A network-based scoring training method

Abstract

The present invention relates to a network-based scoring training method, a central server, and a terminal. The method includes: after the terminal of the person to be scored accesses the network, sending registration information to the central server; according to the registration information sent by the terminal, the central server sends a scoring model and set conditions to the terminal; after the person to be scored completes a task each time, the terminal obtains the current geographical location; after the scorer finishes scoring the person to be scored, the central server sends the score of the scorer to the terminal of the corresponding person to be scored; the terminal calculates the final score of the person to be scored using the scoring model according to the geographical location, the previous scores of the person to be scored, and the set conditions, and sends the final score to the central server.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of scoring training, and in particular, to a network-based scoring training method. Background Art

[0002] In the field of food delivery, food delivery platforms usually score food delivery workers based on user ratings. When scoring, a food delivery rating monitoring model is usually used. The food delivery rating monitoring model is a calibration of the scores after customers rate food delivery workers, taking into account geographical location, weather, and other objective factors, to avoid overly low scores due to objective factors and to normalize the scores of all food delivery workers on the entire platform for easy unified assessment.

[0003] Generally, the headquarters of a food delivery platform will establish a central platform. When training the food delivery rating monitoring model, all data is stored in the central platform for unified training and analysis. However, the usual training and analysis do not distinguish between differences in local living habits and weather conditions in different regions. At the same time, if all data is uploaded to the central platform for processing, this will cause the data to be overly concentrated in the central platform, and the amount of data to be processed is large, resulting in a large investment in both hardware and software for the central platform. In addition, the terminals upload data in real time, which results in a huge amount of data being transmitted, but the storage and computing resources of the Internet of Things terminals are not fully utilized. Summary of the Invention

[0004] The object of the present invention is to reduce the dependence on the central server, make full use of the IT resources of the terminals, and share part of the storage, analysis, and training work of the central server. In addition, based on 5G network technology combined with regional computing capabilities, the requirements of low latency and high speed can be well met, and the accuracy of scoring can be improved.

[0005] According to one aspect of the embodiments of the present invention, an embodiment of the present invention provides a network-based scoring training method, the method comprising:

[0006] After the terminal of the person to be scored accesses the network, it sends registration information to the central server;

[0007] According to the registration information sent by the terminal, the central server sends a scoring model and set conditions to the terminal;

[0008] After each task completed by the person to be scored, the terminal obtains the current geographical location;

[0009] After the scorer completes scoring the person to be scored, the central server sends the score of the scorer to the terminal of the corresponding person to be scored;

[0010] The terminal calculates the final score of the scored person according to the geographical location, the previous scores of the scored person, and the set conditions, and sends the final score to the central server.

[0011] In some embodiments, the central processor ranks all the scored persons according to the scores of all the scored persons received.

[0012] In some embodiments, the set conditions sent by the central server to the terminal are weather conditions and / or time. After the scored person completes the task, the terminal will obtain the current weather conditions and / or the current time.

[0013] According to another aspect of the embodiments of the present invention, embodiments of the present invention provide a central server, characterized in that the central server includes:

[0014] A receiving module, configured to receive the registration information sent by the terminal of the scored person;

[0015] A processing module, configured to determine the scoring model of the terminal according to the registration information sent by the terminal;

[0016] A sending module, configured to send the scoring model and set conditions to the terminal;

[0017] Wherein, the receiving module is further configured to receive the scores of the scored person by the scorer, and the sending module is further configured to send the scores of the scorer to the terminal, and

[0018] The receiving module is further configured to receive the final score sent by the terminal.

[0019] In some embodiments, the processing module is further configured to rank all the scored persons according to the scores of all the scored persons received by the receiving module.

[0020] According to another aspect of the embodiments of the present invention, embodiments of the present invention provide a terminal of a scored person, characterized in that the terminal includes:

[0021] A sending module, configured to send registration information to the central server;

[0022] A receiving module, configured to receive the scoring model and set conditions sent by the central server;

[0023] A processing module, configured to obtain the current geographical location after the scored person completes the task;

[0024] Wherein, the receiving module is further configured to receive the scores of the scored person by the scorer,

[0025] The processing module is further configured to calculate the final score of the person being scored according to the geographical location, the previous scores of the person being scored, and the set conditions, using a scoring model, and

[0026] The sending module is further configured to send the final score to the central server.

[0027] In some embodiments, according to the set conditions sent by the central server to the terminal, after the person being scored completes the task, the processing module further obtains the current weather condition and / or the current time.

