CN113222075B

CN113222075B - Evaluation method and device and electronic equipment

Info

Publication number: CN113222075B
Application number: CN202110461517.0A
Authority: CN
Inventors: 秦波; 赵志勇; 辛晓哲; 苏雪峰; 陈伟
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2021-04-27
Filing date: 2021-04-27
Publication date: 2024-03-08
Anticipated expiration: 2041-04-27
Also published as: CN113222075A

Abstract

The embodiment of the invention provides an evaluation method, an evaluation device and electronic equipment, wherein the method comprises the following steps: acquiring track information of writing strokes written by a user; determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke; determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke; evaluating normalization of the writing of the user according to the first loss information; compared with the prior art, the method and the device for comparing the writing text with the corresponding reference text integrally have finer granularity, so that accuracy of evaluating writing normalization can be improved.

Description

Evaluation method and device and electronic equipment

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to an evaluation method, an evaluation device, and an electronic device.

Background

Chinese characters are recorded symbols of Chinese, and are a mode adopted by people for exchanging and expressing ideas; therefore, chinese character writing and learning have been paid attention to by the world. With the development of computer technology, the writing normalization evaluation of Chinese characters is gradually performed manually, and the writing normalization evaluation of Chinese characters is performed by means of computer technology, so that more conditions for learning to write Chinese characters are created for people.

In the prior art, after a user writes a Chinese character, comparing the whole Chinese character written by the user with the whole standard Chinese character; then, carrying out writing normalization evaluation according to the comparison result; the accuracy of the normalization evaluation mode is low.

Disclosure of Invention

The embodiment of the invention provides an evaluation method for improving the accuracy of writing normalization evaluation.

Correspondingly, the embodiment of the invention also provides an evaluation device and electronic equipment, which are used for ensuring the realization and application of the method.

In order to solve the above problems, an embodiment of the present invention discloses an evaluation method, which specifically includes: acquiring track information of writing strokes written by a user; determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke; determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke; and evaluating the normalization of the writing of the user according to the first loss information.

Optionally, the track information includes coordinate information of a plurality of track points, and determining, according to the track information of the writing strokes, a reference stroke corresponding to the writing stroke from reference strokes corresponding to a reference text includes: acquiring track information of each reference stroke; inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model; the point cloud mapping model determines a track relation based on coordinate information of track points in the track information, and outputs a reference stroke identifier of a reference stroke, the matching degree of which accords with a preset range, according to the track relation; determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identifier; wherein the track relationship comprises at least one of a first relationship, a second relationship, and a third relationship; the first relationship includes a relationship between the writing stroke and a corresponding track point of a reference stroke, the second relationship includes a relationship between track points of the writing stroke, and the third relationship includes a relationship between track points of the reference stroke.

Optionally, the determining the first loss information between the writing stroke and the reference stroke corresponding to the writing stroke includes: determining first geometric information of the writing strokes according to the track information of the writing strokes; determining second geometric information of the reference strokes correspondingly matched with the writing strokes according to track information of the reference strokes correspondingly matched with the writing strokes; and determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to the first geometric information and the second geometric information.

Optionally, the track information includes coordinate information of a plurality of track points; the determining the first geometric information of the writing stroke according to the track information of the writing stroke comprises the following steps: determining at least one of first position information, first length information and first inclination angle information of the writing strokes according to coordinate information of the writing strokes corresponding to each track point; determining first geometric information corresponding to the writing stroke according to at least one of first position information, first length information and first inclination angle information of the writing stroke; the determining the second geometric information of the reference strokes correspondingly matched with the writing strokes according to the track information of the reference strokes correspondingly matched with the writing strokes comprises the following steps: determining at least one of second position information, second length information and second inclination angle information of the reference strokes correspondingly matched with the writing strokes according to the coordinate information of the track points corresponding to the reference strokes correspondingly matched with the writing strokes; and determining second geometric information corresponding to the reference strokes correspondingly matched with the writing strokes according to at least one of second position information, second length information and second inclination angle information of the reference strokes correspondingly matched with the writing strokes.

Optionally, the determining, according to the first geometric information and the second geometric information, first loss information between the writing stroke and a reference stroke corresponding to the writing stroke includes: determining first position loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to the first position information and the second position information; and/or determining first length loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first length information and the second length information; and/or determining first inclination angle loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first inclination angle information and the second inclination angle information; and determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to at least one of the first position loss information, the first length loss information and the first inclination angle loss information.

Optionally, the evaluating the normalization of the writing of the user according to the first loss information includes: and evaluating the normalization of the written strokes written by the user according to the first loss information.

Optionally, the first loss information includes first position loss information, first length loss information, and first inclination angle information; the evaluating the normalization of the writing strokes written by the user according to the first loss information comprises the following steps: if the first position loss information exceeds a position loss range, evaluating the position normalization of the writing strokes written by the user; if the first length loss information exceeds a length loss range, evaluating the length normalization of the writing strokes written by the user; and if the first inclination angle loss information exceeds the inclination angle loss range, evaluating the inclination angle normalization of the writing strokes written by the user.

Optionally, the writing stroke includes a plurality of writing strokes, and evaluating normalization of the writing of the user according to the first loss information includes: determining second loss information between the written text formed by all the writing strokes and the reference text according to the first loss information between each writing stroke and the reference stroke correspondingly matched with each writing stroke; and evaluating normalization of the written text formed by the written strokes written by the user according to the second loss information.

Optionally, the first loss information includes: first position loss information, first length loss information, and first inclination angle information; determining second loss information between the written text formed by all the writing strokes and the reference text according to the first loss information between each writing stroke and the reference stroke correspondingly matched with each writing stroke, wherein the second loss information comprises the following steps: calculating the average value of the first position loss information of each writing stroke to obtain second position loss information between the writing text and the reference text; and/or calculating the average value of the first length loss information of each writing stroke to obtain second length loss information between the writing text and the reference text; and/or calculating a first inclination angle loss information average value of each writing stroke to obtain second inclination angle loss information between the writing text and the reference text; and/or acquiring stroke number loss information and/or stroke order loss information between the written text and the reference text; and/or, obtaining the total reference strokes corresponding to the reference text; and determining second loss information between the writing text formed by all writing strokes and the reference text according to the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke sequence loss information and at least one of the reference total stroke number.

Optionally, the evaluating the normalization of the written text formed by the writing strokes written by the user according to the second loss information includes: determining a writing loss score corresponding to the writing text according to the second loss information; and evaluating the normalization of the written text formed by the written strokes written by the user according to the writing loss score.

Optionally, the evaluating the normalization of the written text formed by the writing strokes written by the user according to the writing loss score includes: when the writing loss score is greater than or equal to a preset loss score, generating writing positive evaluation information aiming at the writing text; and when the writing loss score is smaller than a preset loss score, generating writing negative evaluation information aiming at the writing text.

Optionally, the second loss information includes stroke loss information and/or stroke order loss information; and evaluating normalization of the written text formed by the written strokes written by the user according to the second loss information, wherein the evaluation comprises the following steps: if the stroke loss information is not equal to zero, evaluating the stroke number normalization of the written text; and if the stroke order loss information is not equal to zero, evaluating the stroke order normalization of the written text.

The embodiment of the invention also discloses an evaluation device, which specifically comprises: the acquisition module is used for acquiring track information of writing strokes written by a user; the matching module is used for determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke; a determining module for determining first loss information between the writing stroke and a reference stroke corresponding to the writing stroke; and the evaluation module is used for evaluating the normalization of the writing of the user according to the first loss information.

Optionally, the track information includes coordinate information of a plurality of track points, and the matching module is configured to obtain track information of each reference stroke; inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model; the point cloud mapping model determines a track relation based on coordinate information of track points in the track information, and outputs a reference stroke identifier of a reference stroke, the matching degree of which accords with a preset range, according to the track relation; determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identifier; wherein the track relationship comprises at least one of a first relationship, a second relationship, and a third relationship; the first relationship includes a relationship between the writing stroke and a corresponding track point of a reference stroke, the second relationship includes a relationship between track points of the writing stroke, and the third relationship includes a relationship between track points of the reference stroke.

Optionally, the determining module includes: the first geometric information determining submodule is used for determining the first geometric information of the writing strokes according to the track information of the writing strokes; the second geometric information determining submodule is used for determining second geometric information of the reference strokes correspondingly matched with the writing strokes according to track information of the reference strokes correspondingly matched with the writing strokes; and the first loss information determining submodule is used for determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to the first geometric information and the second geometric information.

Optionally, the track information includes coordinate information of a plurality of track points; the first geometric information determining submodule is used for determining at least one of first position information, first length information and first inclination angle information of the writing strokes according to coordinate information of the writing strokes corresponding to each track point; determining first geometric information corresponding to the writing stroke according to at least one of first position information, first length information and first inclination angle information of the writing stroke; the second geometric information determining submodule is used for determining at least one of second position information, second length information and second inclination angle information of the reference strokes corresponding to the writing strokes according to the coordinate information of the track points corresponding to the reference strokes corresponding to the writing strokes; and determining second geometric information corresponding to the reference strokes correspondingly matched with the writing strokes according to at least one of second position information, second length information and second inclination angle information of the reference strokes correspondingly matched with the writing strokes.

