A magnetic resonance fast quantum measurement method and system

Abstract

The present invention relates to a magnetic resonance fast quantum measurement method and system, wherein the method comprises the following steps: acquiring historical data, including ODMR spectrum data generated during historical measurement processes, and characteristic data of the measurement object and characteristic data of the measuring instrument corresponding to the historical measurement processes; preprocessing the historical data to form training data, and training a neural network model using the training data, so that the trained neural network model can distinguish multiple frequency band nodes of the ODMR spectrum generated during the measurement process; acquiring characteristic data of the current object to be measured and characteristic data of the current measuring instrument, and inputting the data into the trained neural network model to obtain multiple frequency band nodes; generating microwaves of corresponding frequencies by the measuring instrument to act on diamond, respectively measuring the fluorescence intensity emitted by the diamond color center at each frequency, fitting the curve of the current ODMR spectrum by curve fitting, and inverting the ODMR spectrum distribution function to obtain the magnetic field strength of the object to be measured.

Description

Technical Field

[0001] The present invention relates to a magnetic resonance fast quantum measurement method and system, belonging to the technical field of quantum magnetic field measurement. Background Art

[0002] To detect the resonant frequency or zero-field splitting of the NV center's ground state energy level, continuous optically probed magnetic resonance (cw-ODMR) is widely used. This technique typically involves sweeping the microwave frequency over a certain range to measure the difference between the trough and center frequencies.

[0003] In the measurement time of the swept frequency method, the microwave modulation time is relatively long, reaching the order of seconds. Due to the different requirements for magnetic measurement sampling rate in different application scenarios, the current sampling rate of the swept frequency method can only reach a few hertz, which greatly limits its application scope. Summary of the Invention

[0004] In order to solve the above problems in the prior art, the present invention proposes a magnetic resonance fast quantum measurement method and system.

[0005] The technical solutions of the present invention are as follows:

[0006] A magnetic resonance fast quantum measurement method comprises the following steps:

[0007] Acquiring historical data, including ODMR spectrum data generated during historical measurement processes, and characteristic data of measurement objects and characteristic data of measurement instruments corresponding to the historical measurement processes;

[0008] Preprocessing historical data to form training data, and using the training data to train a neural network model, so that the trained neural network model can distinguish multiple frequency band nodes of the ODMR spectrum generated during the measurement process based on characteristic data of the measurement object and characteristic data of the measurement instrument;

[0009] The frequency band nodes are the connection points between the frequency windows where the curve in the ODMR spectrum changes significantly;

[0010] Acquire characteristic data of the current object to be measured and characteristic data of the current measuring instrument, and input them into a trained neural network model to obtain multiple frequency band nodes;

[0011] Corresponding to the frequencies of multiple frequency band nodes, microwaves of corresponding frequencies are generated by a measuring instrument and acted on the diamond, and the fluorescence intensity emitted by the diamond color center at each frequency is measured respectively. The multiple fluorescence intensity data obtained by measurement and the corresponding frequencies are used to fit the current ODMR spectrum curve through curve fitting, and the ODMR spectrum distribution function is inverted to obtain the center frequency of the ODMR spectrum from the ODMR spectrum distribution function;

[0012] The magnetic field strength of the object to be measured is obtained according to the center frequency of the ODMR spectrum.

[0013] As a preferred embodiment, the step of preprocessing historical data to form training data includes:

[0014] Setting a slope change threshold, and traversing the ODMR spectrum curve generated in each historical measurement process according to the slope change threshold;

[0015] For each ODMR spectrum curve, two adjacent points are used as a point group. The slope ratio of the point with a larger slope to the point with a smaller slope in each point group is calculated, and the point groups with a slope ratio greater than the slope threshold are marked.

[0016] Based on all the marked point groups, the significant change segments in the ODMR spectrum curve are determined, and the middle points of each curve change segment are marked as frequency band nodes;

[0017] The number of frequency band nodes of each ODMR spectrum curve is recorded, and the frequency value of each frequency band node is extracted.