[0028] The beneficial effects of the embodiments of the present invention are as follows: The scoring training method of the present invention uses the IT resources of the terminal of the person being scored to share part of the work of collection, storage, parsing, and training of the central server, creating a distributed scoring monitoring model training platform to ensure the fairness and unified accuracy of scoring, while reducing the investment in the central server. The terminal is responsible for collecting geographical location, current weather condition, and environment for parsing, without having to request the central server for parsing through the network every time. The terminal regularly uploads the adjusted parameters and objective information to the central server. After the central server collects a certain amount of data of the same classification, it uses a deep learning framework for re-training and calculation to obtain a new model, and updates the new model in the terminal. In some embodiments, 5G communication technology is used for data transmission between the central server and the terminal. By using 5G communication technology, the deep learning framework of the terminal (for example, the takeaway APP) makes full use of the hardware of the 5G terminal, making each terminal a lightweight training terminal. The interaction between the terminal and the central server is through a 5G private network, which ensures that the data can be transmitted quickly with low latency. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flowchart of the network-based scoring training method according to an embodiment of the present invention;

[0030] Figure 2 It is a schematic diagram of the central server according to an embodiment of the present invention;

[0031] Figure 3 It is a schematic diagram of the terminal of the person being scored according to an embodiment of the present invention.

[0032] REFERENCE SIGNS:

[0033] 11. Receiving module of the central server, 12. Processing module of the central server, 13. Sending module of the central server, 21. Sending module of the terminal of the person being scored, 22. Processing module of the terminal of the person being scored, 23. Receiving module of the terminal of the person being scored. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] In the following description, specific details such as specific system architectures, interfaces, and technologies are presented for the purpose of illustration rather than limitation, in order to provide a thorough understanding of the present invention. However, those skilled in the art should understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, circuits, and methods are omitted to avoid unnecessary details from obscuring the description of the present invention.

[0035] Embodiments of the present invention provide a network-based scoring training method, a central server, and a terminal.

[0036] According to one aspect of the embodiments of the present invention, embodiments of the present invention provide a network-based scoring training method.

[0037] Please refer to Figure 1 , Figure 1 which is a flowchart of the network-based scoring training method according to the embodiments of the present invention.

[0038] As Figure 1 shown, the method includes:

[0039] S1: After the terminal of the person to be scored accesses the network, it sends registration information to the central server.

[0040] Among them, the terminal can be a mobile device such as a mobile phone, a personal digital assistant (PDA), a tablet computer, a portable device (for example, a portable computer, a pocket computer, or a handheld computer), etc. The person to be scored is, for example, a food delivery person or a courier, etc. Hereinafter, a food delivery person is taken as an example for illustration.

[0041] Among them, the central server can be a device such as a workstation or a computer.

[0042] S2: According to the registration information sent by the terminal, the central server sends a scoring model and set conditions to the terminal.

[0043] Among them, the set conditions are used to screen the persons to be scored with the same set conditions. Without specific instructions, the set conditions are default, that is, no set conditions are set.

[0044] In some embodiments, the set conditions sent by the central server to the terminal are weather conditions and / or time, etc. Specifically, the weather conditions can include normal weather and bad weather. Further, the weather conditions can also include more specific weathers such as sunny days, rainy days, heavy rain days, and snowy days. Time can include idle time and busy time.

[0045] S3: After each task is completed by the person to be scored, the terminal obtains the current geographical location. The current geographical location is the geographical location where the person to be scored performs the task.

[0046] In some embodiments, after the person being rated completes the task, the terminal further obtains information such as the current weather condition and / or the current time according to the set conditions sent by the central server.

[0047] S4: After the rater finishes rating the person being rated, the central server sends the rater's rating to the terminal of the corresponding person being rated.

[0048] S5: The terminal calculates the final rating of the person being rated by using the rating model based on the geographical location, the previous ratings of the person being rated, and the set conditions, and sends the final rating to the central server.

[0049] In some embodiments, the rating model sent by the central server to the terminal may be:

[0050]

[0051] - is the final rating of the current person being rated,

[0052] - C is the total number of all evaluations of all persons being rated within the threshold range centered on the current geographical location under the same set conditions,

[0053] - M is the average rating of all persons being rated within the threshold range centered on the current geographical location under the same set conditions, where C and M are known parameters of the model,

[0054] - n is the number of evaluations of the current person being rated,

[0055] - s is the average value of the evaluation scores of the current person being rated including the score of the current rater.

