# US 2023/0065684 A1 · Combined classical/quantum predictor evaluation with model accuracy adjustment

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

- Number: US 2023/0065684 A1
- Document ID: US20230065684A1
- Status: Published application
- Kind: A1
- Application number: 17/410,553
- Filed: 2021-08-24
- Published: 2023-03-02
- Earliest claimed: 2021-08-24
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Aaron K. Baughman; Gururaja Hebbar; Micah Forster; Kavitha Hassan Yogaraj; Yoshika Chhabra
- Web page: https://patentgrep.com/patent/US20230065684A1

## CPC

- G06N 10/00: Quantum computing, i.e. information processing based on quantum-mechanical phenomena
- G06N 20/20: Ensemble learning
- G06F 15/16: Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs {(coordinating program control therefor G06F9/52; in regulating and control system G05B)}
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 10/60: Quantum algorithms, e.g. based on quantum optimisation, quantum Fourier or Hadamard transforms
- G06F 40/56: Natural language generation
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Using a model executing on a classical processor, a set of classical features is scored. The scored set of classical features is divided into a set of feature groups, a number of classical features in a group determined according to a qubit capability of a quantum processor. Using a model executing on the quantum processor and a group of the scored set of classical features, a set of quantum features is scored. The score of a quantum feature is adjusted according to an accuracy of the quantum data model. The scored set of classical features and the scored set of quantum features are combined according to a measure of differences between the scored set of classical features and the scored set of quantum features. Using the combined set of scored features and a first set of input data of a resource, a valuation of a resource is calculated.

## Claims

### Claim 1

A computer-implemented method comprising:
scoring, using a classical data model executing on a classical processor, a set of classical features, a classical feature in the set of classical features comprising a first attribute of a resource, a score of the classical feature comprising an evaluation of a utility of the classical feature in predicting a result involving the resource, the scoring resulting a scored set of classical features;
dividing, into a set of feature groups, the scored set of classical features, a number of classical features in a feature group in the set of feature groups determined according to a qubit capability of a quantum processor;
scoring, using a quantum data model executing on the quantum processor and a feature group of the scored set of classical features, a set of quantum features, a quantum feature in the set of quantum features comprising a second attribute of the resource, a score of the quantum feature comprising an evaluation of a utility of the quantum feature in predicting the result, the scoring resulting a scored set of quantum features;
adjusting, according to an accuracy of the quantum data model, the score of the quantum feature;
combining, forming a combined set of scored features, the scored set of classical features and the scored set of quantum features, the combining performed according to a measure of differences between the scored set of classical features and the scored set of quantum features; and
calculating, using the combined set of scored features and a first set of input data of a resource, a valuation of the resource.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein members of each feature group in the set of feature groups are determined according a ranking, the ranking determined according to a score of each classical feature in the scored set of classical features.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein adjusting, according to the accuracy of the quantum data model, the score of the quantum feature comprises:
computing, for each score in the set of scored quantum features using the accuracy of the quantum data model, an adjusted score; and
normalizing, by dividing each adjusted score by a sum of adjusted scores, each adjusted score.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
further combining, into the combined set of scored features, a scored set of expert features, the further combining performed according to a measure of differences between the scored set of expert features and the scored set of quantum features, a score of an expert feature in the scored set of expert features comprising an expert evaluation of a utility of the expert feature in predicting a result involving the resource.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
constructing, using a natural language processing system, the combined set of scored features, and the valuation, a natural language explanation of the valuation, the natural language explanation expressed in natural language form.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
configuring, according to the valuation, a computing system deployment, the computing system deployment including the resource.

