CN113657325B

CN113657325B - Method, apparatus, medium and program product for determining annotation style information

Info

Publication number: CN113657325B
Application number: CN202110974826.8A
Authority: CN
Inventors: 王琪; 胡雪磊; 李晓琴; 王晓荣
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-08-24
Filing date: 2021-08-24
Publication date: 2024-04-12
Anticipated expiration: 2041-08-24
Also published as: CN113657325A

Abstract

The present disclosure provides a method, apparatus, medium and program product for determining annotation style information, relating to the field of artificial intelligence such as natural language processing and smart medicine. One embodiment of the method comprises the following steps: acquiring a medical record text; identifying the medical record text to obtain target relation information between a target entity in the medical record text and each attribute in at least one attribute; and determining corresponding labeling style information according to the target relation information and the relative position between each attribute and the target entity, wherein the labeling style information is used for labeling the target relation information.

Description

Method, apparatus, medium and program product for determining annotation style information

Technical Field

The present disclosure relates to the field of computers, and more particularly, to natural language processing and smart medicine, and more particularly, to a method, apparatus, medium, and program product for determining annotation style information.

Background

The medical record is a record of medical activities such as examination, diagnosis and treatment of occurrence, development and prognosis of diseases of patients by medical staff, and is also a medical health file of patients which is obtained by summarizing, sorting and comprehensively analyzing the acquired data and writing according to a specified format and requirements. Along with the development of computer and internet technologies, most hospitals realize the electronization of clinical medical records, and the electronic medical records are recorded, stored, managed, transmitted and reproduced by utilizing electronic equipment, so that the method has the advantages of safety, reliability, convenience in recording, storing, sharing and the like.

At present, valuable and usable information can be extracted from the electronic medical record by analyzing big data of the electronic medical record so as to obtain key information to be searched by medical staff.

Disclosure of Invention

The embodiment of the disclosure provides a method, a device, a medium and a program product for determining annotation style information.

In a first aspect, an embodiment of the present disclosure proposes a method for determining labeling style information, including: acquiring a medical record text; identifying the medical record text to obtain target relation information between a target entity in the medical record text and each attribute in at least one attribute; and determining corresponding labeling style information according to the target relation information and the relative position between each attribute and the target entity, wherein the labeling style information is used for labeling the target relation information.

In a second aspect, embodiments of the present disclosure propose an apparatus for determining labeling style information, comprising: the text acquisition module is configured to acquire medical record text; the text recognition module is configured to recognize the medical record text to obtain target relationship information between a target entity in the medical record text and each attribute in at least one attribute; the style determining module is configured to determine corresponding labeling style information according to the target relation information and the relative position between each attribute and the target entity, wherein the labeling style information is used for labeling the target relation information.

In a third aspect, an embodiment of the present disclosure proposes an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.

In a fourth aspect, embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method as described in the first aspect.

In a fifth aspect, embodiments of the present disclosure propose a computer program product comprising a computer program which, when executed by a processor, implements a method as described in the first aspect.

The embodiment of the disclosure provides a method, a device, a medium and a program product for determining labeling style information, wherein medical record text is firstly acquired; then, identifying the medical record text to obtain target relation information between a target entity in the medical record text and each attribute in at least one attribute; and finally, determining corresponding labeling style information according to the target relation information and the relative position between each attribute and the target entity, wherein the labeling style information is used for labeling the target relation information. The corresponding labeling style information can be determined based on the target relation information between the target entity and at least one attribute in the medical record text and the relative position between the attribute and the target entity, so that the labeling of the target relation information between the target entity and the attribute is realized, and the target relation information between the target entity and the attribute can be accurately acquired.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

Other features, objects and advantages of the present disclosure will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is an exemplary system architecture diagram to which the present disclosure may be applied;

FIG. 2 is a flow chart of one embodiment of a method for determining labeling style information according to the present disclosure;

FIG. 3 is a flow chart of one embodiment of a method for determining labeling style information according to the present disclosure;

fig. 4 (a) to 4 (d) are schematic diagrams of labeling style information;

FIG. 5 is a schematic illustration of one application scenario of a method for determining labeling style information according to the present disclosure;

