CN112418986A - Algorithm upgrading solution for high-stability intelligent energy body - Google Patents

Abstract

The invention discloses an algorithm upgrading solution of a high-stability intelligent energy body, belonging to the technical field of intelligent energy bodies, and the specific solving steps of the algorithm upgrading solution of the high-stability intelligent energy body are as follows: s1: iteration of monthly data: according to the order quantity, starting a model training iteration plan regularly; s2: training a model: extracting the individual net size of the satisfied order from the existing order satisfied by the customer, retraining the model parameters, and forming a new size table with a version; s3: updating the personal portrait table: through the newly trained model, the portrait table of the user of the historical order is recalculated, the ideal portrait table is not changed, the portrait table is backfilled, and meanwhile, the historical actual parameters are reserved, so that traceability and evaluation are ensured. In the scene of intelligent measurement, the iteration and the upgrade of the model are carried out on the premise of preferentially ensuring the stability of the algorithm and ensuring the stable return and exchange rate of delivery; the scheme adopts a specific strategy mode, and reduces the service risk.

Description

Algorithm upgrading solution for high-stability intelligent energy body

Technical Field

The invention relates to the technical field of intelligent energy bodies, in particular to an algorithm upgrading solution for a high-stability intelligent energy body.

Background

The human body model is established based on human body parameters, can be used for accurately describing morphological characteristics and mechanical characteristics of a human body, and is a very important auxiliary tool for researching, analyzing, designing, testing and evaluating a human-computer system. Many studies have been made at home and abroad on the establishment and application of human body models. According to the form, the human body model can be divided into a physical model, a digital simulation model and the like. According to the purpose, the human body model can be divided into a human body model for design, a human body model for working posture, a human body model for analyzing action, a human body model for matching a human-computer interface and the like.

At present, the mainstream algorithm iteration means cannot ensure the online delivery fluctuation rate.

Disclosure of Invention

The invention aims to provide a solution for upgrading an algorithm of a high-stability intelligent energy body so as to solve the problem that the fluctuation rate of on-line delivery cannot be ensured by the current mainstream algorithm iteration means provided in the background technology.

In order to achieve the purpose, the invention provides the following technical scheme: an algorithm upgrading solution of a high-stability intelligent energy body comprises the following specific steps:

s1: iteration of monthly data: according to the order quantity, starting a model training iteration plan regularly;

s2: training a model: extracting the individual net size of the satisfied order from the existing order satisfied by the customer, retraining the model parameters, and forming a new size table with a version;

s3: updating the personal portrait table: recalculating the portrait table of the user of the historical order through the newly trained model, backfilling the portrait table without changing an ideal portrait table, and simultaneously keeping the actual parameters of the history to ensure traceability and evaluation;

s4: and (3) getting on line: the new model is on-line, and a certain flow is cut to the new model;

s5: whether the returned goods are lower than the returned goods before the goods come on line: evaluating whether the order is in accordance with expectation according to the satisfaction degree of the actually delivered order;

s6: if the return rate of goods is reduced, the total amount takes effect, and the new model is formally used in the total amount;

s7: otherwise, the policy is rolled back.

Compared with the prior art, the invention has the beneficial effects that:

1) in the scene of intelligent measurement, the iteration and the upgrade of the model are carried out on the premise of preferentially ensuring the stability of the algorithm and ensuring the stable return and exchange rate of delivery;

2) the scheme adopts a specific strategy mode, and reduces the service risk.

Drawings

Fig. 1 is a flow chart of the solution of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.

Example (b):

referring to fig. 1, the present invention provides a technical solution: an algorithm upgrading solution of a high-stability intelligent energy body comprises the following specific steps:

s1: iteration of monthly data: according to the order quantity, starting a model training iteration plan regularly, taking a month as a basic unit of the iteration plan, and performing iteration operation every month;

s2: training a model: extracting the individual net size of the satisfied order from the existing order satisfied by the customer, retraining the model parameters, and forming a new size table with a version, wherein the individual net size of the satisfied order can accurately show the body, so that the customer is satisfied, and the selected mode has strong applicability;

s3: updating the personal portrait table: recalculating the portrait table of the user of the historical order through a newly trained model, not changing an ideal personal portrait table, backfilling the personal portrait table, and simultaneously keeping historical actual parameters to ensure traceability and evaluation, wherein the object of data change and the changed numerical value can be seen by updating the personal portrait table and keeping the historical actual parameters;

s4: and (3) getting on line: the new model is on-line, a certain flow is cut into the new model, the new model and the old model are simultaneously applied, the processing speed is ensured, and meanwhile, whether the new model is insufficient or not can be found, so that an improved space is provided;

s5: whether the returned goods are lower than the returned goods before the goods come on line: evaluating whether the order is in accordance with expectation according to the satisfaction degree of the actually delivered order;

based on the evaluation of whether the expected problem is met in step S5, the following two results are produced:

s6: if the return rate of goods is reduced, the total amount is effective, and the new model is formally used in the total amount to completely replace the old model;

s7: otherwise, the rollback strategy adopts the old model and continues to improve the new model.

While there have been shown and described the fundamental principles and essential features of the invention and advantages thereof, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof; the present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (1)

1. An algorithm upgrading solution of a high-stability intelligent energy body is characterized in that: the specific solving steps of the algorithm upgrading solution of the high-stability intelligent energy body are as follows:

s1: iteration of monthly data: according to the order quantity, starting a model training iteration plan regularly;

s2: training a model: extracting the individual net size of the satisfied order from the existing order satisfied by the customer, retraining the model parameters, and forming a new size table with a version;

s3: updating the personal portrait table: recalculating the portrait table of the user of the historical order through the newly trained model, backfilling the portrait table without changing an ideal portrait table, and simultaneously keeping the actual parameters of the history to ensure traceability and evaluation;

s4: and (3) getting on line: the new model is on-line, and a certain flow is cut to the new model;

s5: whether the returned goods are lower than the returned goods before the goods come on line: evaluating whether the order is in accordance with expectation according to the satisfaction degree of the actually delivered order;

s6: if the return rate of goods is reduced, the total amount takes effect, and the new model is formally used in the total amount;

s7: otherwise, the policy is rolled back.

Images