Optionally, the first loss information determining submodule is used for determining first position loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to the first position information and the second position information; and/or determining first length loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first length information and the second length information; and/or determining first inclination angle loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first inclination angle information and the second inclination angle information; and determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to at least one of the first position loss information, the first length loss information and the first inclination angle loss information.

Optionally, the evaluation module includes: and the stroke evaluation sub-module is used for evaluating the normalization of the writing strokes written by the user according to the first loss information.

Optionally, the first loss information includes first position loss information, first length loss information, and first inclination angle information; the stroke evaluation sub-module is used for evaluating the position normalization of the writing stroke written by the user if the first position loss information exceeds a position loss range; if the first length loss information exceeds a length loss range, evaluating the length normalization of the writing strokes written by the user; and if the first inclination angle loss information exceeds the inclination angle loss range, evaluating the inclination angle normalization of the writing strokes written by the user.

Optionally, the writing stroke includes a plurality of, the evaluation module includes: the second loss information determining submodule is used for determining second loss information between the written text formed by all the written strokes and the reference text according to the first loss information between each written stroke and the reference stroke correspondingly matched with each written stroke; and the text evaluation sub-module is used for evaluating the normalization of the written text formed by the writing strokes written by the user according to the second loss information.

Optionally, the first loss information includes: first position loss information, first length loss information, and first inclination angle information; the second loss information determining submodule is used for calculating the average value of the first position loss information of each writing stroke and obtaining second position loss information between the writing text and the reference text; and/or calculating the average value of the first length loss information of each writing stroke to obtain second length loss information between the writing text and the reference text; and/or calculating a first inclination angle loss information average value of each writing stroke to obtain second inclination angle loss information between the writing text and the reference text; and/or acquiring stroke number loss information and/or stroke order loss information between the written text and the reference text; and/or, obtaining the total reference strokes corresponding to the reference text; and determining second loss information between the writing text formed by all writing strokes and the reference text according to the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke sequence loss information and at least one of the reference total stroke number.

Optionally, the text evaluation sub-module includes: the loss score evaluation unit is used for determining a writing loss score corresponding to the writing text according to the second loss information; and evaluating the normalization of the written text formed by the written strokes written by the user according to the writing loss score.

Optionally, the loss score evaluation unit is configured to generate writing positive evaluation information for the writing text when the writing loss score is greater than or equal to a preset loss score; and when the writing loss score is smaller than a preset loss score, generating writing negative evaluation information aiming at the writing text.

Optionally, the second loss information includes stroke loss information and/or stroke order loss information; the text evaluation submodule comprises: a loss information evaluation unit, configured to evaluate, if the stroke loss information is not equal to zero, a stroke number normalization of the written text; and if the stroke order loss information is not equal to zero, evaluating the stroke order normalization of the written text.

The embodiment of the invention also discloses a readable storage medium, which enables the electronic equipment to execute the evaluation method according to any one of the embodiments of the invention when the instructions in the storage medium are executed by the processor of the electronic equipment.

The embodiment of the invention also discloses an electronic device, which comprises: one or more processors; and one or more readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform the evaluation method according to any one of the embodiments of the present invention

The embodiment of the invention has the following advantages:

in the embodiment of the invention, the track information of each writing stroke written by the user can be obtained in the writing process of the user; then, determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke, and determining first loss information between the writing stroke and the reference stroke corresponding to the writing stroke; evaluating the normalization of the writing of the user according to the first loss information; compared with the prior art, the method and the device for comparing the writing text with the corresponding reference text integrally have finer granularity, so that accuracy of evaluating writing normalization can be improved.

Drawings

FIG. 1 is a flow chart of the steps of an embodiment of an evaluation method of the present invention;

FIG. 2 is a flow chart of the steps of an alternative embodiment of an evaluation method of the present invention;

FIG. 3 is a flow chart of steps of an alternative embodiment of an evaluation method of the present invention;

FIG. 4 is a block diagram showing the construction of an embodiment of an evaluation apparatus of the present invention;

FIG. 5 is a block diagram of an alternative embodiment of an evaluation device of the present invention;

FIG. 6 illustrates a block diagram of an electronic device for evaluation, according to an exemplary embodiment;

fig. 7 is a schematic structural view of an electronic device for evaluation according to another exemplary embodiment of the present invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.

In the embodiment of the invention, a webpage or an application program or an applet or a tool can be provided, and a user can enter a writing interface by opening the webpage or the application program or the applet or the tool; and the user can write on the writing interface. The user can write directly on the touch screen or through an external writing board, and the embodiment of the invention is not limited to the above.

One of the core concepts of the embodiment of the invention is that the normalization of the writing of the user is evaluated by comparing the writing strokes written by the user with the reference strokes corresponding to the reference text; compared with the prior art, the method and the device for comparing the writing text with the reference text are finer in granularity compared with the whole writing text, and further accuracy of evaluating writing normalization can be improved.

Referring to fig. 1, a flowchart illustrating steps of an embodiment of an evaluation method of the present invention may specifically include the following steps:

step 102, obtaining track information of writing strokes written by a user.

And 104, determining the reference strokes corresponding to and matched with the writing strokes from the reference strokes corresponding to the reference text according to the track information of the writing strokes.

In one example of the invention, a user can select a text to be written on a writing interface, and correspondingly, a reference text can be provided on the writing interface; and the user can write with reference to the reference text with the writing interface raised. The reference text may include text in various languages, such as chinese, korean, japanese, etc., which the embodiments of the present invention do not limit. The reference text may be various fonts, for example, when the language of the reference text is chinese, the corresponding fonts may include Song Ti, regular script, bold, script, etc., which the embodiments of the present invention also do not limit.

In yet another example of the present invention, the user may also directly write text on the writing interface without selecting the text to be written on the writing interface; and thus, there is no need to provide reference text at the writing interface.

In the embodiment of the invention, the track information of the written strokes can be obtained in the process of writing one stroke by the user. Wherein, the writing strokes can refer to strokes written by a user in the writing process; the trajectory information of the writing stroke may be used to characterize the trajectory of the writing stroke, and may include coordinate information of a plurality of trajectory points. Then, for each writing stroke written by the user, reference strokes corresponding to and matched with the writing strokes can be searched for respectively.

In one example of the present invention, one way to find the reference strokes that are correspondingly matched with the writing strokes, respectively, may be: if the user writes with reference to the reference text, the reference stroke matched with the writing stroke can be searched from the reference strokes of the reference text based on the track information of the writing stroke after the track information of one writing stroke is obtained. One way to find the reference strokes that match each writing stroke, respectively, may be: if the user writes with reference to the reference text, after the track information of all writing strokes is obtained, the reference strokes matched with each writing stroke can be searched from the reference strokes of the reference text based on the track information of each writing stroke. Wherein, the reference strokes may refer to strokes constituting the reference text.

In one example of the present invention, one way to find the reference strokes that are correspondingly matched with the writing strokes, respectively, may be: if the user does not write with reference to the reference text, text recognition can be performed on the written text formed by the written strokes written by the user after track information of all the written strokes is acquired, and the reference text matched with the written text is determined. And then searching the reference strokes matched with each writing stroke from the reference strokes of the reference text based on the track information of each writing stroke.

For example, take the Chinese character "big" as an example; the "big" word includes 3 strokes: transverse, skim and right-falling; the reference strokes corresponding to the reference text may also include 3: reference stroke 1 ("horizontal"), reference stroke 2 ("left-falling"), and reference stroke 3 ("right-falling"). In the process of writing a large word by a user, if the user writes skimming first and then transverse, finally writing right-falling; the 3 writing strokes written by the user may include: writing stroke 1 ("skim"), writing stroke 2 ("cross") and writing stroke 3 ("right") are described. A reference stroke such as reference stroke 2 matching the writing stroke 1 can be determined from 3 reference strokes based on the track information of the writing stroke 1; determining a reference stroke such as reference stroke 1 matched with the writing stroke 2 from 3 reference strokes according to the track information of the writing stroke 2; and determining a reference stroke, such as reference stroke 3, matching the writing stroke 3 from the 3 reference strokes based on the trajectory information of the writing stroke 3.

The normalization of the user writing may then be evaluated by comparing the written strokes with the corresponding matched reference strokes, which may be referred to steps 106-108:

step 106, determining first loss information between the writing stroke and a reference stroke corresponding to the writing stroke.

And step 108, evaluating the normalization of the writing of the user according to the first loss information.

In the embodiment of the invention, aiming at each writing stroke written by a user, the writing stroke can be compared with the corresponding matched reference stroke, and the difference between the writing stroke and the corresponding matched reference stroke is determined; in other words, a loss between the writing stroke and the corresponding matching reference stroke is determined. Wherein the first loss information may be employed to characterize losses between the written stroke and the corresponding matching reference stroke. Wherein, each writing stroke corresponds to a first loss information with the corresponding matched reference stroke.

In one example of the present invention, steps 104-106 may be performed after each acquisition of the trajectory information of a writing stroke.

In yet another example of the present invention, steps 104 to 106 may be performed for each writing stroke after the user finishes writing and obtains track information of all writing strokes.

