecast self-scoring) of the operation management situation, The person with the highest total score is the analysis result of the predicted best profit strategy and layout in the major category of the business evaluation project (customer financing situation by business).

FIG. 5 is a flowchart of a service evaluation method S100 according to an embodiment of the present disclosure. The service evaluation method S100 further includes steps S170, S180, S182, and S184. In step S170, the machine learning model 114a is used to calculate a third rate of change based on one of the operating sub-data and a piece of historical operating sub-data of the best of the business types A to E.

The formula for the third rate of change is: (score of business type N in the current month-score of business type N in the previous month)/score of business type N in the previous month, where business type N can be the aforementioned business types A to E. In some embodiments, the score of business type N in the previous month may be stored in the server 130 or the external memory 116, and the processor 112 may retrieve the score of the business type N in the previous month from the server 130 or the external memory 116, and execute the machine Learning model 114a. Moreover, since in step S132, the machine learning model 114a can calculate the score of the evaluation factor F14 of the current month from the operating sub-data corresponding to the evaluation items F21 to F26, and the third rate of change can be calculated. In some embodiments, the score of the business type N in the previous month may be calculated from the historical operation sub-data. In some embodiments, depending on the number of evaluation items F21 to F26, the historical operation sub-data may be one or more items. The historical operation sub-data may be the operation sub-data of the business type N one month before the month to be evaluated. For example, if the month to be evaluated is January 108, the historical operation sub-data may be the operating sub-data of December 107. The method of calculating the historical operating sub-data is similar to the aforementioned steps S110 to S132, and will not be repeated here.

In step S180, the machine learning model 114a determines whether the difference between the first rate of change and the third rate of change is greater than the expected value. In some embodiments, the expected value can be set at 5%.

In some embodiments, if the difference between the first rate of change and the third rate of change is greater than the expected value, proceed to step S182 by using the machine learning model 114a to adjust the weights with the highest value and the lowest value in priority to make the first The difference between the rate of change and the third rate of change is smaller than the expected value. Then, step S132 is performed, and the adjustment score of the business evaluation item is calculated by the machine learning model 114a according to the pieces of operation data D1 to D30 and the adjusted weights.

In other embodiments, if the difference between the first rate of change and the third rate of change is greater than the expected value, the machine learning model 114a is based on the scores of each evaluation factor F11~F15, F21~F26, and F31~F34 of each business evaluation item The highest one and the lowest one adjust the weights of the two evaluation factors.

And following steps S134 to S136, it can be verified whether the difference between the first rate of change and the second rate of change is less than the expected value, so as to obtain a more accurate and credible adjustment score for the business evaluation item.

If the difference between the first rate of change and the third rate of change is less than or equal to the expected value, proceed to step S184 without adjusting the weights.

In summary, by adjusting the weight of the machine learning model 114a in the business evaluation system 100 according to the first rate of change and the second rate of change, it is possible to more accurately calculate and evaluate the score of the business evaluation item in the month to be evaluated to determine the branch The best time for the organization to promote its business. And the machine learning model 114a in the business evaluation system 100 can calculate the results of the business types A~E. The highest score is the analysis result of the best profit strategy and layout of the bank branch. Furthermore, the best business promotion time of the branch can be based on the highest average score in each month of the business evaluation item, and the best business promotion type of the branch can be based on the highest score of each business type. In this way, the machine learning model 114a in the business evaluation system 100 calculates the scores of credible business evaluation items and the respective scores of business types A~E, which can be combined into business management as the direction of future profit strategy and layout of bank branches .

Although this case has been disclosed in the above implementation mode, it is not limited to this case. Anyone who is familiar with this technique can make various changes and modifications without departing from the spirit and scope of this case. Therefore, the scope of protection of this case should be attached hereafter. Those defined in the scope of the patent application shall prevail.

100: Business Evaluation System

110: Business Evaluation Host

112: processor

114: Internal memory

114a: machine learning model

116: External memory

120: input interface

130: server

S: Electronic device

Claims (6)

A business evaluation system includes: a server storing a plurality of evaluation factors of a business evaluation item, wherein the evaluation factors respectively correspond to a plurality of weights; an input interface, which is communicatively connected to the server, and the input interface is used for receiving A plurality of operating data, wherein the operating data correspond to the evaluation factors; and a business evaluation host, which is communicatively connected to the server. The business evaluation host stores a machine learning model, and the machine learning model corresponds to the The operating data of the evaluation factors and the weights corresponding to the evaluation factors are used to calculate a score of the business evaluation item, and the machine learning model of this type is used to calculate a score corresponding to one of the evaluation factors. A piece of operation data and a piece of historical operation data among the pieces of operation data calculate a first rate of change and calculate a second rate of change based on the score and a historical score. The machine learning model is based on the first rate of change and the second rate of change A difference adjusts these weights. The business evaluation system according to claim 1, wherein: when the difference between the first rate of change and the second rate of change is less than the expected value, the weights are not adjusted; and when the first rate of change is greater than the When the difference between the second rate of change is greater than an expected value, the machine learning model adjusts the values of the weights so that the difference between the first rate of change and the second rate of change is smaller than the expected value, and the machine learning model is based on The adjusted weights are calculated for the business evaluation project 1. Adjust the score. The business evaluation system according to claim 2, wherein the machine learning model preferentially adjusts the highest value and the lowest value of the weights, so that the difference between the first rate of change and the second rate of change is smaller than the expectation value. The business evaluation system according to claim 1, wherein the input interface is further used to receive a plurality of operation sub-data of each of a plurality of business types, and the operation sub-data of one of the business types respectively correspond to the A part of the evaluation factors, wherein the machine learning model calculates the plural number of the business types based on one of the weights corresponding to the part of the evaluation factors and the respective operating sub-data of the business types According to the scores of the business types, the best one of the business types is judged. The business evaluation system according to claim 4, wherein the machine learning model is further used to calculate a third rate of change based on one of the operating data of the best business type and a piece of historical operating sub-data , The machine learning model judges whether a difference between the first rate of change and the third rate of change is greater than the expected value. The business evaluation system according to claim 5, wherein: when the difference between the first rate of change and the third rate of change is less than the expected Value, the weights are not adjusted; and when the difference between the first rate of change and the third rate of change is greater than the expected value, the machine learning model adjusts the values of the weights to make the first rate of change and the first rate of change 3. The difference of the rate of change is smaller than the expected value, and the machine learning model calculates an adjustment score of the business evaluation item according to the adjusted weights.

Images