FIG. 6 is a schematic structural diagram of one embodiment of an apparatus for determining labeling style information according to the present disclosure;

fig. 7 is a block diagram of an electronic device used to implement an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that, without conflict, the embodiments of the present disclosure and features of the embodiments may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the methods of the present disclosure for determining annotation style information or apparatuses for determining annotation style information may be applied.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user can interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive medical record text or the like. Various client applications, intelligent interactive applications, such as image processing applications, text processing applications, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, the terminal devices may be electronic products that interact with a user through one or more modes of a keyboard, a touch pad, a touch screen, a remote controller, a voice interaction or a handwriting device, such as a PC (Personal Computer ), a mobile phone, a smart phone, a PDA (Personal Digital Assistant, a personal digital assistant), a wearable device, a PPC (Pocket PC), a tablet computer, a smart car machine, a smart television, a smart speaker, a tablet computer, a laptop portable computer, a desktop computer, and so on. When the terminal devices 101, 102, 103 are software, they can be installed in the above-described electronic devices. Which may be implemented as a plurality of software or software modules, or as a single software or software module. The present invention is not particularly limited herein.

The server 105 may provide various services. For example, the server 105 can obtain medical record text; identifying the medical record text to obtain target relation information between a target entity in the medical record text and each attribute in at least one attribute; and determining corresponding labeling style information according to the target relation information and the relative position between each attribute and the target entity, wherein the labeling style information is used for labeling the target relation information.

The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster formed by a plurality of servers, or as a single server. When server 105 is software, it may be implemented as a plurality of software or software modules (e.g., to provide distributed services), or as a single software or software module. The present invention is not particularly limited herein.

It should be noted that the method for determining the labeling style information provided by the embodiments of the present disclosure is generally performed by the server 105, and accordingly, the device for determining the labeling style information is generally disposed in the server 105.

It should be understood that the number of electronic devices, networks, and servers in fig. 1 are merely illustrative. There may be any number of electronic devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a method for determining labeling style information according to the present disclosure is shown. The method for determining the annotation style information may comprise the steps of:

step 201, obtaining medical record text.

In this embodiment, the execution body (e.g., the server 105 shown in fig. 1) of the method for determining the labeling style information may obtain the medical record text. The medical record text can be text in medical record data, and the type of the medical record data can be images or text.

Here, the medical record information may include symptoms, diseases, drug names, and the like. Medical record text is obtained from the medical record data by optical character recognition (Optical Character Recognition, OCR) techniques or OCR recognition models.

The OCR recognition model can be a model obtained by training the medical record text and the recognition result of the medical record text as training samples.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

Step 202, identifying the medical record text to obtain target relationship information between a target entity in the medical record text and each attribute in at least one attribute.

In an embodiment, the executing body may identify the medical record text to obtain a target entity in the medical record text and at least one attribute having target relationship information with the target entity; then, target relationship information between the at least one attribute and the target entity is determined. The target entity may be an entity in the medical field, and the target entity may include: diseases, symptoms, medications, examinations, signs, treatments, and the like. The above-mentioned attributes may be set for practitioners with medical experience in combination with business needs, and may include: the location, time of occurrence, duration, frequency, size, quantity, degree, cause, exacerbation factor, lightening factor, property, color, smell, state, stage/stage, dosage, efficacy, mode of administration, therapeutic effect, examination description value, etc. The target relationship information described above may be used to characterize the relationship between the target entity and each attribute. For example, the target relationship information between the target entity and the attribute is the frequency of occurrence. The target entity may be at least one entity in the medical record text.

Correspondingly, in this example, identifying the medical record text to obtain the target entity and the corresponding at least one attribute in the medical record text can include: recognizing the medical record text through Natural Language Understanding (NLU) to obtain a recognition result of the medical record text; and then, determining a target entity and at least one attribute corresponding to the target entity in the medical record text through a preset table, wherein the preset table comprises the target entity and the corresponding attribute, and the attribute table can be generated through published books and/or related medical files. Or, recognizing the medical record text through the OCR recognition model to obtain a recognition result of the medical record text; and then, determining the target entity in the medical record text and at least one attribute corresponding to the target entity through a preset table.

It should be noted that after obtaining the target relationship information between the target entity and the attribute, a structured medical record may be generated.

And 203, determining the labeling style information according to the target relation information and the relative position between each attribute in the at least one attribute and the target entity.

In this embodiment, the execution body may determine the labeling style information according to the target relationship information and a relative position between each of the at least one attribute and the target entity. The above-mentioned relative position may be a position between the position information of each attribute on the screen of the electronic device and the position information of the target entity on the screen of the electronic device.