[0018] As a preferred embodiment, the neural network model includes a first network model and a second network model;

[0019] The training process of the first network model is:

[0020] The measured object characteristic data and the measuring instrument characteristic data of the historical measurement process are used as inputs of the first network model, the number of frequency band nodes is used as a label, and the first network model is iteratively trained according to the loss between the predicted number of frequency band nodes output by the first network model and the label;

[0021] The training process of the second network model is:

[0022] The measurement object characteristic data, measurement instrument characteristic data, and the number of frequency band nodes in the historical measurement process are used as inputs of the second network model, and the array composed of the frequency values ​​of each frequency band node is used as a label. The second network model is iteratively trained based on the loss between the prediction array output by the second network model and the label.

[0023] As a preferred embodiment, the measurement object characteristic data includes the type of the measurement object;

[0024] The characteristic data of the measuring instrument include optical path laser intensity, polarization state, and operating frequency.

[0025] On the other hand, the present invention also provides a magnetic resonance fast quantum measurement system, comprising:

[0026] A data acquisition module is used to acquire historical data, including ODMR spectrum data generated during historical measurement processes, as well as characteristic data of the measurement object and characteristic data of the measurement instrument corresponding to the historical measurement processes;

[0027] A model training module is used to pre-process historical data to generate training data, and train a neural network model using the training data, so that the trained neural network model can distinguish multiple frequency band nodes of the ODMR spectrum generated during the measurement process based on the characteristic data of the measurement object and the characteristic data of the measurement instrument;

[0028] The frequency band nodes are the connection points between the frequency windows where the curve in the ODMR spectrum changes significantly;

[0029] The frequency band differentiation module is used to obtain the characteristic data of the current object to be measured and the characteristic data of the current measuring instrument, and input them into the trained neural network model to obtain multiple frequency band nodes;

[0030] The characteristic parameter measurement module is used to correspond to the frequencies of multiple frequency band nodes. Microwaves of corresponding frequencies are generated by a measuring instrument and act on the diamond to measure the fluorescence intensity emitted by the diamond color center at each frequency. The multiple fluorescence intensity data obtained by measurement and the corresponding frequencies are used to fit the current ODMR spectrum curve through curve fitting, and the ODMR spectrum distribution function is inverted to obtain the center frequency of the ODMR spectrum from the ODMR spectrum distribution function.

[0031] The magnetic field calculation module is used to obtain the magnetic field strength of the object to be measured according to the center frequency of the ODMR spectrum.

[0032] As a preferred embodiment, the step of preprocessing historical data to form training data includes:

[0033] Setting a slope change threshold, and traversing the ODMR spectrum curve generated in each historical measurement process according to the slope change threshold;

[0034] For each ODMR spectrum curve, two adjacent points are used as a point group. The slope ratio of the point with a larger slope to the point with a smaller slope in each point group is calculated, and the point groups with a slope ratio greater than the slope threshold are marked.

[0035] Based on all the marked point groups, the significant change segments in the ODMR spectrum curve are determined, and the middle points of each curve change segment are marked as frequency band nodes;

[0036] The number of frequency band nodes of each ODMR spectrum curve is recorded, and the frequency value of each frequency band node is extracted.

[0037] As a preferred embodiment, the neural network model includes a first network model and a second network model;

[0038] The training process of the first network model is:

[0039] The measured object characteristic data and the measuring instrument characteristic data of the historical measurement process are used as inputs of the first network model, the number of frequency band nodes is used as a label, and the first network model is iteratively trained according to the loss between the predicted number of frequency band nodes output by the first network model and the label;

[0040] The training process of the second network model is:

[0041] The measurement object characteristic data, measurement instrument characteristic data, and the number of frequency band nodes in the historical measurement process are used as inputs of the second network model, and the array composed of the frequency values ​​of each frequency band node is used as a label. The second network model is iteratively trained based on the loss between the prediction array output by the second network model and the label.