After determining the first loss information between each writing stroke and the corresponding matched reference stroke, the normalization of the user writing can be evaluated according to the first loss information between each writing stroke and the corresponding matched reference stroke. The evaluation of the normalization of the writing of the user can comprise the normalization evaluation of each stroke of the writing of the user, and can also comprise the normalization evaluation of a writing text formed by the strokes of the writing of the user; the embodiments of the present invention are not limited in this regard. When the evaluation of the normalization of the writing of the user is that each writing stroke of the writing of the user is subjected to normalization evaluation, the normalization evaluation may be that after the user writes one writing stroke and steps 104 to 106 are executed for the writing stroke, the normalization evaluation is performed for the writing stroke; after the user writes all the writing strokes and performs steps 104 to 106 for each writing stroke, normalization evaluation may be performed on all the writing strokes. The normalization evaluation of the written text formed by the strokes written by the user may be performed after the user has written all the written strokes and performed steps 104 to 106 for each written stroke.

In addition, the evaluation of the normalization of the user writing may further include determination of the normalization of the user writing, suggestion of the normalization of the user writing, and so on, which is not limited by the embodiment of the present invention.

In summary, in the embodiment of the invention, in the process of writing by a user, track information of each writing stroke written by the user can be obtained; then, determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke, and determining first loss information between the writing stroke and the reference stroke corresponding to the writing stroke; evaluating the normalization of the writing of the user according to the first loss information; compared with the prior art, the method and the device for comparing the writing text with the corresponding reference text integrally have finer granularity, so that accuracy of evaluating writing normalization can be improved.

The following describes, as an example, a case where a user writes with reference to a reference text, a case where normalization of a written stroke written by the user is evaluated.

Referring to fig. 2, a flowchart illustrating steps of an alternative embodiment of an evaluation method of the present invention may specifically include the steps of:

Step 202, obtaining track information of writing strokes written by a user in the process of writing by the user referring to the reference text.

In the embodiment of the invention, the track information can comprise coordinate information of a plurality of track points, and the coordinate information of the track points can be pixel point coordinate information of the track points corresponding to a display interface of the written strokes; the coordinate information may include an abscissa and an ordinate.

When a user writes on the touch screen directly, pixel point coordinates of a plurality of touch points touched by the user in the process of writing any stroke can be obtained; then, coordinate information of the writing strokes corresponding to a plurality of track points is generated by adopting the acquired pixel point coordinates of the plurality of touch points; one of the touch points may correspond to one of the track points. When a user writes through an externally connected writing board, the coordinates of a plurality of touch points touched by the user in the process of writing any stroke can be obtained; correspondingly converting the handwriting board coordinates of the touch points into pixel point coordinates of the touch points in the display interface; and then collecting pixel point coordinates of the plurality of touch points obtained through conversion, and generating coordinate information of the writing strokes corresponding to the plurality of track points.

The coordinate information of the plurality of track points in the track information corresponding to each writing stroke may be arranged according to the sequence of track points generated when the user writes the writing stroke.

Then, determining the reference strokes corresponding to and matched with the writing strokes from the reference strokes corresponding to the reference text according to the track information of the writing strokes; reference may be made to steps 204-208:

step 204, obtaining track information of each reference stroke of the reference text.

In the embodiment of the invention, the track information of each reference stroke of the reference text can be acquired; and then comparing the track information of each writing stroke with the track information of each reference stroke for each writing stroke to determine the reference stroke matched with the writing stroke.

Of course, the track information of the writing strokes also comprises coordinate information of a plurality of track points; the coordinate information of the plurality of track points in the track information corresponding to each reference stroke may be arranged in the order of track points generated when writing the reference stroke.

And 206, inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model to obtain the reference stroke identification output by the point cloud mapping model.

In an alternative embodiment of the present invention, a point cloud mapping method may be used to determine a reference stroke for a writing stroke that matches it accordingly. The point cloud mapping model can be trained in advance by adopting a machine learning mode; the point cloud mapping model can learn the mapping relation between the writing strokes and the reference strokes. And further, a trained point cloud mapping model can be adopted to determine the matched reference strokes of all writing strokes.

A written stroke will now be described as an example. For one writing stroke, the track information of the writing stroke and the track information of each reference stroke can be input into a trained point cloud mapping model; and comparing the track information of the writing strokes with the track information of each reference stroke respectively by using a point cloud mapping model based on a mapping relation learned in advance, and determining the reference strokes which are correspondingly matched with the writing strokes.

In an optional embodiment of the present invention, the inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model to obtain the reference stroke identifier output by the point cloud mapping model may include: the point cloud mapping model determines a track relation based on coordinate information of track points in the track information; and outputting a reference stroke identifier of the reference stroke, the matching degree of which accords with a preset range, according to the track relation. Wherein the track relationship comprises at least one of a first relationship, a second relationship, and a third relationship; the first relationship includes a relationship between the writing stroke and corresponding track points of the reference stroke, the second relationship includes a relationship between track points of the writing stroke, and the third relationship includes a relationship between track points of the reference stroke.

In one embodiment of the present invention, when the track relationship includes one of the first relationship, the second relationship, and the third relationship, the track relationship may include the first relationship. When the track relationship includes two of the first relationship, the second relationship, and the third relationship, the track relationship may include the second relationship and the third relationship.

After the point cloud mapping model obtains the track information of the writing stroke and the track information of each reference stroke, the relation between the writing stroke and each reference stroke can be respectively determined through the point cloud mapping. The track information corresponding to the reference stroke and the track information corresponding to the writing stroke can be determined according to the arrangement sequence of the track points in the track information corresponding to the reference stroke and the arrangement sequence of the track points in the track information corresponding to the writing stroke. For convenience of subsequent description, each pair of corresponding track points in the track information corresponding to the reference stroke and the track information corresponding to the writing stroke may be referred to as a pair of track points; among them, the track point belonging to the reference stroke in the pair of track points may be referred to as a reference track point, and the track point belonging to the writing stroke is referred to as a writing track point. Then, for each pair of track points, a relationship between two track points in the pair of track points is determined based on the coordinate information of the writing track point and the coordinate information of the reference track point in the pair of track points. And generating a first relation, namely a first relation between the writing stroke and the track point corresponding to the reference stroke, based on the relation between the two track points in each pair of track points corresponding to the writing stroke and the reference stroke. And then the first relation between the writing stroke and the corresponding track point of each reference stroke can be obtained according to the mode.

In addition, the point cloud mapping model can also determine a second relation among the track points in the writing stroke according to the coordinate information of the track points in the writing stroke. And for each reference stroke, the point cloud mapping model can determine a third relation among track points in the reference stroke according to the coordinate information of the track points corresponding to the reference stroke; and a third relationship between the track points in the reference strokes can be obtained.

The preset range may be set according to requirements, which is not limited in the embodiment of the present invention. In one example, a reference stroke identification of a reference stroke having a highest degree of matching with the written stroke may be output according to the trajectory relationship.

In an optional embodiment of the present invention, the point cloud mapping model may include a point cloud mapping module and a matching module, where the point cloud mapping module is connected to the matching module, and the point cloud mapping module is disposed before the matching module. The point cloud mapping model may be used to determine relationships between various track points in the track information, and the matching module may be used to determine reference strokes that correspondingly match the writing strokes.

The method comprises the following substeps 2062 to 2064, wherein the point cloud mapping model determines a track relation based on coordinate information of track points in the track information, and outputs a reference stroke identifier of a reference stroke with the matching degree of the writing stroke conforming to a preset range according to the track relation:

Step 2062, inputting the track information of the writing strokes and the track information of each reference stroke into the point cloud mapping model, wherein the point cloud mapping model determines track relations based on the coordinate information of track points in the track information and inputs the track relations into the matching module.

In step 2064, the matching module outputs a reference stroke identifier of the reference stroke with the matching degree of the writing stroke conforming to the preset range according to the track relationship.

In the embodiment of the invention, the track information of the writing strokes and the track information of each reference stroke can be input into the point cloud mapping model; after the point cloud mapping model obtains the track information of the writing stroke and the track information of each reference stroke, the relation between the writing stroke and each reference stroke can be respectively determined through the point cloud mapping. Wherein, for the writing stroke and a reference stroke, the track points corresponding to the reference stroke and the track information corresponding to the writing stroke can be determined according to the arrangement sequence of the track points in the track information corresponding to the reference stroke and the arrangement sequence of the track points in the track information corresponding to the writing stroke; for convenience of the following description, each pair of corresponding track points in the track information corresponding to the reference stroke and the track information corresponding to the writing stroke may be referred to as a pair of track points. Among them, the track point belonging to the reference stroke in the pair of track points may be referred to as a reference track point, and the track point belonging to the writing stroke is referred to as a writing track point. Then, for each pair of track points, a relationship between two track points in the pair of track points is determined based on the coordinate information of the writing track point and the coordinate information of the reference track point in the pair of track points. And generating a first relation, namely a first relation between the writing stroke and the track point corresponding to the reference stroke, based on the relation between the two track points in each pair of track points corresponding to the writing stroke and the reference stroke. And then the first relation between the writing stroke and the corresponding track point of each reference stroke can be obtained according to the mode.

In addition, the point cloud mapping model may determine a second relationship between each track point in the writing stroke according to the coordinate information of each track point in the writing stroke. And for each reference stroke, the point cloud mapping model can determine a third relation among track points in the reference stroke according to the coordinate information of the track points corresponding to the reference stroke; and a third relationship between the track points in the reference strokes can be obtained.