Here, the annotation style information may be used to annotate target relationship information between the target entity and each attribute by an annotation line and/or an annotation text.

The method for determining the labeling style information provided by the embodiment of the disclosure comprises the steps of firstly obtaining a medical record text; then, identifying the medical record text to obtain target relation information between a target entity in the medical record text and each attribute in at least one attribute; and finally, determining corresponding labeling style information according to the target relation information and the relative position between each attribute and the target entity, wherein the labeling style information is used for labeling the target relation information. The corresponding labeling style information can be determined based on the target relation information between the target entity and at least one attribute in the medical record text and the relative position between the attribute and the target entity, so that the labeling of the target relation information between the target entity and the attribute is realized, and the relation information between the target entity and the attribute can be accurately obtained.

With further reference to fig. 3, fig. 3 illustrates a flow 300 of another embodiment of a method for determining labeling style information according to the present disclosure. The method for determining the annotation style information may comprise the steps of:

step 301, obtaining a medical record text.

Step 302, the medical record text is identified, and target relation information between the target entity in the medical record text and each attribute in at least one attribute is obtained.

Step 303, determining the relative position between each attribute and the target entity according to the position information of each attribute in the at least one attribute and the position information of the target entity.

In this embodiment, an execution body (e.g., the server 105 shown in fig. 1) of the method for determining the labeling style information may determine a relative position between each attribute and the target entity according to position information of each attribute of the at least one attribute.

Specifically, the relative location between each attribute and the target entity can be determined based on each attribute in the medical record text, and the location information of the target entity on the screen of a server (e.g., server 105 shown in FIG. 1).

In one example, the location information of the target entity and attribute may be determined by offsetLeft and offsetTop. And the relative positions of the target entity and the attribute can be determined by the difference value of offsetLeft and offsetTop of the target entity and the attribute.

And step 304, determining the labeling style information according to the target relation information and the relative position corresponding to each attribute.

In this embodiment, the execution body determines the labeling style information according to the target relationship information and the relative position corresponding to each attribute.

Here, a mapping relationship between the labeling style information and the target relationship information and the relative position corresponding to each attribute may be previously established to determine the labeling style information according to the target relationship information and the relative position corresponding to each attribute. The labeling style information described above may be used to label target relationship information between each attribute and the target entity. The marking style information may include marking lines and/or marking text. The style presentation form of the labeling style information may include a static display, a dynamic display, and the like.

In this embodiment, specific operations of steps 301 and 302 are described in detail in steps 201 and 202 in the embodiment shown in fig. 2, and are not described herein.

As can be seen from fig. 3, the method for determining the marking pattern information in this embodiment highlights the step of determining the marking pattern information, compared to the corresponding embodiment of fig. 2. Thus, the solution described in this embodiment determines the relative position between each attribute and the target entity according to the position information of each attribute in the at least one attribute and the position information of the target entity; then determining labeling style information according to the target relation information and the corresponding relative position of each attribute; the corresponding labeling style information can be determined based on the relative position determined by the position information of each attribute in at least one attribute and the position information of the target entity and the target relation information, so that the labeling of the target relation information between the target entity and the attributes is realized, and the relation information between the target entity and the attributes can be accurately obtained.

In some optional implementations of the present embodiment, determining the relative position between each attribute and the target entity based on the location information of each attribute in the at least one attribute and the location information of the target entity may include:

determining at least one attribute in the medical record text and the position information of the target entity on the preset screen according to the size information of the preset screen; and determining the relative position between each attribute and the target entity according to the position information of each attribute and the position information of the target entity.

In this implementation manner, the executing body may determine, according to the size information of the preset screen, the location information of each attribute and the target entity in the medical record text on the preset screen; and then, determining the relative position between each attribute and the target entity according to the position information of each attribute and the position information of the target entity. The preset screen may be a screen of a server (e.g., the server 105 shown in fig. 1) for displaying medical record text. According to the size information of the preset screen, the display arrangement of the medical record text on the preset screen can be determined, for example, the medical record text is displayed in 3 rows on the preset screen.