### Claim 7

A computer program product for predictor evaluation, the computer program product comprising:
one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to score, using a classical data model executing on a classical processor, a set of classical features, a classical feature in the set of classical features comprising a first attribute of a resource, a score of the classical feature comprising an evaluation of a utility of the classical feature in predicting a result involving the resource, the scoring resulting a scored set of classical features;
program instructions to divide, into a set of feature groups, the scored set of classical features, a number of classical features in a feature group in the set of feature groups determined according to a qubit capability of a quantum processor;
program instructions to score, using a quantum data model executing on the quantum processor and a feature group of the scored set of classical features, a set of quantum features, a quantum feature in the set of quantum features comprising a second attribute of the resource, a score of the quantum feature comprising an evaluation of a utility of the quantum feature in predicting the result, the scoring resulting a scored set of quantum features;
program instructions to adjust, according to an accuracy of the quantum data model, the score of the quantum feature;
program instructions to combine, forming a combined set of scored features, the scored set of classical features and the scored set of quantum features, the combining performed according to a measure of differences between the scored set of classical features and the scored set of quantum features; and
program instructions to calculate, using the combined set of scored features and a first set of input data of a resource, a valuation of the resource.

### Claim 8 (depends on 7)

The computer program product of claim 7, wherein members of each feature group in the set of feature groups are determined according a ranking, the ranking determined according to a score of each classical feature in the scored set of classical features.

### Claim 9 (depends on 7)

The computer program product of claim 7, wherein program instructions to adjust, according to the accuracy of the quantum data model, the score of the quantum feature comprises:
program instructions to compute, for each score in the set of scored quantum features using the accuracy of the quantum data model, an adjusted score; and
program instructions to normalize, by dividing each adjusted score by a sum of adjusted scores, each adjusted score.

### Claim 10 (depends on 7)

The computer program product of claim 7, the stored program instructions further comprising:
program instructions to further combine, into the combined set of scored features, a scored set of expert features, the further combining performed according to a measure of differences between the scored set of expert features and the scored set of quantum features, a score of an expert feature in the scored set of expert features comprising an expert evaluation of a utility of the expert feature in predicting a result involving the resource.

### Claim 11 (depends on 7)

The computer program product of claim 7, the stored program instructions further comprising:
program instructions to construct, using a natural language processing system, the combined set of scored features, and the valuation, a natural language explanation of the valuation, the natural language explanation expressed in natural language form.

### Claim 12 (depends on 7)

The computer program product of claim 7, the stored program instructions further comprising:
program instructions to configure, according to the valuation, a computing system deployment, the computing system deployment including the resource.

### Claim 13 (depends on 7)

The computer program product of claim 7, wherein the stored program instructions are stored in the at least one of the one or more storage media of a local data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.

### Claim 14 (depends on 7)

The computer program product of claim 7, wherein the stored program instructions are stored in the at least one of the one or more storage media of a server data processing system, and wherein the stored program instructions are downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

### Claim 15 (depends on 7)

The computer program product of claim 7, wherein the computer program product is provided as a service in a cloud environment.

### Claim 16

A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
program instructions to score, using a classical data model executing on a classical processor, a set of classical features, a classical feature in the set of classical features comprising a first attribute of a resource, a score of the classical feature comprising an evaluation of a utility of the classical feature in predicting a result involving the resource, the scoring resulting a scored set of classical features;
program instructions to divide, into a set of feature groups, the scored set of classical features, a number of classical features in a feature group in the set of feature groups determined according to a qubit capability of a quantum processor;
program instructions to score, using a quantum data model executing on the quantum processor and a feature group of the scored set of classical features, a set of quantum features, a quantum feature in the set of quantum features comprising a second attribute of the resource, a score of the quantum feature comprising an evaluation of a utility of the quantum feature in predicting the result, the scoring resulting a scored set of quantum features;
program instructions to adjust, according to an accuracy of the quantum data model, the score of the quantum feature;
program instructions to combine, forming a combined set of scored features, the scored set of classical features and the scored set of quantum features, the combining performed according to a measure of differences between the scored set of classical features and the scored set of quantum features; and
program instructions to calculate, using the combined set of scored features and a first set of input data of a resource, a valuation of the resource.

### Claim 17 (depends on 16)

The computer system of claim 16, wherein members of each feature group in the set of feature groups are determined according a ranking, the ranking determined according to a score of each classical feature in the scored set of classical features.