Further, a track relation is obtained based on at least one relation among the first relation, the second relation and the third relation; then the point cloud mapping model sends the track relation to a matching module; a reference stroke matching the writing stroke is determined from the plurality of reference strokes based on the trajectory relationship by the matching module, and a reference stroke identification of the reference stroke matching the writing stroke is output.

Wherein the reference stroke identification may be used to uniquely identify a reference stroke; the reference stroke identification of reference stroke 1 in the example above may be: RE_1, the reference stroke identification for reference stroke 2 may be: RE_2, the reference stroke identification of reference stroke 3 may be: re_3.

In one example of the present invention, the algorithm employed by the matching module may be an EM (Expectation-maximization) algorithm.

Step 208, determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identification.

A reference stroke matching the written stroke may then be determined based on the reference stroke identification output by the point cloud mapping model.

Further, the corresponding matching reference strokes for each writing stroke may be determined through steps 206-208 described above.

Determining the first loss information between the writing stroke and the corresponding matched reference stroke, referring to the following steps 210-214:

step 210, determining first geometric information of the writing stroke according to the track information of the writing stroke.

Step 212, determining second geometric information of the reference strokes correspondingly matched with the writing strokes according to the track information of the reference strokes correspondingly matched with the writing strokes.

Step 214, determining first loss information between the writing stroke and the reference stroke correspondingly matched with the writing stroke according to the first geometric information and the second geometric information.

In an embodiment of the present invention, steps 210-214 may be performed for each writing stroke to determine first loss information between the writing stroke and a corresponding matching reference stroke.

A written stroke will now be described as an example. Wherein, the geometric information of the writing stroke and the geometric information of the reference stroke correspondingly matched with the writing stroke can be respectively determined; first loss information between the writing stroke and a reference stroke corresponding to the writing stroke is then determined based on geometric information of the writing stroke and the reference stroke corresponding to the writing stroke. In one example, the geometric information may include various types of information, such as position information, length information, inclination angle information, and the like, to which embodiments of the present invention are not limited.

The step 210 may include the following sub-steps 2102 to 2104:

and a sub-step 2102 of determining at least one of first position information, first length information and first inclination angle information of the writing stroke according to the coordinate information of each track point corresponding to the writing stroke.

In one example, a center point of the writing stroke may be determined according to coordinate information of the writing stroke corresponding to each track point; the coordinate information of the center is then determined as first position information of the writing stroke. In one example, an average value of the abscissa may be calculated according to the abscissa of each trace point corresponding to the writing stroke; calculating an average value of the ordinate according to the ordinate of each track point corresponding to the writing stroke; and then searching the track points with the closest abscissa and the closest ordinate average value from the track points corresponding to the writing strokes, and taking the track point with the closest ordinate and the closest ordinate average value as a center point. In another example, a middle locus point among the locus points corresponding to the writing stroke may be set as the center point. Of course, the center point of the writing stroke may be determined in other ways, as well, and embodiments of the invention are not limited in this respect. In addition, the first location information of the writing stroke may be determined in other manners, which are not limited by embodiments of the present invention.

In one example, the length of the writing stroke may be calculated according to the coordinate information of the writing stroke corresponding to each track point; the length of the written stroke is then used as the length information of the written stroke. The length calculation mode of the writing strokes can be as follows:

wherein L1 is the length of the writing stroke; (A1, B1) is coordinate information of a first trajectory point of the writing stroke; (A2, B2) is coordinate information of a second trajectory point of the writing stroke; (An, bn) is the coordinate information of the nth trace point of the writing stroke, n is a positive integer.

In one example, a slope corresponding to each track point in the writing stroke may be calculated according to coordinate information of each track point corresponding to the writing stroke; and then determining first inclination angle information based on the corresponding slope of each track point in the writing stroke. In one example, the largest slope among the slopes corresponding to all the track points may be determined as the first inclination angle information.

Substep 2104 determines first geometric information corresponding to the writing stroke according to at least one of the first position information, the first length information and the first inclination angle information of the writing stroke.

In an alternative embodiment of the present invention, at least one of the first position information, the first length information, and the first inclination angle information of the writing stroke may be used to generate the first geometric information corresponding to the writing stroke. In one example, the first geometric information may include: first position information, first length information, and first inclination angle information.

Of course, when other geometric information related to the writing stroke is determined, the first geometric information is then generated using at least one of the first position information, the first length information, and the first inclination angle information described above, and other geometric information.

The step 212 may include the following sub-steps 2122 to 2124:

sub-step 2122, determining at least one of second position information, second length information and second inclination angle information of the reference stroke corresponding to the writing stroke according to coordinate information of each track point corresponding to the reference stroke corresponding to the writing stroke.

Sub-step 2124, determining second geometric information corresponding to the reference stroke corresponding to the writing stroke according to at least one of second position information, second length information and second inclination angle information of the reference stroke corresponding to the writing stroke.

Sub-steps 2122 to 2124 are similar to sub-steps 2102 to 2104 described above, and are not described in detail herein.

Wherein the second geometric information may be predetermined or may be determined in the process of determining the first loss information between the writing stroke and the corresponding matched reference stroke, which is not limited by the embodiment of the present invention.

Then, according to the first geometric information and the second geometric information, determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke; reference may be made to sub-steps 2142 to 2144:

a substep 2142, determining, according to the first position information and the second position information, first position loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke; and/or determining first length loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first length information and the second length information; and/or determining first inclination angle loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first inclination angle information and the second inclination angle information.

In one example of the present invention, a loss of position between a writing stroke and a reference stroke that corresponds to a writing stroke may be determined based on the position of the writing stroke and the position of the reference stroke that corresponds to the writing stroke. In one example, an L2 norm may be calculated based on first location information of a writing stroke and second location information of a reference stroke that corresponds to the writing stroke, and first location loss information between the writing stroke and the reference stroke that corresponds to the writing stroke may be obtained. For example, the following formula can be referred to:

Pi is second position loss information between the ith writing stroke and the corresponding matched reference stroke; (Ai, bi) first position information of the ith writing stroke, (Ci, di) second position information of the reference stroke corresponding to the ith writing stroke.

In one example of the present invention, a length loss between a writing stroke and a reference stroke that corresponds to a writing stroke may be determined based on the length of the writing stroke and the length of the reference stroke that corresponds to the writing stroke. In one example, an L2 norm may be calculated based on first length information of a writing stroke and second length information of a reference stroke corresponding to the writing stroke, and first length loss information between the writing stroke and the reference stroke corresponding to the writing stroke may be obtained. For example, the following formula can be referred to:

wherein Li is first length loss information between the ith writing stroke and the corresponding matched reference stroke; li1 is the first length information of the ith writing stroke, and Li2 is the second length information of the reference stroke corresponding to the ith writing stroke.

In one example of the present invention, the tilt angle loss between a writing stroke and a reference stroke corresponding to the writing stroke may be calculated from the tilt angle of the writing stroke and the tilt angle of the reference stroke corresponding to the writing stroke. In one example, the L2 norm may be calculated based on first tilt angle information of a writing stroke and second tilt angle information of a reference stroke corresponding to the writing stroke, and first tilt angle loss information between the writing stroke and the reference stroke may be obtained. For example, the following formula can be referred to:

Wherein θi is first inclination angle loss information between the ith writing stroke and the corresponding matched reference stroke; θi1 is the first inclination angle information of the ith writing stroke, and θi2 is the second inclination angle information of the reference stroke corresponding to the ith writing stroke.

Substep 2144, determining, according to the at least one of the first position loss information, the first length loss information, and the first inclination angle loss information, first loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke.

And further, at least one of the first position loss information, the first length loss information and the first inclination angle loss information may be used to generate first loss information between the writing stroke and the corresponding matched reference stroke. When two or more of the first position loss information, the first length loss information and the first inclination angle loss information are adopted to generate first loss information between the writing strokes and the corresponding matched reference strokes, the first position loss information, the first length loss information and the first inclination angle loss information can be respectively used as one dimension of the first loss information; that is, the first loss information may include a plurality of dimensions, the first position loss information corresponds to a position dimension, the first length loss information corresponds to a length dimension, and the first inclination angle information corresponds to an inclination angle dimension.

Of course, when other geometric information is determined as described above, the first loss information may further include loss information of other dimensions, which is not limited in the embodiment of the present invention.

After determining first loss information between the writing stroke and the corresponding matched reference stroke, evaluating normalization of the writing of the user according to the first loss information; reference may be made to step 216:

and step 216, evaluating the normalization of the writing strokes written by the user according to the first loss information.

In the embodiment of the invention, the normalization evaluation can be carried out on each writing stroke written by the user according to the first loss information of each writing stroke. The normalization evaluation can be performed on the writing strokes written by the user after the user writes one writing stroke, or can be performed on all writing strokes written by the user after the user writes all writing strokes.

Step 216 may include the following: sub-step 2162 and/or sub-step 2164 and/or sub-step 2166; wherein sub-steps 2162-2166 are for the evaluation of normalization of a written stroke.