In this implementation manner, when the size information of the preset screen changes, the method for determining the labeling style information may further include:

determining the relative position between the attribute and the target entity according to the new size information, and redefining the labeling style information; or, before the size information of the preset screen is changed (for example, after step 203 is performed), an image of the marking pattern information is acquired, so that when the size information of the preset screen is changed, the image of the marking pattern information is displayed on the screen corresponding to the new size information.

In one example, after the size information of the preset screen is changed, the new size information may be listened to through a window. Addeventlist, and then the annotation style information may be redetermined through a throttle algorithm (e.g., 100ms interval).

In this implementation manner, the executing body may determine, according to the duration information of the preset screen, location information of each attribute information in at least one attribute in the medical record text, and location information of the target entity, and determine a relative location between each attribute and the target entity.

In some optional implementations of the present embodiment, the labeling style information may include: annotating text and/or annotating lines.

In this implementation, the above noted annotation text may be used to reveal target relationship information between each attribute and the target entity. The annotation text may include at least one of: font size, color, character spacing of text. The above noted annotation lines, which may include lines (e.g., dashed or solid lines or transparent lines or arrowed lines), line widths, line colors, etc., may connect each attribute to the target entity via lines.

The labeling text is used for labeling the target relation information, and the labeling lines are used for pointing to the attributes and the target entities corresponding to the target relation information.

In one example, in fig. 4 (a), the labeling text is used to label the target relationship information (i.e., 'frequency of occurrence') between 'cough (i.e., target subject)' and 'repetition', the labeling line is used to point to 'cough' and 'repetition', and the arrow of the labeling line points to 'cough'.

It should be noted that, the display effects of the labeling text and the labeling line may be set according to the requirement of the user or the size information of the screen.

In this implementation manner, the target relationship information between each attribute and the target entity may be labeled according to a labeling text and/or a labeling line included in the labeling style information.

In some optional implementations of this embodiment, if the labeling style information includes labeling text and labeling lines, the labeling text includes at least one of: the position information of the labeling text on the labeling lines and the distance between the labeling texts.

The annotation lines may include: the system comprises a connection starting point and a connection ending point, wherein the connection starting point is used for pointing to each attribute, and the connection ending point is used for pointing to a target entity.

It should be noted that, the labeling text may be in any direction of the labeling line, for example, in any position above and below the labeling line; or, the labeling text is displayed on the labeling line.

In this implementation, the target relationship information between the attribute and the target entity may be annotated by the annotation line and the annotation text.

In some optional implementations of this embodiment, the annotation text may include at least one of: the position information of the marked text, the distance between the marked text and the font information of the marked text.

In this implementation, the location information of the labeling text may be location information of the labeling text on a preset screen (e.g., a screen of the server 105 shown in fig. 1). The distance between the markup texts may be the distance between the characters in the markup texts. The font information of the markup text may include font, color, and height of the markup text equal to font-related information.

In this implementation, the height of the labeling text may be lower than the height of the labeling lines to avoid overlapping the labeling text and the labeling lines.

In some optional implementations of the present embodiment, the annotation line may include a link start point that may be used to point to each attribute and a link end point that may be used to point to the target entity; or the link start point may be used to point to a target entity and the link end point may be used to point to each attribute.

In the implementation manner, the attribute corresponding to a certain labeling text and the target entity can be determined through the pointing direction of the labeling line.

In the implementation mode, the attribute and the target entity with the corresponding relation can be reflected through the pointing direction of the marked line.

In some optional implementations of this embodiment, the labeling line may further include a first inflection point, and the labeling text is displayed in a preset direction of the first inflection point.

In this implementation, the labeling text is displayed in a preset direction of the first inflection point of the labeling line, e.g., the labeling text is displayed above, below, to the left, to the right, or at any other location of the first inflection point.

In this implementation manner, the execution body may display the labeling text in a preset direction of the first inflection point of the labeling line.

In some optional implementations of this embodiment, the labeling line may further include a first inflection point and a second inflection point, and the labeling text is displayed in a preset direction of a line connecting the first inflection point and the second inflection point.

In this implementation manner, the labeling text may be displayed in a preset direction of the first inflection point and the second inflection point, for example, the labeling text is displayed above, below, to the left, to the right, or any other position of the first inflection point and the second inflection point.

It should be noted that, the corners of the marking line at the first inflection point and the second inflection point may be any angle, and as long as the marking line does not overlap with the medical record text, the marking line may be included in the scope of the embodiments of the disclosure. Optionally, the corner of the marking line at the first inflection point and/or the second inflection point is 90 degrees.