### Claim 18 (depends on 16)

The computer system of claim 16, wherein program instructions to adjust, according to the accuracy of the quantum data model, the score of the quantum feature comprises:
program instructions to compute, for each score in the set of scored quantum features using the accuracy of the quantum data model, an adjusted score; and
program instructions to normalize, by dividing each adjusted score by a sum of adjusted scores, each adjusted score.

### Claim 19 (depends on 16)

The computer system of claim 16, the stored program instructions further comprising:
program instructions to further combine, into the combined set of scored features, a scored set of expert features, the further combining performed according to a measure of differences between the scored set of expert features and the scored set of quantum features, a score of an expert feature in the scored set of expert features comprising an expert evaluation of a utility of the expert feature in predicting a result involving the resource.

### Claim 20 (depends on 16)

The computer system of claim 16, the stored program instructions further comprising:
program instructions to construct, using a natural language processing system, the combined set of scored features, and the valuation, a natural language explanation of the valuation, the natural language explanation expressed in natural language form.

### Claim 21 (depends on 16)

The computer system of claim 16, the stored program instructions further comprising:
program instructions to configure, according to the valuation, a computing system deployment, the computing system deployment including the resource.

### Claim 22

A data processing environment comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
program instructions to score, using a classical data model executing on a classical processor, a set of classical features, a classical feature in the set of classical features comprising a first attribute of a resource, a score of the classical feature comprising an evaluation of a utility of the classical feature in predicting a result involving the resource, the scoring resulting a scored set of classical features;
program instructions to divide, into a set of feature groups, the scored set of classical features, a number of classical features in a feature group in the set of feature groups determined according to a qubit capability of a quantum processor;
program instructions to score, using a quantum data model executing on the quantum processor and a feature group of the scored set of classical features, a set of quantum features, a quantum feature in the set of quantum features comprising a second attribute of the resource, a score of the quantum feature comprising an evaluation of a utility of the quantum feature in predicting the result, the scoring resulting a scored set of quantum features;
program instructions to adjust, according to an accuracy of the quantum data model, the score of the quantum feature;
program instructions to combine, forming a combined set of scored features, the scored set of classical features and the scored set of quantum features, the combining performed according to a measure of differences between the scored set of classical features and the scored set of quantum features; and
program instructions to calculate, using the combined set of scored features and a first set of input data of a resource, a valuation of the resource.

### Claim 23 (depends on 22)

The data processing environment of claim 22, wherein members of each feature group in the set of feature groups are determined according a ranking, the ranking determined according to a score of each classical feature in the scored set of classical features.

### Claim 24 (depends on 22)

The data processing environment of claim 22, wherein program instructions to adjust, according to the accuracy of the quantum data model, the score of the quantum feature comprises:
program instructions to compute, for each score in the set of scored quantum features using the accuracy of the quantum data model, an adjusted score; and
program instructions to normalize, by dividing each adjusted score by a sum of adjusted scores, each adjusted score.

### Claim 25

A hybrid classical-quantum computing environment comprising one or more classical processors, one or more quantum processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
program instructions to score, using a classical data model executing on a classical processor, a set of classical features, a classical feature in the set of classical features comprising a first attribute of a resource, a score of the classical feature comprising an evaluation of a utility of the classical feature in predicting a result involving the resource, the scoring resulting a scored set of classical features;
program instructions to divide, into a set of feature groups, the scored set of classical features, a number of classical features in a feature group in the set of feature groups determined according to a qubit capability of a quantum processor;
program instructions to score, using a quantum data model executing on the quantum processor and a feature group of the scored set of classical features, a set of quantum features, a quantum feature in the set of quantum features comprising a second attribute of the resource, a score of the quantum feature comprising an evaluation of a utility of the quantum feature in predicting the result, the scoring resulting a scored set of quantum features;
program instructions to adjust, according to an accuracy of the quantum data model, the score of the quantum feature;
program instructions to combine, forming a combined set of scored features, the scored set of classical features and the scored set of quantum features, the combining performed according to a measure of differences between the scored set of classical features and the scored set of quantum features; and
program instructions to calculate, using the combined set of scored features and a first set of input data of a resource, a valuation of the resource.