[0042] As a preferred embodiment, the measurement object characteristic data includes the type of the measurement object;

[0043] The characteristic data of the measuring instrument include optical path laser intensity, polarization state, and operating frequency.

[0044] On the other hand, the present invention further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0045] In another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the method described in any embodiment of the present invention when the program is executed by a processor.

[0046] Additional aspects and advantages of the present invention will be set forth in the following description, and some of them will be obvious from the description, or may be learned by practicing the present invention. In addition, the various aspects and advantages of the present invention may be realized and obtained by the method steps and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of the method flow of embodiment 1 of the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0049] It should be understood that the step numbers used herein are only for convenience of description and are not intended to limit the order in which the steps are to be executed.

[0050] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0051] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0052] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0053] Example 1:

[0054] See also Figure 1 This embodiment provides a magnetic resonance fast quantum measurement method, comprising the following steps:

[0055] S100, acquiring historical data, including ODMR spectrum data generated during historical measurement processes, and characteristic data of the measurement object and the measurement instrument corresponding to the historical measurement processes;

[0056] S200, preprocessing historical data to form training data, and training a neural network model using the training data, so that the trained neural network model can distinguish multiple frequency band nodes of the ODMR spectrum generated during the measurement process based on characteristic data of the measurement object and characteristic data of the measurement instrument;

[0057] The frequency band nodes are the connection points between the frequency windows where the curve in the ODMR spectrum changes significantly;

[0058] S300, obtaining characteristic data of the current object to be measured and characteristic data of the current measuring instrument, and inputting them into the trained neural network model to obtain multiple frequency band nodes;

[0059] S400, corresponding to the frequencies of multiple frequency band nodes, generating microwaves of corresponding frequencies by a measuring instrument and applying them to the diamond, respectively measuring the fluorescence intensity emitted by the diamond color center at each frequency, fitting the current ODMR spectrum curve by curve fitting using the multiple fluorescence intensity data obtained by the measurement and the corresponding frequencies, and inverting the ODMR spectrum distribution function to obtain the center frequency of the ODMR spectrum from the ODMR spectrum distribution function;

[0060] S500 : Obtain the magnetic field strength of the object to be measured according to the center frequency of the ODMR spectrum.

[0061] Based on the above implementation, this embodiment can obtain multiple frequency band nodes through the characteristic data of the object to be measured and the characteristic data of the current measuring instrument. The frequency band nodes are the connection points of the frequency windows where the curve in the ODMR spectrum produces significant changes. They can well characterize the changes in the ODMR spectrum curve. The ODMR spectrum curve follows statistical laws such as Gaussian distribution and Poisson distribution. Through these frequency band nodes, we can fit the ODMR spectrum curve. This only requires a few microwave modulations to complete, greatly reducing the number and time of microwave modulation, thereby significantly improving the speed of quantum magnetic field measurement.

[0062] As a preferred implementation of this embodiment, the step of preprocessing historical data to form training data includes:

[0063] A specific slope change threshold is set, and the optical double resonance microwave (ODMR) spectrum curve generated in each historical measurement process is carefully analyzed through this threshold;

[0064] When analyzing each optical magnetic resonance (ODMR) spectrum curve, we group any two adjacent points on the curve into a point group. Next, we calculate the slope ratio of the points with the larger slope relative to the points with the smaller slope within this point group. Once this slope ratio exceeds a pre-defined slope threshold, the point group is marked for further analysis and processing.

[0065] When analyzing an ODMR spectrum, the first step is to identify segments of significant change within the spectrum based on all marked point groups. A segment of significant change is composed of a continuous set of marked points. This process requires careful observation and analysis of the curve's changes to ensure that every important turning point is accurately captured. Once these segments of significant change have been identified, the next step is to precisely mark the midpoints of each segment. These midpoints serve as frequency band nodes in subsequent analysis and are key to understanding the dynamics of the entire ODMR spectrum.

[0066] The number of frequency band nodes of each ODMR spectrum curve is recorded, and the frequency value of each frequency band node is extracted.