In fig. 4 (a), the marked text is displayed above the line connecting the first inflection point and the second inflection point, the corner of the first store and the second inflection point being 90 degrees. In the 4 (a), the attribute and the target entity are displayed on the same line of the preset screen, and the target relationship information includes that the target relationship information between 'repetition' and 'cough' is 'occurrence frequency', 'more than 10 years' and 'cough' is 'time', 'emphasis' and 'cough' is 'return state', '3 days' and 'cough' is 'return time', wherein 'occurrence frequency', 'time', 'return state', 'return time' is the labeling text. In the 4 (a), the marked lines between 'repeat, more than 10 years, aggravate, 3 days' and 'cough' are respectively pointed to by 'repeat, more than 10 years, aggravate, 3 days' and 'cough'; the arrow on the marked line points to the 'cough'.

In fig. 4 (b), the attributes and target entities are displayed in different rows of a preset screen (e.g., the screen of the server 105 shown in fig. 1).

In this fig. 4 (b), the target relationship information between 'cough (i.e., target entity)' and '2006' is 'time'; the target relation information between 'cough' and 'after spring cooling' is 'induction condition'; the target relation information between 'cough' and 'repetition' is 'frequency of occurrence'; the target relationship information between 'cough' and 'quantity' is 'degree'; the information on the target relationship between 'cough' and 'post-cephalosporin infection administration' is 'condition for regression'; the information on the target relationship between 'cough' and 'gradual symptom relief' is 'state of return'.

It should be noted that, if the attribute is on the target entity or in the same line with the target entity, the attribute is used as the connection start point of the marking line, moves upward, moves laterally to above the target entity, and finally points to the target entity. If the attribute is below the target entity, the attribute is used as a connecting line starting point of the marking line, moves upwards to the upper part of the line, moves transversely to the lower part of the target entity and finally points to the target entity.

In fig. 4 (c), the medical record text is displayed on a preset screen (e.g., the screen of the server 105 shown in fig. 1) in 3 rows, with the target entity displayed on row 2.

In fig. 4 (c), the target relationship information between 'wheezing (i.e., target entity)' and 'autumn 2006' is 'time'; the target relation information between 'wheeze' and 'after cooling' is 'induced condition'; the target relation information between 'wheeze' and 'post-activity' is 'return condition'; the target relation information between 'wheeze' and 'aggravation' is 'return state'; the target relationship information between 'wheeze' and 'post anti-infective treatment' is 'return condition'; the target relationship information between 'wheeze' and '1 month' is 'return time'; the target relationship information between 'wheeze' and 'gradual release' is 'return state'.

It should be noted that if the attribute is in the line on the target entity or in the same line as the target entity, the attribute is used as the connection start point of the marking line, moves upward, moves laterally to above the target entity, and finally points to the target entity. If the attribute is in the next row of the target entity, the attribute is used as a connecting line starting point of the marking line, moves upwards to the upper part of the row, moves transversely to the lower part of the target entity and finally points to the target entity.

In fig. 4 (d), the medical record text is displayed on a preset screen (e.g., the screen of the server 105 shown in fig. 1) for 2 rows, wherein the target entity is displayed on row 2.

In this fig. 4 (d), the target relationship information between 'wheezing (i.e., target entity)' and '12 months of 2010' is 'time'; the target relation information between 'wheeze' and 'after cooling' is 'induced condition'; the target relationship information between 'wheeze' and 'reappearance' is 'frequency of occurrence'; the target relationship information between 'wheeze' and 'apparent cough' is 'accompanying state'.

It should be noted that, the attribute is used as the connection start point of the labeling line, moves upward, moves laterally above the target entity, and finally points to the target entity.

In this implementation manner, the labeling text may be displayed in a preset direction of the connecting line of the first inflection point and the second inflection point of the labeling line.

In some optional implementations of this embodiment, if at least two attributes included in the at least one attribute are displayed on the preset screen in a same line, a height of a labeling line corresponding to each of the at least two attributes on the preset screen is different.

In this implementation manner, the executing body may display a marking line corresponding to each attribute on a preset screen according to a preset height corresponding to the attribute in at least two attributes.

It should be noted that the preset height may be set according to the size information of the preset screen and/or the requirement of the user.