[0056] For example, if C = 10, M = 8, n = 3, and s = 8.5, then according to the above rating model, Thus, the final rating of the current person being rated is 8.1. In some embodiments, the set condition is selected to be, for example, normal weather. When receiving the evaluation model at the terminal, C represents the total of 5 evaluation numbers under the same weather condition (normal weather) in the area, and the average score is 7.2 points (assuming the scores are 8 points, 7.5 points, 8.5 points, 7 points, and 5 points); the number of evaluations of the delivery person in the area under the same weather condition is 2. If the weather condition is relatively bad this time, resulting in a relatively low score (5 points) from the current customer (rater), this situation is filtered out. The average score of the delivery person's 2 evaluations under normal weather is 6 points (i.e., n = 2, s = 6). The terminal of the delivery person calculates that the score for this time is 6.86 points, that is, the calibrated score excluding the influence of bad weather is 6.86 points.

[0057] In some embodiments, the central server also sends a geographical threshold range to the terminal, such as 1 kilometer, etc., to adjust various data parameters according to requirements. Among them, the threshold can be set based on requirements and experience.

[0058] S6: The central processor ranks all the rated persons according to the ratings of all the rated persons received.

[0059] In some embodiments, data transmission between the central server and the terminal uses 5G communication technology. Based on the 5G private network, the mobile terminal of the deliveryman is used to train the distributed scoring monitoring model, making full use of the computing resources of the terminal to share part of the storage, parsing, and training work of the central platform. Thus, the computing pressure on the central platform is reduced, and based on the 5G network technology combined with regional computing capabilities, the requirements of low latency and high speed can be met, improving the accuracy of scoring.

[0060] According to another aspect of the embodiments of the present invention, embodiments of the present invention provide a central server corresponding to the above method.

[0061] Please refer to Figure 2 , Figure 2 which is a schematic diagram of the central server of the embodiments of the present invention.

[0062] As Figure 2 shown, the central server includes:

[0063] A receiving module 11, configured to receive the registration information sent by the terminal of the rated person, receive the rating of the rated person by the rater, and the final rating sent by the terminal;

[0064] A processing module 12, configured to determine the scoring model of the terminal according to the registration information sent by the terminal;

[0065] A sending module 13, configured to send the scoring model and set conditions to the terminal, and send the rating of the rater to the terminal.

[0066] In some embodiments, the scoring model sent by the central server is the above formula 1.

[0067] In some embodiments, the processing module 2 is further configured to rank all the rated persons according to the ratings of all the rated persons received by the receiving module 11.

[0068] In some embodiments, the processing module 12 of the central server may include specific processing units such as a data acquisition unit, an Internet of Things device management unit, a data training unit, a model management unit, and a data management unit to implement the method described in the present invention.

[0069] In some embodiments, the central server is further configured to send setting conditions such as weather conditions and / or time to the terminal.

[0070] Please refer to Figure 3 , Figure 3 which is a schematic diagram of the terminal of the person to be scored in the embodiment of the present invention.

[0071] As Figure 3 shown, the terminal includes:

[0072] A sending module 21, configured to send registration information to the central server and send the final score to the central server;

[0073] A processing module 22, configured to obtain the current geographical location after the person to be scored completes the task, and calculate the final score of the person to be scored by using a scoring model according to the geographical location, the previous scores of the person to be scored, and the set conditions;

[0074] A receiving module 23, configured to receive the scoring model and the set conditions sent by the central server, and the scores given by the scorers to the person to be scored.

[0075] In some embodiments, the scoring model received by the terminal from the central server is the above formula 1.

[0076] In some embodiments, according to the set conditions sent by the central server to the terminal, after the person to be scored completes the task, the processing module will also obtain the current weather conditions and / or the current time.

[0077] In some embodiments, the processing module 22 of the terminal may include specific processing units such as a model management unit, a data training unit, and a local data collection unit to implement the method described in the present invention.

[0078] The embodiments of the present invention will be further described with specific examples.

[0079] When the network-based scoring training method described in the embodiments of the present invention is used for food delivery, the terminal device of the food delivery person sends registration information to the central server of the food delivery service department through the 5G network. The central server sends the scoring model within the jurisdiction area through the work number sent by the terminal of the food delivery person. After the food delivery person finishes each meal delivery, his terminal will obtain the current geographical location and weather conditions (and time and other information). After the customer's score is completed, the central server sends the customer's score to the terminal of the food delivery person. The terminal calculates the final score by using the scoring model according to the geographical location, weather conditions, and the previous scores of the food delivery person, and sends it to the central server. The scoring monitoring model is:

[0080]

[0081] Among them, C is the total number of evaluations under the same weather condition within the delivery range centered at this geographical location and within the threshold (for example, the threshold is 1 kilometer); M is the average score under the same weather condition within the delivery range centered at this geographical location and within the threshold (for example, the threshold is 1 kilometer); n is the number of evaluations of this food delivery rider. S is the average value of the evaluation scores of this food delivery rider (including the current score). The central platform ranks all the food delivery riders on the platform based on the scores sent by each terminal.

