CN-116468949-B - Fingerprint pattern type identification method, electronic equipment and storage medium

Abstract

The invention relates to the technical field of sample analysis, in particular to a fingerprint pattern type identification method, electronic equipment and a storage medium, and aims to solve the problem of accurately identifying the fingerprint pattern type. The method comprises the steps of obtaining a fingerprint to be identified, inputting the fingerprint to be identified into a model set formed by at least one effective identification model to obtain a fingerprint type identification result, wherein the at least one effective identification model is obtained by screening a trained identification model according to preset conditions, and the identification model is obtained by training based on corresponding ion peak clusters. By the embodiment, the fingerprint to be identified can be integrally analyzed, and the limitation that the traditional method depends on identifying individual characteristic peaks is eliminated, so that the identification result is more accurate, the fingerprint type identification method is not limited by sample sources, is simpler and more reliable, and has wider application range.

Inventors

• LI GUOTAO

Assignees

• 融智生物科技（青岛）有限公司

Dates

Publication Date

20260508

Application Date

20230423

Claims (8)

1. 1. A fingerprint pattern type recognition method, the method comprising: acquiring a fingerprint to be identified; Inputting the fingerprint to be identified into a model set formed by at least one effective identification model to obtain a fingerprint type identification result, wherein the at least one effective identification model is obtained by screening a trained identification model according to preset conditions, and the identification model is obtained by training based on a corresponding ion peak cluster; the method further comprises the step of obtaining a model set, wherein the method specifically comprises the following steps: Training the plurality of recognition models to obtain a plurality of trained recognition models; Screening the plurality of trained recognition models according to the preset conditions to obtain at least one effective recognition model; Combining the at least one valid recognition model to obtain the model set; the training of the plurality of recognition models includes: acquiring a plurality of training sets, wherein each training set is a corresponding ion peak cluster marked with a type label; and inputting each training set into a corresponding recognition model, and training the corresponding recognition model respectively.
2. 2. The method of claim 1, wherein the acquiring a plurality of training sets comprises: Acquiring a plurality of fingerprints marked with type labels; Normalizing the plurality of fingerprints to obtain an ion peak set of the plurality of fingerprints; The set of ion peaks is divided into at least one cluster of ion peaks.
3. 3. The method of claim 2, wherein said dividing the set of ion peaks into at least one cluster of ion peaks comprises: acquiring the density degree of the distribution of a plurality of ion peaks in the ion peak set; Dividing the plurality of ion peaks into at least one ion peak cluster according to the intensity level.
4. 4. The method of claim 1, wherein the step of determining the position of the substrate comprises, The preset conditions at least comprise the number of preset fingerprints and a preset accuracy threshold; the screening the plurality of trained recognition models according to the preset conditions includes: respectively judging whether the number of fingerprints participating in training in the plurality of trained recognition models meets the preset number of fingerprints; respectively judging whether the accuracy of the plurality of recognition models meets the preset accuracy threshold; Screening the identification models which simultaneously meet the preset fingerprint number and the preset accuracy threshold as the effective identification models.
5. 5. The method of claim 1, wherein said combining said at least one valid recognition model to obtain said set of models comprises: Combining the plurality of valid recognition models in different ways to obtain a plurality of model sets consisting of the plurality of valid recognition models.
6. 6. The method of claim 5, wherein the method further comprises: outputting a plurality of recognition results based on the plurality of model sets; Performing error function calculation on the plurality of recognition results; Respectively checking whether the plurality of model sets meet a preset error threshold value or not based on the error function calculation result; Screening one or more model sets meeting the preset error threshold value as trained model sets.
7. 7. An electronic device comprising a processor and a storage means, the storage means being adapted to store a plurality of program code, characterized in that the program code is adapted to be loaded and executed by the processor to perform the fingerprint pattern type recognition method of any one of claims 1 to 6.
8. 8. A computer readable storage medium having stored therein a plurality of program codes, characterized in that the program codes are adapted to be loaded and executed by a processor to perform the fingerprint pattern type recognition method according to any one of claims 1 to 6.

Description

Fingerprint pattern type identification method, electronic equipment and storage medium Technical Field The invention relates to the technical field of sample analysis, in particular to a fingerprint pattern type identification method, electronic equipment and a storage medium. Background Most of the traditional fingerprint pattern type identification methods adopt characteristic peak identification, but some characteristic peaks of the fingerprint patterns are not obvious or have low abundance, so that the fingerprint pattern type cannot be identified because the characteristic peaks are not easy to detect. Accordingly, there is a need in the art for a new solution to the above-mentioned problems. Disclosure of Invention The present invention has been made to overcome the above-mentioned drawbacks, and provides a fingerprint type identification method, an electronic device, and a storage medium that solve or at least partially solve the technical problem of how to accurately identify a fingerprint type. In a first aspect, a fingerprint pattern type identification method is provided, the method including: acquiring a fingerprint to be identified; Inputting the fingerprint to be identified into a model set formed by at least one effective identification model to obtain a fingerprint type identification result, wherein the at least one effective identification model is obtained by screening the trained identification model according to preset conditions, and the identification model is obtained by training based on corresponding ion peak clusters. In one technical scheme of the fingerprint pattern type identification method, the method further comprises obtaining a model set, wherein the obtaining the model set specifically comprises: Training the plurality of recognition models to obtain a plurality of trained recognition models; Screening the plurality of trained recognition models according to the preset conditions to obtain at least one effective recognition model; and combining the at least one effective identification model to obtain the model set. In one technical scheme of the fingerprint pattern type recognition method, the training of the plurality of recognition models includes: acquiring a plurality of training sets, wherein each training set is a corresponding ion peak cluster marked with a type label; and inputting each training set into a corresponding recognition model, and training the corresponding recognition model respectively. In one technical scheme of the fingerprint pattern type identification method, the acquiring a plurality of training sets includes: Acquiring a plurality of fingerprints marked with type labels; Normalizing the plurality of fingerprints to obtain an ion peak set of the plurality of fingerprints; The set of ion peaks is divided into at least one cluster of ion peaks. In one technical scheme of the fingerprint pattern type identification method, the dividing the ion peak set into at least one ion peak cluster includes: acquiring the density degree of the distribution of a plurality of ion peaks in the ion peak set; Dividing the plurality of ion peaks into at least one ion peak cluster according to the intensity level. In one technical scheme of the fingerprint pattern type identification method, The preset conditions at least comprise the number of preset fingerprints and a preset accuracy threshold; the screening the plurality of trained recognition models according to the preset conditions includes: respectively judging whether the number of fingerprints participating in training in the plurality of trained recognition models meets the preset number of fingerprints; respectively judging whether the accuracy of the plurality of recognition models meets the preset accuracy threshold; Screening the identification models which simultaneously meet the preset fingerprint number and the preset accuracy threshold as the effective identification models. In one technical scheme of the fingerprint pattern type recognition method, the combining the at least one effective recognition model to obtain the model set includes: Combining the plurality of valid recognition models in different ways to obtain a plurality of model sets consisting of the plurality of valid recognition models. In one technical scheme of the fingerprint pattern type identification method, the method further comprises: outputting a plurality of recognition results based on the plurality of model sets; Performing error function calculation on the plurality of recognition results; Respectively checking whether the plurality of model sets meet a preset error threshold value or not based on the error function calculation result; Screening one or more model sets meeting the preset error threshold value as trained model sets. In a second aspect, an electronic device is provided, which includes a processor and a storage device, where the storage device is adapted to store a plurality of program codes, where the pro