In this implementation manner, in order to avoid overlapping of the labeling lines corresponding to the plurality of attributes, the labeling lines corresponding to each of the plurality of attributes may be displayed according to different heights.

In some optional implementations of this embodiment, the height of the annotation line corresponding to each of the at least two attributes on the preset screen is a product of the display order of each attribute on the preset screen and the preset height.

In this implementation manner, the executing body may determine the height of the corresponding marking line according to the product of the display order of each attribute of the at least two attributes on the preset screen and the preset height.

In one example, each of the at least two attributes is numbered in the order in which the medical record text is displayed on the preset screen, with index starting at 1. The height of the marking lines is determined by the product of lineHeight and index in the options, so that the marking lines can be displayed in a layered mode, and the connecting lines are prevented from being overlapped.

Correspondingly, in 4 (a), the heights of the marking lines corresponding to 'repeated', 'more than 10 years', 'emphasized', and '3 days' are different, and the heights of the marking lines are 1 x lineheight, 2 x lineheight, 3 x lineheight, and 4 x lineheight in sequence.

It should be noted that, the lineHeight may be the height of each line of text in the medical record text, or may be set randomly by the user.

In addition, the height of the annotation text may be less than the height of the corresponding annotation line.

In some optional implementations of the present embodiment, the method for determining the labeling style information further comprises: acquiring preset relation information; and displaying the doctor advice quality control prompt information in response to the target relation information not conforming to the preset relation information.

In this implementation manner, the executing body may acquire preset relationship information, so as to display quality control prompt information of the medical advice when the target relationship information is inconsistent with the preset relationship information.

In one example, the target relationship information corresponding to ' cough ' for more than 10 years ' is ' return condition '; the preset relationship information corresponding to 'cough' and 'more than 10 years' is 'time'. At this time, the target relation information is inconsistent with the preset relation information, and the doctor's advice quality control prompt information is displayed. For example, 'return condition' highlight, red color display, etc.; or the text reminding target relation information is inconsistent with the preset relation information; or the voice reminding target relation information is inconsistent with the preset relation information.

In the implementation mode, the target relation information between the target entity and the attribute in the medical record text can be accurately marked, so that the accuracy rate of medical advice quality control is improved.

In some alternative implementations of the present embodiment, the annotation lines and annotation text may be drawn by embedded elements (span tags) or SVG.

Here, the Span tag is located inside the Span tag of the attribute, the Span tag of the attribute is located relatively, and the embedded element is located absolutely. In the process of drawing the marking line, the Span label can position the relative attribute of the starting point of the marking line, and the position of the starting point of the connecting line is not required to be repeatedly determined.

Here, the annotation lines and the annotation text can be drawn by means of scalable vector graphics (Scalable Vector Graphics, SVG). The SVG may be used to handle graphics class requirements. For relatively complex visual graphics, annotation of attribute relationships can be achieved on SVG canvas by embedding the canvas on the original element. SVG can decouple mark text and mark lines, which is beneficial to the maintenance of items.

In one example, the annotation line may be drawn by a "span" tab: the line pointed out from the attribute, the source is above the left side of the attribute, and the height is the product of lineHeight and index in options.

Note that js may draw a line between the attribute and the subject by the method of createElement, appendChild. The start point of the connecting line is the position on the left side of the attribute, and the end point is the position on the left side of the main body.

In the implementation mode, the relative attribute of the starting point of the marking line is positioned absolutely, and the starting point position of the marking line does not need to be determined repeatedly.

In one example, a transverse line connecting the source and the target (e.g., a line connecting the first inflection point and the second inflection point) may be drawn as follows.

Specifically, the left position of the cross line connecting the source and the target is affected by the attribute to the left or right of the target entity. When the attribute is at the left side of the target entity, the left coordinate of the connecting line is 0; when the attribute is to the right of the target entity, the left coordinate of the link is the absolute value of the distance of the negative attribute from the target entity. The position of Top is consistent with the calculation of height in the line pointed out by the dependency, and is the product of lineHeight and index in negative options. The width of a link is the absolute value of the distance of the attribute from the target entity.

In one example, the annotation text on the transverse line (e.g., the line connecting the first inflection point and the second inflection point) may be drawn as follows.

