# US 2026/0073338 A1 · Method for generating portrait of mechanical equipment

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

- Number: US 2026/0073338 A1
- Document ID: US20260073338A1
- Status: Published application
- Kind: A1
- Application number: 19/388,424
- Filed: 2025-11-13
- Published: 2026-03-12
- Earliest claimed: 2022-02-14
- Assignees: Yantai Jereh Oilfield Services Group Co., Ltd.
- Applicants: Yantai Jereh Oilfield Services Group Co., Ltd.
- Inventors: Xinmeng WANG; Zongwen WANG; Hailong LI
- Web page: https://patentgrep.com/patent/US20260073338A1

## CPC

- G06Q 10/06395: {Quality analysis or management}
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06N 3/048: Activation functions
- Y02P 90/30: Computing systems specially adapted for manufacturing
- 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
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

A method for generating a portrait of mechanical equipment includes: obtaining all data information related to mechanical equipment; performing data fusion on the data information related to the mechanical equipment to obtain a multi-source data information set; obtaining target attribute data and target state data of the mechanical equipment based on the multi-source data information set; generating attribute labels of the mechanical equipment based on the obtained target attribute data; inputting current target state data of the mechanical equipment into a trained neural network model to obtain current state labels of the mechanical equipment, where the current state labels include state label values of the mechanical equipment; and generating an equipment portrait of the mechanical equipment through attribute label values of the obtained attribute labels and the state label values of the obtained current state labels.

## Claims

### Claim 1

A method for generating an equipment portrait of mechanical equipment, comprising:
obtaining data information related to the mechanical equipment;
performing data fusion on the data information related to the mechanical equipment to obtain a multi-source data information set;
obtaining target attribute data and target state data of the mechanical equipment based on the multi-source data information set;
initializing a neural network model based on the target state data of the mechanical equipment and a quantity of target state label values of the target state data;
generating a plurality of statistical indicators based on the target state data; and
inputting a data matrix comprising the plurality of statistical indicators and state classification label data of the target state data into the neural network model, and training the neural network model to obtain a trained neural network model.

### Claim 2 (depends on 1)

The method according to claim 1, further comprising:
generating attribute labels of the mechanical equipment based on the target attribute data;
inputting the target state data of the mechanical equipment into the trained neural network model to obtain current state labels of the mechanical equipment, wherein the current state labels comprise state label values of the mechanical equipment;
generating the equipment portrait of the mechanical equipment with attribute label values of the attribute labels and the state label values of the current state labels; and
determining whether the mechanical equipment fails based on the equipment portrait of the mechanical equipment.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the obtaining target attribute data and target state data of the mechanical equipment based on the multi-source data information set comprises:
obtaining initial attribute data and initial state data based on the multi-source data information set;
obtaining the target attribute data based on a degree of attention to and/or importance of the initial attribute data; and
performing normalization processing on the initial state data to obtain the target state data.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the generating the equipment portrait of the mechanical equipment with attribute label values of the attribute labels and the state label values of the current state labels comprises:
constructing a set of label values and a set of equipment based on the attribute label values and the state label values of the mechanical equipment;
constructing a co-occurrence matrix based on the set of label values and the set of equipment;
obtaining, based on the co-occurrence matrix, label clusters of the attribute labels and the current state labels by using a clustering algorithm; and
obtaining key label values of the equipment based on the label clusters, and generating the equipment portrait of the mechanical equipment.

### Claim 5 (depends on 4)

The method according to claim 4, wherein the obtaining key label values of the equipment based on the label clusters, and generating the equipment portrait of the mechanical equipment comprises:
comparing label values of each equipment with label values included in the label clusters; and
obtaining a first label cluster with a largest quantity of label value categories covered by the label values included in each equipment among the label clusters, and setting corresponding label values in the first label cluster as the key label values of the equipment.

### Claim 6 (depends on 2)

The method according to claim 2, further comprising:
visualizing the generated equipment portrait as a portrait word cloud map.

### Claim 7 (depends on 2)

The method according to claim 2, further comprising:
comparing state label values of the target state data of the mechanical equipment with set values to obtain the current state labels of the mechanical equipment.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the performing data fusion on the data information related to the mechanical equipment to obtain the multi-source data information set comprises:
setting unique identifiers for each equipment that are different from each other;
obtaining a first database table with field of a unique identifier for each equipment and a second database table; and
in Structured Query Language (SQL), construct an association relationship between the first database table and the second database table by using the unique identifier as an associated field.

