# US 2024/0177215 A1 · Service Execution System and Related Product

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0177215 A1
- Document ID: US20240177215A1
- Status: Published application
- Kind: A1
- Application number: 18/436,760
- Filed: 2024-02-08
- Published: 2024-05-30
- Earliest claimed: 2021-08-12
- Assignees: Huawei Cloud Computing Technologies Co., Ltd.
- Applicants: Huawei Cloud Computing Technologies Co., Ltd.
- Inventors: Weihua Shan; Yang Dong; Huang Xu
- Web page: https://patentgrep.com/patent/US20240177215A1

## CPC

- G06F 18/2413: based on distances to training or reference patterns
- G06Q 30/0631: {Recommending goods or services}
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G06Q 10/0637: Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 30/0251: Targeted advertisements
- G06Q 50/60: Business processes related to postal services (shipping G06Q10/083; franking apparatus G07B17/00)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

This application provides a service execution system including a service execution apparatus and a decision apparatus. The service execution apparatus collects a first quantity of service requests from a received service request, to obtain a first sample set, and sends the first sample set to the decision apparatus. The decision apparatus evaluates a first model and a first policy based on the first sample set, then the decision apparatus processes following steps basing on evaluation result of the first model.

## Claims

### Claim 1

A service execution system, wherein the system comprises a service execution apparatus and a decision apparatus, wherein
the service execution apparatus collects a first quantity of service requests from a received service request, to obtain a first sample set;
the service execution apparatus sends the first sample set to the decision apparatus;
the decision apparatus evaluates a first model and a first policy based on the first sample set; and
when an evaluation result of the first model is better than an evaluation result of the first policy, the decision apparatus sends the first model to the service execution apparatus, and the service execution apparatus processes a future received service request based on the first model; or
when an evaluation result of the first policy is better than an evaluation result of the first model, the decision apparatus sends the first policy to the service execution apparatus, and the service execution apparatus processes a future received service request according to the first policy.

### Claim 2 (depends on 1)

The system according to claim 1, wherein before that the decision apparatus evaluates a first model and a first policy based on the first sample set,
the service execution apparatus collects a second quantity of service requests from the received service request, to obtain a second sample set, wherein the second sample set comprises a training sample set and a test sample set;
the service execution apparatus sends the second sample set to the decision apparatus;
the decision apparatus obtains a plurality of models, wherein the plurality of models comprise: a model that is obtained by the decision apparatus by training an initial model based on the training sample set, and a model that is obtained by the decision apparatus by training the initial model based on a historical service request, wherein the historical service request is received by the service execution apparatus before the service execution apparatus collects the second quantity of service requests from the received service request; and
the decision apparatus evaluates the plurality of models based on the test sample set, to determine the first model, wherein the first model is a model having a best evaluation result in the plurality of models.

### Claim 3 (depends on 2)

The system according to claim 2, wherein before that the decision apparatus evaluates a first model and a first policy based on the first sample set,
the decision apparatus obtains a plurality of policies; and
the decision apparatus evaluates the plurality of policies based on the second sample set, to determine the first policy, wherein the first policy is a policy having a best evaluation result in the plurality of policies.

### Claim 4 (depends on 2)

The system according to claim 2, wherein the first sample set and the second sample set are a same sample set, or the first sample set comprises the second sample set.

### Claim 5

A decision method, applied to a service execution system, wherein the service execution system comprises a service execution apparatus and a decision apparatus, and the method comprises:
obtaining, by the decision apparatus, a first sample set, wherein the first sample set comprises a first quantity of service requests collected by the service execution apparatus from a received service request;
evaluating, by the decision apparatus, a first model and a first policy based on the first sample set; and
when an evaluation result of the first model is better than an evaluation result of the first policy, sending, by the decision apparatus, the first model to the service execution apparatus, to enable the service execution apparatus to process a future received service request based on the first model; or
when an evaluation result of the first policy is better than an evaluation result of the first model, sending, by the decision apparatus, the first policy to the service execution apparatus, to enable the service execution apparatus to process a future received service request according to the first policy.

### Claim 6 (depends on 5)

The method according to claim 5, wherein before the evaluating, by the decision apparatus, a first model and a first policy based on the first sample set, the method further comprises:
obtaining, by the decision apparatus, a second sample set, wherein the second sample set comprises a second quantity of service requests collected by the service execution apparatus from the received service request, and the second sample set comprises a training sample set and a test sample set;
obtaining, by the decision apparatus, a plurality of models, wherein the plurality of models comprise: a model that is obtained by the decision apparatus by training an initial model based on the training sample set, and a model that is obtained by the decision apparatus by training the initial model based on a historical service request, wherein the historical service request is received by the service execution apparatus before the service execution apparatus collects the second quantity of service requests from the received service request; and
evaluating, by the decision apparatus, the plurality of models based on the test sample set, to determine the first model, wherein the first model is a model having a best evaluation result in the plurality of models.

### Claim 7 (depends on 6)

The method according to claim 6, wherein before the evaluating, by the decision apparatus, a first model and a first policy based on the first sample set, the method further comprises:
obtaining, by the decision apparatus, a plurality of policies; and
evaluating, by the decision apparatus, the plurality of policies based on the second sample set, to determine the first policy, wherein the first policy is a policy having a best evaluation result in the plurality of policies.

### Claim 8 (depends on 6)

The method according to claim 6, wherein the first sample set and the second sample set are a same sample set, or the first sample set comprises the second sample set.

### Claim 9

A computing device, wherein the computing device comprises a processor and a storage, the storage stores computer instructions, and the processor executes the computer instructions, to enable the computing device to perform the following method:
obtaining a first sample set, wherein the first sample set comprises a first quantity of service requests collected by the service execution apparatus from a received service request;
evaluating a first model and a first policy based on the first sample set; and
when an evaluation result of the first model is better than an evaluation result of the first policy, sending, by the decision apparatus, the first model to the service execution apparatus, to enable the service execution apparatus to process a future received service request based on the first model; or
when an evaluation result of the first policy is better than an evaluation result of the first model, sending, by the decision apparatus, the first policy to the service execution apparatus, to enable the service execution apparatus to process a future received service request according to the first policy.