[0067] As a preferred implementation of this embodiment, the neural network model includes a first network model and a second network model;

[0068] The training process of the first network model is:

[0069] The measured object characteristic data and the measuring instrument characteristic data of the historical measurement process are used as inputs of the first network model, the number of frequency band nodes is used as a label, and the first network model is iteratively trained according to the loss between the predicted number of frequency band nodes output by the first network model and the label;

[0070] The training process of the second network model is:

[0071] The measurement object characteristic data, measurement instrument characteristic data, and the number of frequency band nodes in the historical measurement process are used as inputs of the second network model, and the array composed of the frequency values ​​of each frequency band node is used as a label. The second network model is iteratively trained based on the loss between the prediction array output by the second network model and the label.

[0072] According to the above implementation, the neural network model constructed and trained in this embodiment can first predict the number of frequency band nodes in the ODRM spectrum curve of the current object to be measured through the first network model, and then input this predicted number of frequency band nodes together with the characteristic data of the measurement object and the characteristic data of the measuring instrument into the second network model to output the frequency prediction value of each frequency band node.

[0073] As a preferred implementation of this embodiment, the described measurement object characteristic data is not limited to a single parameter, but includes information in multiple dimensions, with particular emphasis on the key feature of the type of measurement object, which can classify and identify different types of measurement objects.

[0074] In this embodiment, the characteristic data of the measuring instrument described covers several key parameters that are crucial for ensuring accurate and reliable measurements. Specifically, these characteristic data include optical path laser intensity, polarization state, and operating frequency. Optical path laser intensity refers to the intensity level of the laser beam as it propagates along the optical path during measurement. The polarization state describes the polarization characteristics of the laser beam. The operating frequency refers to the frequency of the laser emitted by the measuring instrument during measurement.

[0075] Example 2:

[0076] This embodiment provides a magnetic resonance fast quantum measurement system, including:

[0077] A data acquisition module, configured to acquire historical data, including ODMR spectrum data generated during historical measurements, as well as characteristic data of the measurement object and characteristic data of the measurement instrument corresponding to the historical measurements; this module is configured to implement the function of step S100 in the first embodiment and will not be further described herein;

[0078] A model training module is used to preprocess historical data to generate training data, and to train a neural network model using the training data, so that the trained neural network model can distinguish multiple frequency band nodes of the ODMR spectrum generated during the measurement process based on the characteristic data of the measurement object and the characteristic data of the measurement instrument. This module is used to implement the function of step S200 in Example 1 and is not further described here.

[0079] The frequency band nodes are the connection points between the frequency windows where the curve in the ODMR spectrum changes significantly;

[0080] A frequency band differentiation module is used to obtain characteristic data of the current object to be measured and characteristic data of the current measuring instrument, and input them into the trained neural network model to obtain multiple frequency band nodes; this module is used to implement the function of step S300 in the first embodiment and will not be repeated here;

[0081] A characteristic parameter measurement module is used to generate microwaves of corresponding frequencies to the frequencies of multiple frequency band nodes using a measuring instrument, apply them to the diamond, and measure the fluorescence intensity emitted by the diamond color center at each frequency. The multiple fluorescence intensity data obtained by the measurement and the corresponding frequencies are used to fit the current ODMR spectrum curve through curve fitting, and the ODMR spectrum distribution function is inverted to obtain the center frequency of the ODMR spectrum from the ODMR spectrum distribution function. This module is used to implement the function of step S400 in Example 1 and is not further described here.

[0082] The magnetic field calculation module is used to obtain the magnetic field strength of the object to be measured according to the center frequency of the ODMR spectrum. This module is used to implement the function of step S500 in the first embodiment and will not be described in detail here.

[0083] As a preferred implementation of this embodiment, the step of preprocessing historical data to form training data includes:

[0084] Setting a slope change threshold, and traversing the ODMR spectrum curve generated in each historical measurement process according to the slope change threshold;

[0085] For each ODMR spectrum curve, two adjacent points are used as a point group. The slope ratio of the point with a larger slope to the point with a smaller slope in each point group is calculated, and the point groups with a slope ratio greater than the slope threshold are marked.