Sub-step 2162, if the first position loss information exceeds the position loss range, evaluates the position normalization of the writing strokes written by the user.

Sub-step 2164, if the first length loss information exceeds the length loss range, evaluates the length normalization of the writing strokes written by the user.

Sub-step 2166, if the first tilt angle loss information exceeds the tilt angle loss range, evaluates the tilt angle normalization of the writing stroke written by the user.

For each writing stroke, it may be determined whether the first position loss information of the writing stroke and the corresponding matched reference stroke exceeds a preset position loss range. If the first position loss information of the writing stroke and the corresponding matched reference stroke exceeds the position loss range, the position of the writing stroke is far away from the position of the corresponding matched reference stroke, and at the moment, the position normalization of the writing stroke written by the user can be evaluated by combining the first position information of the writing stroke and the second position information of the corresponding matched reference stroke. For example, if the ordinate of the first position information is greater than the ordinate of the second position information, the normalization determination information may be displayed as "on the horizontal side" or the normalization advice information may be displayed as "on the horizontal side". For example, if the abscissa based on the first position information is smaller than the abscissa based on the second position information, the normalized decision information may be displayed as "right-to-left" or as "right-to-right" as "normalized advice information. The location loss range may be set as desired, and embodiments of the present invention are not limited in this regard.

For each writing stroke, it may be determined whether the first length loss information of the writing stroke and the corresponding matching reference stroke is out of length loss range. If the first length loss information of the writing stroke and the corresponding matched reference stroke exceeds the length loss range, the length of the writing stroke is larger than the length of the corresponding matched reference stroke. At this time, the length normalization of the writing stroke written by the user may be evaluated in combination with the first length information of the writing stroke and the second length information of the corresponding matched reference stroke. For example, if the first length information is greater than the second length information, the normalization determination information is displayed "too long" and/or the normalization suggestion information such as "short for horizontal rewriting" is displayed. If the first length information is smaller than the second length information, the normalization determination information is displayed as "too short" and/or the normalization suggestion information is displayed as "longer-to-write". The length loss range may be set as desired, and embodiments of the present invention are not limited in this regard.

For each writing stroke, it may be determined whether the first tilt angle loss information of the writing stroke and the corresponding matching reference stroke is outside the tilt angle loss range. If the first inclination angle loss information of the writing stroke and the corresponding matched reference stroke exceeds the inclination angle loss range, the inclination angle of the writing stroke is larger than the inclination angle of the corresponding matched reference stroke. The inclination angle normalization of the writing stroke written by the user can be evaluated by combining the first inclination angle information of the writing stroke and the second inclination angle information of the corresponding matched reference stroke. For example, if the first inclination angle information is greater than the second inclination angle information, the normative determination information "too much skimming" is displayed, and/or the normative advice information such as "the inclination angle of skimming is slightly eased" is displayed. If the first inclination angle information is smaller than the second inclination angle information, the normative judgment information of "insufficient skimming inclination" is displayed, and/or the normative suggestion information such as "skimming inclination slightly larger" is displayed. The tilt angle loss range may be set as desired, and embodiments of the present invention are not limited in this regard.

In summary, in the embodiment of the present invention, track information of each reference stroke may be obtained, and then track information of the writing stroke and track information of each reference stroke are input into a point cloud mapping model trained in advance, so as to obtain a reference stroke identifier output by the point cloud mapping model; determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identifier; because the pre-trained point cloud mapping model learns the mapping relation between the writing strokes and the reference strokes, the embodiment of the invention can accurately determine the reference strokes matched with the writing strokes.

Secondly, in the embodiment of the invention, the point cloud mapping model comprises a point cloud mapping module and a matching module, the track information of the writing strokes and the track information of each reference stroke can be input to the point cloud mapping module, and the point cloud mapping model determines track relations based on the coordinate information of track points in the track information and inputs the track relations to the matching module; then, outputting a reference stroke identifier of a reference stroke with the highest matching degree with the writing stroke by the matching module according to the track relation; the track relation can comprise a first relation, a second relation and a third relation, wherein the first relation comprises a relation between corresponding track points of the writing stroke and the reference stroke, the second relation comprises a relation between track points of the writing stroke, and the third relation comprises a relation between track points of the reference stroke; compared with the point cloud mapping method in the prior art, which only determines the relation between the corresponding track points of the writing strokes and the reference strokes, the embodiment of the invention also determines the relation between the track points of the writing strokes and the relation between the track points of the reference strokes; and the reference strokes matched with the writing strokes can be searched based on richer information, so that the accuracy of determining the reference strokes matched with the writing strokes can be further increased.

Further, in the embodiment of the present invention, the first geometric information of the writing stroke may be determined according to the track information of the writing stroke; determining second geometric information of the reference strokes correspondingly matched with the writing strokes according to track information of the reference strokes correspondingly matched with the writing strokes; then determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to the first geometric information and the second geometric information; and then the difference between the written strokes and the reference strokes matched with the corresponding rows is accurately determined according to the geometric relationship between the written strokes and the reference strokes. And the first loss information may include: first position loss information, first length loss information, and first inclination angle loss information; and the difference between the writing stroke and the reference stroke correspondingly matched with the writing stroke can be described from a plurality of dimension geometric dimensions, so that the determined first loss information is more comprehensive, and the difference between the two accurate determinations can be further improved.

Further, in the embodiment of the present invention, the normalization of the writing strokes written by the user may be evaluated according to the first loss information; and furthermore, each stroke written by the user can be subjected to normalization evaluation, so that the user can conveniently write from each stroke in a normalization manner, and the writing level can be improved.

Thirdly, if the first position loss information exceeds a position loss range, evaluating the position normalization of the writing strokes written by the user; and/or if the first length loss information exceeds a length loss range, evaluating the length normalization of the writing strokes written by the user; and/or if the first inclination angle loss information exceeds the inclination angle loss range, evaluating the inclination angle normalization of the writing strokes written by the user; furthermore, each stroke written by the user is evaluated from multiple dimensions, so that the comprehensiveness of the handwriting normalization evaluation of the user is improved; and may also facilitate increased writing levels.

In an alternative embodiment of the present invention, normalization may also be performed on a written text formed by a written stroke written by a user, and may be as follows:

referring to fig. 3, a flowchart illustrating steps of an alternative embodiment of an evaluation method of the present invention may specifically include the steps of:

step 302, obtaining track information of writing strokes written by a user in the process of writing by the user referring to the reference text.

Step 304, obtaining track information of each reference stroke of the reference text.

And 306, inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model to obtain the reference stroke identification output by the point cloud mapping model.

Step 308, determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identification.

Step 310, determining first geometric information of the writing stroke according to the track information of the writing stroke.

Step 312, determining second geometric information of the reference strokes correspondingly matched with the writing strokes according to the track information of the reference strokes correspondingly matched with the writing strokes.

Step 314, determining first loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first geometric information and the second geometric information.

Steps 302 to 314 are similar to steps 202 to 214, and are not repeated here.

Step 316, determining second loss information between the written text formed by all the writing strokes and the reference text according to the first loss information between each writing stroke and the reference stroke correspondingly matched with each writing stroke.

In the embodiment of the invention, the second loss information between the written text formed by all the written strokes written by the user and the reference text can be determined according to the first loss information between each written stroke and the corresponding matched reference stroke. Then, according to the second loss information, evaluating the normalization of the written text formed by the written strokes written by the user; i.e. step 318 is performed. On the other hand, the second loss information can be converted into a writing loss score, and then the normalization of the writing text formed by the writing strokes written by the user is evaluated based on the writing loss score; i.e. step 320 is performed.

Step 316 may include, among other things, the following: sub-step 3162 and/or sub-step 3164 and/or sub-step 3166 and/or sub-step 3168 and/or sub-step 31610 and/or sub-step 31612:

sub-step 3162, calculating an average value of the first position loss information of each writing stroke, and obtaining second position loss information between the writing text formed by all writing strokes and the reference text.

Wherein a position loss between the written text and the reference text may be determined based on an average of the position losses of the data strokes. Wherein a position loss average value may be calculated based on the first position loss information of each writing stroke, resulting in second position loss information between the writing text and the reference text.

Sub-step 3164, calculating an average value of the first length loss information of each writing stroke, and obtaining second length loss information between the writing text formed by all writing strokes and the reference text.

Wherein a length penalty between the written text and the reference text may be determined based on an average of the length penalty of each data stroke. Wherein a length loss average value may be calculated based on the first length loss information of each written stroke, resulting in second length loss information between the written text and the reference text.

Sub-step 3166, calculating a first tilt angle loss information average value of each writing stroke, and obtaining second tilt angle loss information between the writing text formed by all writing strokes and the reference text.

Wherein the loss of tilt angle between the written text and the reference text may be determined based on an average of the loss of tilt angle of each data stroke. Wherein the average value of the tilt angle losses can be calculated based on the first tilt angle loss information of each writing stroke, and the second tilt angle loss information between the writing text and the reference text is obtained.

In the embodiment of the invention, the loss between the written text and the reference text can be determined according to the loss between each written stroke and the corresponding matched reference stroke, and the loss between the written text and the reference text can be determined according to the total number of strokes, the stroke sequence and the like.

Substep 3168, obtaining stroke number loss information and/or stroke order loss information between the written text and the reference text.

