Text recognition method based on terminal device, device, and storage medium

A terminal device, comprising:

• a processor and a memory, wherein
• the memory stores computer-executable instructions;
• and
• the processor executes the computer-executable instructions stored in the memory, to cause the terminal device to be configured to:
• display a first interface, wherein the first interface comprises a first window, the first window displays a preview stream collected by the terminal device, and the first interface comprises a first button;
• display a second button on the first interface when an object category of a first image in the preview stream is a document object;
• display a second interface in response to that the second button on the first interface is triggered, wherein the second interface comprises a second window and a third window, the second window displays the preview stream collected by the terminal device, an outer frame of a document in a current frame image in the preview stream is highlighted, the second interface displays a third button when the current frame image of the preview stream comprises a target text, the second interface does not display the third button when the current frame image of the preview stream does not comprise the target text, and the third window displays the first button;
• display a third interface in response to that the third button on the second interface is triggered, wherein the third interface comprises a fourth window and a fifth window, the third interface displays the third button, the fourth window displays a second image in the preview stream, the second image comprises the highlighted target text, the fifth window displays a fifth button when the target text in the fourth window does not comprise an entity, the fifth window displays the fifth button and at least one sixth button when the target text in the fourth window comprises an entity, and the sixth button is in a one-to-one correspondence with the entity in the target text in the fourth window;
• and
• display a fourth interface in response to that the first button on the second interface is triggered, wherein the fourth interface displays a third image in the preview stream, and an outer frame of a document in the third image on the fourth interface is highlighted.

A non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors of an electronic device, cause the electronic device to be configured to,

• display a first interface, wherein the first interface comprises a first window, the first window displays a preview stream collected by the terminal device, and the first interface comprises a first button;
• display a second button on the first interface when an object category of a first image in the preview stream is a document object;
• display a second interface in response to that the second button on the first interface is triggered, wherein the second interface comprises a second window and a third window, the second window displays the preview stream collected by the terminal device, an outer frame of a document in a current frame image in the preview stream is highlighted, the second interface displays a third button when the current frame image of the preview stream comprises a target text, the second interface does not display the third button when the current frame image of the preview stream does not comprise the target text, and the third window displays the first button;
• display a third interface in response to that the third button on the second interface is triggered, wherein the third interface comprises a fourth window and a fifth window, the third interface displays the third button, the fourth window displays a second image in the preview stream, the second image comprises the highlighted target text, the fifth window displays a fifth button when the target text in the fourth window does not comprise an entity, the fifth window displays the fifth button and at least one sixth button when the target text in the fourth window comprises an entity, and the sixth button is in a one-to-one correspondence with the entity in the target text in the fourth window;
• and
• display a fourth interface in response to that the first button on the second interface is triggered, wherein the fourth interface displays a third image in the preview stream, and an outer frame of a document in the third image on the fourth interface is highlighted.