[0086] Based on all the marked point groups, the significant change segments in the ODMR spectrum curve are determined, and the middle points of each curve change segment are marked as frequency band nodes;

[0087] The number of frequency band nodes of each ODMR spectrum curve is recorded, and the frequency value of each frequency band node is extracted.

[0088] As a preferred implementation of this embodiment, the neural network model includes a first network model and a second network model;

[0089] The training process of the first network model is:

[0090] The measured object characteristic data and the measuring instrument characteristic data of the historical measurement process are used as inputs of the first network model, the number of frequency band nodes is used as a label, and the first network model is iteratively trained according to the loss between the predicted number of frequency band nodes output by the first network model and the label;

[0091] The training process of the second network model is:

[0092] The measurement object characteristic data, measurement instrument characteristic data, and the number of frequency band nodes in the historical measurement process are used as inputs of the second network model, and the array composed of the frequency values ​​of each frequency band node is used as a label. The second network model is iteratively trained based on the loss between the prediction array output by the second network model and the label.

[0093] As a preferred implementation of this embodiment, the measurement object characteristic data includes the type of the measurement object;

[0094] The characteristic data of the measuring instrument include optical path laser intensity, polarization state, and operating frequency.

[0095] Example 3:

[0096] This embodiment provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the magnetic resonance fast quantum measurement method as described in any embodiment of the present invention is implemented.

[0097] Example 4:

[0098] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the magnetic resonance fast quantum measurement method as described in any embodiment of the present invention is implemented.

[0099] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0100] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0101] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0102] In the several embodiments provided in this application, if any function 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 this understanding, the technical solution of this application, or the part that contributes to the prior art, or the 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 enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk, and other media that can store program code.

[0103] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A magnetic resonance fast quantum measurement method, characterized in that: The following steps are involved: Acquiring historical data, including ODMR spectrum data generated during historical measurement processes, and characteristic data of measurement objects and characteristic data of measurement instruments corresponding to the historical measurement processes; Preprocessing historical data to form training data, and using the training data to train a neural network model, so that the trained neural network model can distinguish multiple frequency band nodes of the ODMR spectrum generated during the measurement process based on characteristic data of the measurement object and characteristic data of the measurement instrument; The frequency band nodes are the connection points between the frequency windows where the curve in the ODMR spectrum changes significantly; Acquire characteristic data of the current object to be measured and characteristic data of the current measuring instrument, and input them into a trained neural network model to obtain multiple frequency band nodes; Corresponding to the frequencies of multiple frequency band nodes, microwaves of corresponding frequencies are generated by a measuring instrument and acted on the diamond. The fluorescence intensity emitted by the diamond color center at each frequency is measured respectively. The multiple fluorescence intensity data obtained by measurement and the corresponding frequencies are used to fit the current ODMR spectrum curve through curve fitting, and the ODMR spectrum distribution function is inverted to obtain the center frequency of the ODMR spectrum from the ODMR spectrum distribution function. Obtaining the magnetic field strength of the object to be measured according to the center frequency of the ODMR spectrum; The step of preprocessing historical data to form training data includes: Setting a slope change threshold, and traversing the ODMR spectrum curve generated in each historical measurement process according to the slope change threshold; For each ODMR spectrum curve, two adjacent points are used as a point group. The slope ratio of the point with a larger slope to the point with a smaller slope in each point group is calculated, and the point groups with a slope ratio greater than the slope threshold are marked. Based on all the marked point groups, the significant change segments in the ODMR spectrum curve are determined, and the middle points of each curve change segment are marked as frequency band nodes; The number of frequency band nodes of each ODMR spectrum curve is recorded, and the frequency value of each frequency band node is extracted.