### Claim 9 (depends on 1)

The method according to claim 1, wherein the neural network model comprises a backpropagation neural network model.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the statistical indicators comprise: a mean value, a standard deviation, a square root amplitude, an effective value, a peak value, skewness, kurtosis, a maximum value, a margin value, a form factor, or a pulse index.

### Claim 11 (depends on 7)

The method according to claim 7, wherein the state label values comprise: normal, fault, high, medium, and low.

### Claim 12

A computer device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor, when executing the computer program, is configured to perform operations comprising:
obtaining data information related to mechanical equipment;
performing data fusion on the data information related to the mechanical equipment to obtain a multi-source data information set;
obtaining target attribute data and target state data of the mechanical equipment based on the multi-source data information set;
initializing a neural network model based on the target state data of the mechanical equipment and a quantity of target state label values of the target state data;
generating a plurality of statistical indicators based on the target state data; and
inputting a data matrix comprising the plurality of statistical indicators and state classification label data of the target state data into the neural network model, and training the neural network model.

### Claim 13 (depends on 12)

The computer device according to claim 12, wherein the operations further comprise:
generating attribute labels of the mechanical equipment based on the target attribute data;
inputting the target state data of the mechanical equipment into a trained neural network model to obtain current state labels of the mechanical equipment, wherein the current state labels comprise state label values of the mechanical equipment; and
generating an equipment portrait of the mechanical equipment with attribute label values of the attribute labels and the state label values of the current state labels.

### Claim 14 (depends on 12)

The computer device according to claim 12, wherein the obtaining target attribute data and target state data of the mechanical equipment based on the multi-source data information set comprises:
obtaining initial attribute data and initial state data based on the multi-source data information set;
obtaining the target attribute data based on a degree of attention to and/or importance of the initial attribute data; and
performing normalization processing on the initial state data to obtain the target state data.

### Claim 15 (depends on 13)

The computer device according to claim 13, wherein the generating the equipment portrait of the mechanical equipment with attribute label values of the attribute labels and the state label values of the current state labels comprises:
constructing a set of label values and a set of equipment based on the attribute label values and the state label values of the mechanical equipment;
constructing a co-occurrence matrix based on the set of label values and the set of equipment;
obtaining, based on the co-occurrence matrix, label clusters of the attribute labels and the current state labels by using a clustering algorithm; and
obtaining key label values of the equipment based on the label clusters, and generating the equipment portrait of the mechanical equipment.

### Claim 16 (depends on 15)

The computer device according to claim 15, wherein the obtaining key label values of the equipment based on the label clusters, and generating the equipment portrait of the mechanical equipment comprises:
comparing label values of each equipment with label values included in the label clusters; and
obtaining a first label cluster with a largest quantity of label value categories covered by the label values included in each equipment among the label clusters, and setting corresponding label values in the first label cluster as the key label values of the equipment.

### Claim 17 (depends on 13)

The computer device according to claim 13, wherein the operations further comprise:
visualizing the generated equipment portrait as a portrait word cloud map.

### Claim 18 (depends on 13)

The computer device according to claim 13, wherein the operations further comprise:
comparing state label values of the target state data of the mechanical equipment with set values to obtain the current state labels of the mechanical equipment.

### Claim 19 (depends on 12)

The computer device according to claim 12, wherein the performing data fusion on the data information related to the mechanical equipment to obtain the multi-source data information set comprises:
setting unique identifiers for each equipment that are different from each other;
obtaining a first database table with a unique identifier for each equipment and a second database table associated with the first database table; and
associating the first database table with the second database table by using the unique identifier.

### Claim 20

A non-transitory computer-readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, causes the processor to perform operations comprising:
obtaining data information related to mechanical equipment;
performing data fusion on the data information related to the mechanical equipment to obtain a multi-source data information set;
obtaining target attribute data and target state data of the mechanical equipment based on the multi-source data information set;
initializing a neural network model based on the target state data of the mechanical equipment and a quantity of target state label values of the target state data;
generating a plurality of statistical indicators based on the target state data; and
inputting a data matrix comprising the plurality of statistical indicators and state classification label data of the target state data into the neural network model, and training the neural network model to obtain a trained neural network model.
