Forums
Questions about some functions of MyScript
Hello,
Thank you for contacting us.
2. Sorry, there is only an online tool for Text SK generation.
3. The recognition speed of lite depends on the language, and is improved with lite resources, and the recognition accuracy is slightly reduced. It depends on the performance of the device to make a trade-off.
5- The recognition accuracy depends on several parameters as the context (the more context, the better the recognition result), the handwriting quality, the resources that you are using... Which objects (Editor/OffscreeenEditor/Recognizer) and which content type are you using for your tests?
Best regards,
Gwenaëlle
1. 我们需要 "置信度" 这个值，用于给用户提醒：请注意，你要小心这个结果，它可能有问题。 有什么方式可以获取吗？
4. 现在我们的做法是把常见汉字都列出来，再去除不可能出现在内容中的字。如果黑名单那机制那就太好了
5. 使用的 Recognizer + Text，只书写 "3 斤"，经常识别成 "沂"
---translate---
Thanks for your reply :)
1. We need the "confidence" value to remind users: Please note that you should be careful with this result, it may be problematic. Is there any way to obtain it?
4. Our current approach is to list all common Chinese characters and then remove characters that are unlikely to appear in the content. It would be great if there was a blacklist mechanism
5. When using Recognizer + Text, only "3斤" is written, and it is often recognized as "沂"
Hello,
Thank you for your update.
1. As already indicated, there is no way to get the confidence score. We recommend you remind users of candidates, instead.
4. The public API does not have such a blacklist mechanism. For people having a contract with MyScript, our professional services team may generate such SK on demand. You should discuss this with your sales representative.
5. The more ink context our recognition Engine has, the better the accuracy of the recognition result. The recognition result also depend on other factors like the quality of the handwriting or of the ink capture. For a deeper analysis, please provide us the strokes coordinates that you send to your Recognizer, the configuration of your Recognizer and the scaleX and scale Y values.
Best regards,
Gwenaëlle
For question 5, you can look at this data, corresponding to "1包"
[{\"x\":13.25879970932007,\"y\":134.1424748840332,\"t\":1744461612000,\"event\":\"DOWN\"},{\"x\":13.26155680847168,\"y\":134.1707522277832,\"t\":1744461612011,\"event\":\"MOVE\"},{\"x\":13.2876496925354,\"y\":134.18484439086913,\"t\":1744461612021,\"event\":\"MOVE\"},{\"x\":13.297505195617676,\"y\":134.2068779296875,\"t\":1744461612030,\"event\":\"MOVE\"},{\"x\":13.285398376464844,\"y\":134.21978411865234,\"t\":1744461612040,\"event\":\"MOVE\"},{\"x\":13.325023864746093,\"y\":134.29145416259766,\"t\":1744461612050,\"event\":\"MOVE\"},{\"x\":13.342877426147462,\"y\":134.38541354370116,\"t\":1744461612060,\"event\":\"MOVE\"},{\"x\":13.371788452148438,\"y\":134.492255859375,\"t\":1744461612070,\"event\":\"MOVE\"},{\"x\":13.400882606506348,\"y\":134.58918017578125,\"t\":1744461612081,\"event\":\"MOVE\"},{\"x\":13.449402900695802,\"y\":134.92729907226564,\"t\":1744461612092,\"event\":\"MOVE\"},{\"x\":13.47807702255249,\"y\":135.3160892944336,\"t\":1744461612100,\"event\":\"MOVE\"},{\"x\":13.