2. The magnetic resonance fast quantum measurement method according to claim 1, characterized in that: The neural network model includes a first network model and a second network model; The training process of the first network model is: The measured object characteristic data and the measuring instrument characteristic data of the historical measurement process are used as inputs of the first network model, the number of frequency band nodes is used as a label, and the first network model is iteratively trained according to the loss between the predicted number of frequency band nodes output by the first network model and the label; The training process of the second network model is: The measurement object characteristic data, measurement instrument characteristic data, and the number of frequency band nodes in the historical measurement process are used as inputs of the second network model, and the array composed of the frequency values ​​of each frequency band node is used as a label. The second network model is iteratively trained based on the loss between the prediction array output by the second network model and the label.

3. The magnetic resonance fast quantum measurement method according to claim 1, characterized in that: The measurement object characteristic data includes the type of the measurement object; The characteristic data of the measuring instrument include optical path laser intensity, polarization state, and operating frequency.

4. A magnetic resonance fast quantum measurement system, characterized in that: include: A data acquisition module is used to acquire historical data, including ODMR spectrum data generated during historical measurement processes, as well as characteristic data of the measurement object and characteristic data of the measurement instrument corresponding to the historical measurement processes; A model training module is used to pre-process historical data to generate training data, and train a neural network model using the training data, so that the trained neural network model can distinguish multiple frequency band nodes of the ODMR spectrum generated during the measurement process based on the characteristic data of the measurement object and the characteristic data of the measurement instrument; The frequency band nodes are the connection points between the frequency windows where the curve in the ODMR spectrum changes significantly; The frequency band differentiation module is used to obtain the characteristic data of the current object to be measured and the characteristic data of the current measuring instrument, and input them into the trained neural network model to obtain multiple frequency band nodes; The characteristic parameter measurement module is used to correspond to the frequencies of multiple frequency band nodes. Microwaves of corresponding frequencies are generated by a measuring instrument and act on the diamond to measure the fluorescence intensity emitted by the diamond color center at each frequency. The multiple fluorescence intensity data obtained by measurement and the corresponding frequencies are used to fit the current ODMR spectrum curve through curve fitting, and the ODMR spectrum distribution function is inverted to obtain the center frequency of the ODMR spectrum from the ODMR spectrum distribution function. A magnetic field calculation module is used to obtain the magnetic field strength of the object to be measured based on the center frequency of the ODMR spectrum; The step of preprocessing historical data to form training data includes: Setting a slope change threshold, and traversing the ODMR spectrum curve generated in each historical measurement process according to the slope change threshold; For each ODMR spectrum curve, two adjacent points are used as a point group. The slope ratio of the point with a larger slope to the point with a smaller slope in each point group is calculated, and the point groups with a slope ratio greater than the slope threshold are marked. Based on all the marked point groups, the significant change segments in the ODMR spectrum curve are determined, and the middle points of each curve change segment are marked as frequency band nodes; The number of frequency band nodes of each ODMR spectrum curve is recorded, and the frequency value of each frequency band node is extracted.

5. The magnetic resonance fast quantum measurement system according to claim 4, characterized in that: The neural network model includes a first network model and a second network model; The training process of the first network model is: The measured object characteristic data and the measuring instrument characteristic data of the historical measurement process are used as inputs of the first network model, the number of frequency band nodes is used as a label, and the first network model is iteratively trained according to the loss between the predicted number of frequency band nodes output by the first network model and the label; The training process of the second network model is: The measurement object characteristic data, measurement instrument characteristic data, and the number of frequency band nodes in the historical measurement process are used as inputs of the second network model, and the array composed of the frequency values ​​of each frequency band node is used as a label. The second network model is iteratively trained based on the loss between the prediction array output by the second network model and the label.

6. The magnetic resonance fast quantum measurement system according to claim 4, characterized in that: The measurement object characteristic data includes the type of the measurement object; The characteristic data of the measuring instrument include optical path laser intensity, polarization state, and operating frequency.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the magnetic resonance fast quantum measurement method according to any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the magnetic resonance fast quantum measurement method according to any one of claims 1 to 3 is implemented.

Images