In the embodiment of the invention, after the writing of the user is determined, the total writing stroke number corresponding to the written text can be determined, and the reference total stroke number corresponding to the reference text can be obtained; the difference between the reference total number of strokes and the written total number of strokes may then be calculated and used to determine stroke number loss information between the reference text and the written text. Wherein, the reference total stroke number may be subtracted from the total writing stroke number, or the total writing stroke number may be subtracted from the reference total stroke number, which is not limited in this embodiment of the present invention.

The reference sequence corresponding to the reference strokes in the reference text and the writing sequence of the writing strokes corresponding to the writing text can be obtained; stroke order loss information between the reference text and written text is then determined based on the reference order and written order. The method comprises the steps that reference strokes corresponding to all writing strokes are sequenced according to the writing sequence corresponding to all writing strokes, and corresponding sequencing results are obtained; and comparing the reference sequence with the sequencing result to determine the stroke sequence loss between the reference text and the written text. In one example, a number of reference strokes of the ordering result that is different from the order in the reference order may be determined as a stroke order penalty between the reference text and the written text. For example, writing a stroke includes: writing strokes Wr1, wr2 and Wr3, and the corresponding writing sequence is: wr1→Wr2→Wr3. The reference strokes include: reference stroke Re1, reference stroke Re2 and reference stroke Re3, corresponding reference sequences are: re 1- & gtRe 2- & gtRe 3. The written strokes correspond to the reference strokes as follows: writing stroke Wr 1-reference stroke Re2, writing stroke Wr 2-reference stroke Re1, writing stroke Wr 3-reference stroke Re3. Sequencing the reference strokes according to the writing sequence, wherein the sequencing result is as follows: re 2- & gtRe 1- & gtRe 3; and comparing the sequencing result with the reference sequence to determine that the number of the reference strokes with different sequences of the sequencing result and the reference sequence is 2, and taking 2 as the stroke sequence loss.

Substep 31612, determining second loss information between the written text formed by all writing strokes and the reference text according to the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke order loss information and at least one of the reference total stroke number.

And further, at least one of the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke order loss information and the reference total stroke number can be adopted to generate second loss information between the writing text formed by all writing strokes and the reference text. Wherein when two or more of the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke order loss information, and the reference total stroke number are adopted, the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke order loss information, and the reference total stroke number may be respectively regarded as one dimension of the second loss information. That is, the second loss information may include a plurality of dimensions, the second position loss information corresponds to a position dimension, the second length loss information corresponds to a length dimension, the second tilt angle information corresponds to a tilt angle dimension, the stroke number loss information corresponds to a stroke loss dimension, the stroke order loss information corresponds to a timing loss dimension, and the reference total stroke number corresponds to a reference stroke dimension.

And step 318, evaluating normalization of the written text formed by the written strokes written by the user according to the second loss information.

In one embodiment of the invention, the normalization of the written text formed by the writing strokes written by the user can be evaluated directly based on the information of partial dimensionality of the second loss information. Sub-step 3182 and/or sub-step 3184 may be included:

substep 3182, if the stroke loss information is not equal to zero, evaluating the normalization of the stroke number of the written text.

Wherein, it can be judged whether the stroke loss information is equal to zero; if the stroke loss information is not equal to zero, it can be determined whether the stroke loss information is greater than zero. If the stroke loss information is obtained by subtracting the total stroke number of the reference strokes from the total stroke number of the writing strokes, when the stroke loss information is greater than zero, the normalization of the stroke number of the writing text can be evaluated, such as 'M strokes are increased'. When the stroke loss information is less than zero, the normalization of the stroke number of the written text can be evaluated, such as 'M1 strokes are reduced'.

Substep 3184, if the stroke order loss information is not equal to zero, evaluating a stroke order normalization of the written text.

Wherein, it can be judged whether the stroke order loss information is equal to zero; if the stroke order loss information is not equal to zero, the stroke order normalization of the written text can be evaluated, such as 'M2 strokes are misplaced'.

Step 320, determining a writing loss score corresponding to the writing text according to the second loss information.

And step 322, evaluating normalization of a written text formed by the written strokes written by the user according to the writing loss score.

In the embodiment of the invention, the loss information of each dimension in the second loss information can be fused to obtain fused loss information; and converting the fused loss information into a written loss value. Wherein the substep 3206 may include the following substeps S22 to S26:

and S22, acquiring weights corresponding to the dimension loss information in the second loss information.

And S24, carrying out weighted calculation on each dimension loss information in the second loss information based on the corresponding weight of each dimension loss information to obtain a weighted result.

And S26, determining a writing loss score corresponding to the writing text according to the weighted result.

In the embodiment of the invention, the weight corresponding to each dimension loss information in the second loss information can be acquired first; and then, the dimension loss information in the second loss information can be fused by carrying out weighted calculation on the dimension loss information in the second loss information according to the corresponding weight of the dimension loss information. Then, the weighted result obtained by the weighted calculation can be converted to obtain a writing loss score; for example, the weighted results may be mapped using an S-type function to obtain a loss-of-writing score.

The weight corresponding to each dimension loss information in the second loss information may be predetermined, and then the weight corresponding to each dimension loss information in the predetermined second loss information may be obtained. Or the writing loss value is determined in the process of determining the writing loss value, and further, after the writing loss value, the writing loss value can be obtained; the embodiments of the present invention are not limited in this regard. One way to determine the weight corresponding to each dimension loss information in the second loss information may be to search by using a grid search method, so as to obtain an optimal weight. Another way to determine the weights corresponding to the dimension loss information in the second loss information may be to determine the optimal weights by using a bayesian optimization algorithm. The embodiment of the invention does not limit the mode how to determine the weight corresponding to each dimension loss information in the second loss information.

Wherein sub-step 3228 may include the following sub-steps S42-S44:

and a substep S42, when the writing loss score is greater than or equal to a preset loss score, generating writing positive evaluation information aiming at the writing text.

And a substep S44, when the writing loss score is smaller than a preset loss score, generating writing negative evaluation information aiming at the writing text.

In the embodiment of the invention, the writing loss score can be compared with a preset loss score, and whether the writing loss score is smaller than the preset loss score or not is judged. When the writing loss score is greater than or equal to a preset loss score, writing positive evaluation information of writing text formed by writing strokes written by the user can be generated; the written positive evaluation information may include information that confirms normalization of a written text written by the user, such as "write well". When the writing loss score is smaller than a preset loss score, writing negative evaluation information of writing text formed by writing strokes written by the user can be generated; the written negative evaluation information may include information that negates normalization of a written text written by the user, such as "write not so well".

In summary, in the embodiment of the present invention, normalization of a written text formed by writing strokes written by the user may be evaluated according to the second loss information; the writing loss score corresponding to the writing text can be determined according to the second loss information, and then the normalization of the writing text formed by the writing strokes written by the user is evaluated according to the writing loss score; furthermore, the text written by the user can be evaluated in the whole, so that the user can know the normalization of the text written by the user in the whole, and the user can know how to adjust the writing from the whole.

Secondly, in the embodiment of the invention, when the writing loss score is greater than or equal to a preset loss score, writing positive evaluation information aiming at the writing text is generated; when the writing loss score is smaller than a preset loss score, generating writing negative evaluation information aiming at the writing text; and the user can be affirmed when the writing standardization of the user is good, and the user can be righted when the writing standardization of the user is poor, so that the user is helped to improve the writing level.

Thirdly, in the embodiment of the invention, if the stroke loss information is not equal to zero, evaluating the stroke number normalization of the written text; and then when the number of strokes written by the user is wrong, prompting the user. And if the stroke order loss information is not equal to zero, evaluating the stroke order normalization of the written text; and then when the user writes the stroke error, the user is prompted.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

Referring to fig. 4, there is shown a block diagram of an embodiment of an evaluation apparatus according to the present invention, which may specifically include the following modules:

an acquisition module 402, configured to acquire track information of a writing stroke written by a user;

a matching module 404, configured to determine, according to the track information of the writing strokes, a reference stroke corresponding to the writing stroke from the reference strokes corresponding to the reference text;

a determining module 406, configured to determine first loss information between the writing stroke and a reference stroke corresponding to the writing stroke;

and the evaluation module 408 is configured to evaluate normalization of the writing of the user according to the first loss information.

Referring to fig. 5, a block diagram of an alternative embodiment of an evaluation device of the present invention is shown.

In an optional embodiment of the present invention, the track information includes coordinate information of a plurality of track points, and the matching module 404 is configured to obtain track information of each reference stroke; inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model; the point cloud mapping module determines a track relation based on coordinate information of track points in the track information, and outputs a reference stroke identifier of a reference stroke, the matching degree of which accords with a preset range, according to the track relation; determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identifier; wherein the track relationship comprises at least one of a first relationship, a second relationship, and a third relationship; the first relationship includes a relationship between the writing stroke and a corresponding track point of a reference stroke, the second relationship includes a relationship between track points of the writing stroke, and the third relationship includes a relationship between track points of the reference stroke.

In an alternative embodiment of the present invention, the determining module 406 includes:

a first geometric information determination submodule 4062, configured to determine first geometric information of the writing stroke according to track information of the writing stroke;

a second geometric information determining submodule 4064, configured to determine second geometric information of the reference stroke corresponding to the writing stroke according to track information of the reference stroke corresponding to the writing stroke;

a first loss information determination submodule 4066, configured to determine, according to the first geometric information and the second geometric information, first loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke.