505754112243652,\"y\":135.69328720092773,\"t\":1744461612110,\"event\":\"MOVE\"},{\"x\":13.53607202911377,\"y\":135.93385391235353,\"t\":1744461612122,\"event\":\"MOVE\"},{\"x\":13.611846473693848,\"y\":136.517236907959,\"t\":1744461612134,\"event\":\"MOVE\"},{\"x\":13.660980102539062,\"y\":136.99002200317383,\"t\":1744461612144,\"event\":\"MOVE\"},{\"x\":13.6849408493042,\"y\":137.41093817138673,\"t\":1744461612155,\"event\":\"MOVE\"},{\"x\":13.685629760742188,\"y\":137.6926767883301,\"t\":1744461612167,\"event\":\"MOVE\"},{\"x\":13.711461032867431,\"y\":138.09968682861327,\"t\":1744461612181,\"event\":\"MOVE\"},{\"x\":13.708743175506592,\"y\":138.19579724121093,\"t\":1744461612202,\"event\":\"MOVE\"},{\"x\":13.68304852294922,\"y\":138.2526774902344,\"t\":1744461612216,\"event\":\"MOVE\"},{\"x\":13.626316520690919,\"y\":138.31592944335938,\"t\":1744461612225,\"event\":\"MOVE\"},{\"x\":12.999719593048097,\"y\":138.5468455810547,\"t\":1744461612234,\"event\":\"UP\"},{\"x\":15.849599418640137,\"y\":133.22807720947264,\"t\":1744461613000,\"event\":\"DOWN\"},{\"x\":15.849574710845948,\"y\":133.23460006713867,\"t\":1744461613013,\"event\":\"MOVE\"},{\"x\":15.84920118713379,\"y\":133.25454071044922,\"t\":1744461613026,\"event\":\"MOVE\"},{\"x\":15.847483268737793,\"y\":133.2810274658203,\"t\":1744461613040,\"event\":\"MOVE\"},{\"x\":15.842431251525879,\"y\":133.3226760864258,\"t\":1744461613051,\"event\":\"MOVE\"},{\"x\":15.78885167312622,\"y\":133.54118600463866,\"t\":1744461613063,\"event\":\"MOVE\"},{\"x\":15.709856494903566,\"y\":133.78378747558594,\"t\":1744461613085,\"event\":\"MOVE\"},{\"x\":15.60678865814209,\"y\":134.06646789550783,\"t\":1744461613094,\"event\":\"MOVE\"},{\"x\":15.508633312225342,\"y\":134.38289044189455,\"t\":1744461613106,\"event\":\"MOVE\"},{\"x\":15.349231704711915,\"y\":134.8758603515625,\"t\":1744461613124,\"event\":\"MOVE\"},{\"x\":15.25066068649292,\"y\":135.10473010253907,\"t\":1744461613134,\"event\":\"MOVE\"},{\"x\":15.04187982559204,\"y\":135.84935906982423,\"t\":1744461613144,\"event\":\"UP\"},{\"x\":15.81912017440796,\"y\":134.40156372070314,\"t\":1744461613000,\"event\":\"DOWN\"},{\"x\":15.842335327148438,\"y\":134.3925061340332,\"t\":1744461613010,\"event\":\"MOVE\"},{\"x\":15.890934104919435,\"y\":134.3892621459961,\"t\":1744461613031,\"event\":\"MOVE\"},{\"x\":15.958110237121582,\"y\":134.38275091552734,\"t\":1744461613041,\"event\":\"MOVE\"},{\"x\":16.03749201965332,\"y\":134.36677514648437,\"t\":1744461613052,\"event\":\"MOVE\"},{\"x\":16.296859909057616,\"y\":134.30532540893554,\"t\":1744461613061,\"event\":\"MOVE\"},{\"x\":16.483043312072756,\"y\":134.26333959960937,\"t\":1744461613070,\"event\":\"MOVE\"},{\"x\":16.662137031555176,\"y\":134.2215863342285,\"t\":1744461613079,\"event\":\"MOVE\"},{\"x\":16.803331901550294,\"y\":134.185495513916,\"t\":1744461613088,\"event\":\"MOVE\"},{\"x\":17.094273445129396,\"y\":134.11117446899414,\"t\":1744461613097,\"event\":\"MOVE\"},{\"x\":17.22247201538086,\"y\":134.08185067749022,\"t\":1744461613106,\"event\":\"MOVE\"},{\"x\":17.308635360717773,\"y\":134.0565964050293,\"t\":1744461613120,\"event\":\"MOVE\"},{\"x\":17.39062163543701