[0082] Thus, the method and product of the embodiment of the present invention achieve the cooperation between the terminal and the central server to train the monitoring model, and disperse the data processing steps during the processing, so that the terminal shares the computing workload of the central server.

[0083] Readers should understand that in the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0084] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0085] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0086] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.

[0087] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0088] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0089] It should also be understood that in each embodiment of the present invention, the magnitudes of the serial numbers of the above-mentioned processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0090] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A network-based scoring training method, characterized in that, The method includes: After the terminal of the person to be scored accesses the network, it sends registration information to the central server; According to the registration information sent by the terminal, the central server sends a scoring model and set conditions to the terminal; After the person to be scored completes a task each time, the terminal obtains the current geographical location; After the scorer finishes scoring the person to be scored, the central server sends the score obtained by the person to be scored to the terminal of the corresponding person to be scored; and The terminal calculates the final score of the person to be scored using the scoring model based on the geographical location, the previous scores of the person to be scored, and the set conditions, and sends the final score to the central server.

2. The method according to claim 1, characterized in that, The scoring model is Among them, is the final score of the current person being scored, C is the total number of all evaluations of all persons to be scored within a threshold range centered on the current geographical location under the same set conditions, M is the average score of all persons to be scored within a threshold range centered on the current geographical location under the same set conditions, n is the number of evaluations of the current person to be scored, s is the average value of the evaluation scores of the current person to be scored including the score given by the current scorer.

3. The method according to claim 1 or 2, characterized in that, The method further includes: The central server ranks all persons to be scored according to the scores of all persons to be scored received.

4. The method according to claim 1 or 2, characterized in that, The set conditions sent by the central server to the terminal are weather conditions and / or time. After the person to be scored completes a task, the terminal obtains the current weather conditions and / or the current time.

5. A central server, characterized in that, The central server includes: A receiving module for receiving the registration information sent by the terminal of the person to be scored; A processing module for determining the scoring model of the terminal according to the registration information sent by the terminal; and A sending module for sending the scoring model and set conditions to the terminal; Wherein, the receiving module is further used for receiving the score of the person to be scored by the scorer, and the sending module is further used for sending the score of the scorer to the terminal, and The receiving module is further used for receiving the final score sent by the terminal.

6. The central server according to claim 5, characterized in that, The scoring model is Among them, is the final score of the current person being scored, C is the total number of all evaluations of all persons to be scored within a threshold range centered on the current geographical location under the same set conditions, M is the average score of all persons to be scored within a threshold range centered on the current geographical location under the same set conditions, n is the number of evaluations of the current person to be scored, s is the average value of the evaluation scores of the current person to be scored including the score given by the current scorer.

7. The central server according to claim 5 or 6, characterized in that, The processing module is further used for: Ranking all persons to be scored according to the scores of all persons to be scored received by the receiving module.

8. A terminal of the person being scored, characterized in that, The terminal includes: A sending module for sending registration information to the central server; A receiving module for receiving the scoring model and set conditions sent by the central server; and A processing module for obtaining the current geographical location after the person to be scored completes a task; Wherein, the receiving module is further used for receiving the score of the person to be scored by the scorer, The processing module is further used for calculating the final score of the person to be scored using the scoring model based on the geographical location, the previous scores of the person to be scored, and the set conditions, and The sending module is further used for sending the final score to the central server.

9. The terminal according to claim 8, characterized in that, The scoring model is Among them, is the final score of the current person being scored, C is the number of all evaluations of all evaluated persons within the threshold range centered on the current geographical location and under the same set conditions. M is the average score of all evaluated persons within the threshold range centered on the current geographical location and under the same set conditions. n is the number of evaluations of the current evaluated person. s is the average value of the evaluation scores of the current evaluated person, including the score given by the current rater.

10. The terminal according to claim 8 or 9, characterized in that, According to the set conditions sent by the central server to the terminal, after the evaluated person completes the task, the processing module will also obtain the current weather condition and / or the current time.

Images