In an optional embodiment of the invention, the track information includes coordinate information of a plurality of track points;

the first geometric information determining submodule 4062 is configured to determine at least one of first position information, first length information and first inclination angle information of the writing stroke according to coordinate information of each track point corresponding to the writing stroke; determining first geometric information corresponding to the writing stroke according to at least one of first position information, first length information and first inclination angle information of the writing stroke;

The second geometric information determining submodule 4064 is configured to determine at least one of second position information, second length information and second inclination angle information of the reference stroke corresponding to the writing stroke according to coordinate information of each track point corresponding to the reference stroke corresponding to the writing stroke; and determining second geometric information corresponding to the reference strokes correspondingly matched with the writing strokes according to at least one of second position information, second length information and second inclination angle information of the reference strokes correspondingly matched with the writing strokes.

In an alternative embodiment of the present invention, the first loss information determining submodule 4066 is configured to determine, according to the first location information and the second location information, first location loss information between the writing stroke and a reference stroke corresponding to the writing stroke; and/or determining first length loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first length information and the second length information; and/or determining first inclination angle loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first inclination angle information and the second inclination angle information; and determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to at least one of the first position loss information, the first length loss information and the first inclination angle loss information.

In an alternative embodiment of the present invention, the evaluation module 408 includes:

and a stroke evaluation sub-module 4082, configured to evaluate normalization of the writing stroke written by the user according to the first loss information.

In an optional embodiment of the invention, the first loss information includes first position loss information, first length loss information, and first inclination angle information;

the stroke evaluation submodule 4082 is configured to evaluate, if the first position loss information exceeds a position loss range, position normalization of the writing stroke written by the user; if the first length loss information exceeds a length loss range, evaluating the length normalization of the writing strokes written by the user; and if the first inclination angle loss information exceeds the inclination angle loss range, evaluating the inclination angle normalization of the writing strokes written by the user.

In an alternative embodiment of the present invention, the writing stroke includes a plurality of writing strokes, and the evaluation module 408 includes:

a second loss information determining submodule 4084, configured to determine second loss information between the written text formed by all the written strokes and the reference text according to the first loss information between each written stroke and the reference stroke corresponding to each written stroke;

And a text evaluation submodule 4086, configured to evaluate normalization of the written text formed by the writing strokes written by the user according to the second loss information.

In an alternative embodiment of the present invention, the first loss information includes: first position loss information, first length loss information, and first inclination angle information;

the second loss information determining submodule 4084 is configured to calculate an average value of the first position loss information of each writing stroke, and obtain second position loss information between the writing text and the reference text; and/or calculating the average value of the first length loss information of each writing stroke to obtain second length loss information between the writing text and the reference text; and/or calculating a first inclination angle loss information average value of each writing stroke to obtain second inclination angle loss information between the writing text and the reference text; and/or acquiring stroke number loss information and/or stroke order loss information between the written text and the reference text; and/or, obtaining the total reference strokes corresponding to the reference text; and determining second loss information between the writing text formed by all writing strokes and the reference text according to the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke sequence loss information and at least one of the reference total stroke number.

In an alternative embodiment of the present invention, the text evaluation submodule 4086 includes:

a loss score evaluation unit 40862, configured to determine a writing loss score corresponding to the written text according to the second loss information; and evaluating the normalization of the written text formed by the written strokes written by the user according to the writing loss score.

In an alternative embodiment of the present invention,

the loss score evaluation unit 4082 is configured to generate writing positive evaluation information for the writing text when the writing loss score is greater than or equal to a preset loss score; and when the writing loss score is smaller than a preset loss score, generating writing negative evaluation information aiming at the writing text.

In an alternative embodiment of the present invention, the second loss information includes stroke loss information and/or stroke order loss information; the text evaluation submodule 4086 includes:

a loss information evaluation unit 40864, configured to evaluate, if the stroke loss information is not equal to zero, a stroke number normalization of the written text; and if the stroke order loss information is not equal to zero, evaluating the stroke order normalization of the written text.

In summary, in the embodiment of the invention, track information of each writing stroke written by a user can be obtained in the writing process of the user; then, determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke, and determining first loss information between the writing stroke and the reference stroke corresponding to the writing stroke; evaluating the normalization of the writing of the user according to the first loss information; compared with the prior art, the method and the device for comparing the writing text with the corresponding reference text integrally have finer granularity, so that accuracy of evaluating writing normalization can be improved.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

Fig. 6 is a block diagram of an electronic device 600 for evaluation, according to an example embodiment. For example, the electronic device 600 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, a smart wearable device, and the like.

Referring to fig. 6, an electronic device 600 may include one or more of the following components: a processing component 602, a memory 604, a power component 606, a multimedia component 608, an audio component 610, an input/output (I/O) interface 612, a sensor component 614, and a communication component 616.

The processing component 602 generally controls overall operation of the electronic device 600, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 602 may include one or more processors 620 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 602 can include one or more modules that facilitate interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate interaction between the multimedia component 608 and the processing component 602.

The memory 604 is configured to store various types of data to support operations at the electronic device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 604 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power component 606 provides power to the various components of the electronic device 600. The power components 606 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 600.

The multimedia component 608 includes a screen between the electronic device 600 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and/or a rear camera. When the electronic device 600 is in an operational mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 610 is configured to output and/or input audio signals. For example, the audio component 610 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 600 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 604 or transmitted via the communication component 616. In some embodiments, audio component 610 further includes a speaker for outputting audio signals.

The I/O interface 612 provides an interface between the processing component 602 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 614 includes one or more sensors for providing status assessment of various aspects of the electronic device 600. For example, the sensor assembly 614 may detect an on/off state of the electronic device 600, a relative positioning of the components, such as a display and keypad of the electronic device 600, the sensor assembly 614 may also detect a change in position of the electronic device 600 or a component of the electronic device 600, the presence or absence of a user's contact with the electronic device 600, an orientation or acceleration/deceleration of the electronic device 600, and a change in temperature of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 614 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 616 is configured to facilitate communication between the electronic device 600 and other devices, either wired or wireless. The electronic device 600 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication part 614 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communications component 614 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 600 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as memory 604, including instructions executable by processor 620 of electronic device 600 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

A non-transitory computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform a method of evaluation, the method comprising: acquiring track information of writing strokes written by a user; determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke; determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke; and evaluating the normalization of the writing of the user according to the first loss information.

Fig. 7 is a schematic structural view of an electronic device 700 for evaluation according to another exemplary embodiment of the present invention. The electronic device 700 may be a server that may vary widely in configuration or performance and may include one or more central processing units (central processing units, CPU) 722 (e.g., one or more processors) and memory 732, one or more storage media 730 (e.g., one or more mass storage devices) that store applications 742 or data 744. Wherein memory 732 and storage medium 730 may be transitory or persistent. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 722 may be arranged to communicate with a storage medium 730 and execute a series of instruction operations in the storage medium 730 on a server.

The server(s) may also include one or more power supplies 726, one or more wired or wireless network interfaces 750, one or more input/output interfaces 758, one or more keyboards 756, and/or one or more operating systems 741 such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.

In an exemplary embodiment, the server is configured to execute one or more programs by the one or more central processors 722, including instructions for: acquiring track information of writing strokes written by a user; determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke; determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke; and evaluating the normalization of the writing of the user according to the first loss information.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Further, the age (sex, identification card number, passport number, etc. (adjusted according to need)) and the like according to the embodiments of the present application are not suitable for use of personal information, but are general descriptions.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.

The above description of an evaluation method, an evaluation device and an electronic apparatus provided by the present invention applies specific examples to illustrate the principles and embodiments of the present invention, and the above examples are only used to help understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. An evaluation method, comprising:

acquiring track information of writing strokes written by a user;

determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke;

determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke;

evaluating normalization of the writing of the user according to the first loss information;

the determining, according to the track information of the writing strokes, a reference stroke corresponding to the writing stroke from the reference strokes corresponding to the reference text, includes:

Determining a track relation based on coordinate information of track points in the track information by using a point cloud mapping model, and outputting a reference stroke identifier of a reference stroke, the matching degree of which accords with a preset range, according to the track relation;

determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identifier;

wherein the track relationship comprises at least one of a first relationship, a second relationship, and a third relationship; the first relationship includes a relationship between the writing stroke and a corresponding track point of a reference stroke, the second relationship includes a relationship between track points of the writing stroke, and the third relationship includes a relationship between track points of the reference stroke.

2. The method of claim 1, wherein the trajectory information includes coordinate information of a plurality of trajectory points, the determining a reference stroke that corresponds to a match with the writing stroke from among reference strokes that correspond to reference text based on the trajectory information of the writing stroke, further comprising:

acquiring track information of each reference stroke;

and inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model.

3. The method of claim 1, wherein the determining first loss information between the writing stroke and a reference stroke that corresponds to a match to the writing stroke comprises:

determining first geometric information of the writing strokes according to the track information of the writing strokes;

determining second geometric information of the reference strokes correspondingly matched with the writing strokes according to track information of the reference strokes correspondingly matched with the writing strokes;

and determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to the first geometric information and the second geometric information.