,\"y\":134.05357333374025,\"t\":1744461613130,\"event\":\"MOVE\"},{\"x\":17.604735019683837,\"y\":134.02235430908203,\"t\":1744461613139,\"event\":\"MOVE\"},{\"x\":17.714548084259032,\"y\":134.00986669921875,\"t\":1744461613147,\"event\":\"MOVE\"},{\"x\":17.787424449920653,\"y\":134.00547161865234,\"t\":1744461613156,\"event\":\"MOVE\"},{\"x\":17.85735186767578,\"y\":134.00658782958985,\"t\":1744461613165,\"event\":\"MOVE\"},{\"x\":17.962086753845217,\"y\":133.99962313842772,\"t\":1744461613174,\"event\":\"MOVE\"},{\"x\":18.01850772857666,\"y\":134.00392520141602,\"t\":1744461613183,\"event\":\"MOVE\"},{\"x\":18.067940757751465,\"y\":134.0059599609375,\"t\":1744461613192,\"event\":\"MOVE\"},{\"x\":18.12246795272827,\"y\":134.0114712524414,\"t\":1744461613202,\"event\":\"MOVE\"},{\"x\":18.190548099517823,\"y\":134.01895916748046,\"t\":1744461613211,\"event\":\"MOVE\"},{\"x\":18.222335403442383,\"y\":134.04439947509766,\"t\":1744461613220,\"event\":\"MOVE\"},{\"x\":18.24609994125366,\"y\":134.0579567871094,\"t\":1744461613238,\"event\":\"MOVE\"},{\"x\":18.257993110656738,\"y\":134.08318780517578,\"t\":1744461613248,\"event\":\"MOVE\"},{\"x\":18.27602834701538,\"y\":134.14498635864257,\"t\":1744461613256,\"event\":\"MOVE\"},{\"x\":18.281147220611572,\"y\":134.2125287475586,\"t\":1744461613266,\"event\":\"MOVE\"},{\"x\":18.282366622924805,\"y\":134.29591900634765,\"t\":1744461613276,\"event\":\"MOVE\"},{\"x\":18.26
Hello Kongyan4696,
You are currently in direct contact with our support team.
It is not relevant to duplicate the threads, one with the team and one on the support forum.
In order to save time for everyone, we will close the topics on the forum.
Best regards,
Etienne
Thanks for your reply, the forum is public, maybe it can help others who encounter similar problems.
Kongyan4696
你好，很高兴能使用到这么棒的服务，有些问题想咨询下，请不吝赐教。
1. 识别结果和候选词有没有 "置信度" 这个数据？
2. 目前客户端能通过 RecognitionAssetsBuilder 生成 LK 资源，通过在线工具能生成 LK + SK 资源。 请问客户端或者我们服务器有办法生成 SK 资源吗？
3. AK 文件现在有lite版和普通版，有没有细分领域单独训练的版本？我们业务场景下，用户手写的内容范围比较固定。
4. LK、SK 都是白名单模式，有没有黑名单机制？在我们业务场景下某些文字肯定是不会出现的，这样应该也能提升准确率。
5. 我们发现 "数字+汉字" 的输入下比较容易出错，比如
"3斤" 识别成了 "沂"
"1包" 识别成了 "泡"
请问下这块有最佳实践吗？
---translate---
Hello, I'm very happy to use such a great service. I have some questions to ask, please feel free to enlighten me .
1. Is there a "confidence" data for recognition results and candidate words?
2. Currently, the client can generate LK resources through RecognitionAssetsBuilder, and LK + SK resources can be generated through online tools. Is there a way for the client or our server to generate SK resources?
3. AK files now have lite and regular versions. Are there versions that are trained separately for specific fields? In our business scenarios, the range of user handwritten content is relatively fixed.
4. LK and SK are both whitelist modes. Is there a blacklist mechanism? In our business scenarios, some characters will definitely not appear, which should also improve the accuracy.
5. We found that it is easy to make mistakes when inputting "numbers + Chinese characters", for example,
"3斤" is recognized as "沂"
"1包" is recognized as "泡"
Is there any best practice in this area?