4. A method according to claim 3, wherein the trajectory information comprises coordinate information of a plurality of trajectory points; the determining the first geometric information of the writing stroke according to the track information of the writing stroke comprises the following steps:

determining at least one of first position information, first length information and first inclination angle information of the writing strokes according to coordinate information of the writing strokes corresponding to each track point; determining first geometric information corresponding to the writing stroke according to at least one of first position information, first length information and first inclination angle information of the writing stroke;

The determining the second geometric information of the reference strokes correspondingly matched with the writing strokes according to the track information of the reference strokes correspondingly matched with the writing strokes comprises the following steps:

determining at least one of second position information, second length information and second inclination angle information of the reference strokes correspondingly matched with the writing strokes according to the coordinate information of the track points corresponding to the reference strokes correspondingly matched with the writing strokes; and determining second geometric information corresponding to the reference strokes correspondingly matched with the writing strokes according to at least one of second position information, second length information and second inclination angle information of the reference strokes correspondingly matched with the writing strokes.

5. The method of claim 4, wherein determining first loss information between the writing stroke and a reference stroke corresponding to the writing stroke based on the first and second geometric information comprises:

determining first position loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to the first position information and the second position information; and/or determining first length loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first length information and the second length information; and/or determining first inclination angle loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first inclination angle information and the second inclination angle information;

And determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to at least one of the first position loss information, the first length loss information and the first inclination angle loss information.

6. The method of claim 1, wherein evaluating the normalization of the user writing based on the first loss information comprises:

and evaluating the normalization of the written strokes written by the user according to the first loss information.

7. The method of claim 6, wherein the first loss information comprises first position loss information, first length loss information, and first tilt angle information;

the evaluating the normalization of the writing strokes written by the user according to the first loss information comprises the following steps:

if the first position loss information exceeds a position loss range, evaluating the position normalization of the writing strokes written by the user;

if the first length loss information exceeds a length loss range, evaluating the length normalization of the writing strokes written by the user;

And if the first inclination angle loss information exceeds the inclination angle loss range, evaluating the inclination angle normalization of the writing strokes written by the user.

8. The method of claim 1, wherein the written stroke comprises a plurality of strokes, and wherein evaluating normalization of the user writing based on the first loss information comprises:

determining second loss information between the written text formed by all the writing strokes and the reference text according to the first loss information between each writing stroke and the reference stroke correspondingly matched with each writing stroke;

and evaluating normalization of the written text formed by the written strokes written by the user according to the second loss information.

9. The method of claim 8, wherein the first loss information comprises: first position loss information, first length loss information, and first inclination angle information;

determining second loss information between the written text formed by all the writing strokes and the reference text according to the first loss information between each writing stroke and the reference stroke correspondingly matched with each writing stroke, wherein the second loss information comprises the following steps:

Calculating the average value of the first position loss information of each writing stroke to obtain second position loss information between the writing text and the reference text; and/or calculating the average value of the first length loss information of each writing stroke to obtain second length loss information between the writing text and the reference text; and/or calculating a first inclination angle loss information average value of each writing stroke to obtain second inclination angle loss information between the writing text and the reference text; and/or acquiring stroke number loss information and/or stroke order loss information between the written text and the reference text; and/or, obtaining the total reference strokes corresponding to the reference text;

and determining second loss information between the writing text formed by all writing strokes and the reference text according to the second position loss information, the second length loss information, the second inclination angle loss information, the stroke number loss information, the stroke sequence loss information and at least one of the reference total stroke number.

10. The method of claim 8, wherein evaluating normalization of the written text formed by the written strokes written by the user based on the second loss information comprises:

Determining a writing loss score corresponding to the writing text according to the second loss information;

and evaluating the normalization of the written text formed by the written strokes written by the user according to the writing loss score.

11. The method of claim 10, wherein evaluating normalization of written text formed by the written strokes written by the user based on the loss-of-writing score comprises:

when the writing loss score is greater than or equal to a preset loss score, generating writing positive evaluation information aiming at the writing text;

and when the writing loss score is smaller than a preset loss score, generating writing negative evaluation information aiming at the writing text.

12. The method of claim 8, wherein the second loss information comprises stroke loss information and/or stroke order loss information;

and evaluating normalization of the written text formed by the written strokes written by the user according to the second loss information, wherein the evaluation comprises the following steps:

if the stroke loss information is not equal to zero, evaluating the stroke number normalization of the written text;

and if the stroke order loss information is not equal to zero, evaluating the stroke order normalization of the written text.

13. An evaluation device, comprising:

the acquisition module is used for acquiring track information of writing strokes written by a user;

the matching module is used for determining a reference stroke corresponding to the writing stroke from all the reference strokes corresponding to the reference text according to the track information of the writing stroke;

a determining module for determining first loss information between the writing stroke and a reference stroke corresponding to the writing stroke;

the evaluation module is used for evaluating the normalization of the writing of the user according to the first loss information;

the matching module is further configured to: determining a track relation based on coordinate information of track points in the track information by using a point cloud mapping model, and outputting a reference stroke identifier of a reference stroke, the matching degree of which accords with a preset range, according to the track relation; determining a reference stroke correspondingly matched with the writing stroke based on the reference stroke identifier; wherein the track relationship comprises at least one of a first relationship, a second relationship, and a third relationship; the first relationship includes a relationship between the writing stroke and a corresponding track point of a reference stroke, the second relationship includes a relationship between track points of the writing stroke, and the third relationship includes a relationship between track points of the reference stroke.

14. The apparatus of claim 13, wherein the trajectory information comprises coordinate information of a plurality of trajectory points,

the matching module is also used for acquiring track information of each reference stroke; and inputting the track information of the writing strokes and the track information of each reference stroke into a pre-trained point cloud mapping model.

15. The apparatus of claim 13, wherein the trajectory information comprises coordinate information of a plurality of trajectory points; the determining module includes:

the first geometric information determining submodule is used for determining at least one of first position information, first length information and first inclination angle information of the writing strokes according to coordinate information of the writing strokes corresponding to each track point; determining first geometric information corresponding to the writing stroke according to at least one of first position information, first length information and first inclination angle information of the writing stroke;

the second geometric information determining submodule is used for determining at least one of second position information, second length information and second inclination angle information of the reference strokes corresponding to the writing strokes according to the coordinate information of the track points corresponding to the reference strokes corresponding to the writing strokes; and determining second geometric information corresponding to the reference strokes correspondingly matched with the writing strokes according to at least one of second position information, second length information and second inclination angle information of the reference strokes correspondingly matched with the writing strokes.

16. The apparatus of claim 15, wherein the determining module includes a first loss information determining sub-module for determining first location loss information between the writing stroke and a reference stroke corresponding to the writing stroke based on the first location information and the second location information; and/or determining first length loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first length information and the second length information; and/or determining first inclination angle loss information between the writing stroke and a reference stroke corresponding to and matched with the writing stroke according to the first inclination angle information and the second inclination angle information; and determining first loss information between the writing stroke and a reference stroke correspondingly matched with the writing stroke according to at least one of the first position loss information, the first length loss information and the first inclination angle loss information.

17. The apparatus of claim 13, wherein the first loss information comprises first position loss information, first length loss information, and first tilt angle information; the evaluation module includes:

The stroke evaluation sub-module is used for evaluating the position normalization of the writing strokes written by the user if the first position loss information exceeds a position loss range; if the first length loss information exceeds a length loss range, evaluating the length normalization of the writing strokes written by the user; and if the first inclination angle loss information exceeds the inclination angle loss range, evaluating the inclination angle normalization of the writing strokes written by the user.

18. The apparatus of claim 13, wherein the writing stroke comprises a plurality of, the evaluation module comprising:

the second loss information determining submodule is used for determining second loss information between the written text formed by all the written strokes and the reference text according to the first loss information between each written stroke and the reference stroke correspondingly matched with each written stroke;

and the text evaluation sub-module is used for evaluating the normalization of the written text formed by the writing strokes written by the user according to the second loss information.

19. The apparatus of claim 18, wherein the text evaluation sub-module comprises:

The loss score evaluation unit is used for determining a writing loss score corresponding to the writing text according to the second loss information; and evaluating the normalization of the written text formed by the written strokes written by the user according to the writing loss score.

20. The apparatus of claim 19, wherein the device comprises a plurality of sensors,

the loss score evaluation unit is used for generating writing positive evaluation information aiming at the writing text when the writing loss score is greater than or equal to a preset loss score; and when the writing loss score is smaller than a preset loss score, generating writing negative evaluation information aiming at the writing text.

21. The apparatus of claim 19, wherein the second loss information comprises stroke loss information and/or stroke order loss information;

the text evaluation submodule comprises:

a loss information evaluation unit, configured to evaluate, if the stroke loss information is not equal to zero, a stroke number normalization of the written text; and if the stroke order loss information is not equal to zero, evaluating the stroke order normalization of the written text.

22. An electronic device, comprising:

One or more processors; and

one or more readable media having instructions stored thereon, which when executed by the one or more processors, cause the electronic device to perform the evaluation method of any of claims 1-12.

23. A readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the evaluation method according to any one of the method claims 1-12.