Specifically, the labeling text on the horizontal line is in the middle of the horizontal line of the connecting line source and the target, and when the attribute is at the left side of the target entity, the left coordinate of the connecting line is half of the absolute value of the distance between the attribute and the target entity; when the attribute is to the right of the target entity, the left coordinate of the link is half the absolute value of the distance of the negative attribute to the target entity. The top value of the text is slightly higher than the horizontal line position of the link source and the target, and is the product of lineHeight and index in negative options plus a fixed height, for example, 14px.

In one example, a line (e.g., a first inflection point (e.g., an inflection point near a link endpoint) that points to a target entity may be drawn as follows.

Specifically, the left position of the line pointing to the target entity is affected by whether the attribute is to the left or right of the target entity. In addition, the height and bottom positions of the line are affected by the attribute being on the top side (including the attribute and the target entity in the same row) or the bottom side of the target entity.

In one example, an arrow pointing onto the annotation line can be drawn as follows.

In some optional implementations of this embodiment, in order to make the labeling text and the labeling line and the medical record text not be displayed on the preset screen in a overlapping manner, the method for determining the labeling style information further includes: and setting the display requirement of the medical record text on a preset screen.

In one example, the display requirements may include at least one of:

(1) Each row can display 5-12 attributes at most; (2) When the attribute is folded, drawing a labeling line by taking the left side of the first character in the attribute as a connecting line starting point of the labeling line; (3) The target entity attribute extraction area is set to a preset width, for example 250px.

In one example, the display requirements may further include: the line spacing of the medical record text on the preset screen.

In this implementation, the layout of the first attribute of the line may be set to be an inline-block element (display). And calculating the travel distance according to the number of the marking lines between the two rows.

In the implementation mode, the marking style information can be determined by determining the position information of the target main body and the attribute in the text in the medical record text, so that the development cost is reduced. Furthermore, it is possible to provide a device for the treatment of a disease.

With further reference to fig. 5, fig. 5 shows a schematic diagram of one application scenario of the method for determining labeling style information according to the present disclosure. In this application scenario, the user can click on selecting an entity (e.g., 'cough') in the medical record text displayed on the screen of the server 501 (e.g., server 105 shown in fig. 1), and display on the screen the annotation style information for annotating the entity with a correspondence to the target relationship information entity between the entity and the corresponding at least one attribute.

In fig. 5, after 'cough' is selected, it is displayed on a preset screen as follows: the target relation information between 'repeated' and 'cough' is 'occurrence frequency', 'more than 10 years' and 'cough' is 'time', 'emphasis' and 'cough' is 'return state', '3 days' and 'cough' is 'return time', wherein 'occurrence frequency', 'time', 'return state', 'return time' is marked text. In the 4 (a), the marked lines between 'repeat, more than 10 years, aggravate, 3 days' and 'cough' are respectively pointed to by 'repeat, more than 10 years, aggravate, 3 days' and 'cough'; the arrow on the marked line points to the 'cough'.

In this implementation manner, the labeling style information may be generated on a preset screen through a span tag or SVG.

With further reference to fig. 6, as an implementation of the method shown in the foregoing figures, the present disclosure provides an embodiment of an apparatus for determining annotation style information, where the apparatus embodiment corresponds to the method embodiment shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 6, the apparatus 600 for determining the labeling style information of the present embodiment may include: a text acquisition module 601, a text recognition module 602, and a style determination module 603. Wherein, the text acquisition module 601 is configured to acquire medical record text; the text recognition module 602 is configured to recognize the medical record text to obtain target relationship information between a target entity in the medical record text and each attribute in the at least one attribute; the style determining module 603 is configured to determine corresponding labeling style information according to the target relationship information and the relative position between each attribute and the target entity, wherein the labeling style information is used for labeling the target relationship information.

In the present embodiment, in the apparatus 600 for determining the labeling style information: the specific processing of the information obtaining module 601, the requirement determining module 602, the weight determining module 603 and the result determining module 604 and the technical effects thereof may refer to the relevant descriptions of steps 201 to 204 in the corresponding embodiment of fig. 2, and are not repeated herein.

In some optional implementations of the present embodiment, the style determination module 603 includes: a position determining unit configured to determine a relative position between each attribute and the target entity based on the position information of each attribute of the at least one attribute and the position information of the target entity; and a style determining unit configured to determine the labeling style information according to the target relationship information and the relative position corresponding to each attribute.

In some optional implementations of the present embodiment, the location determination unit is further configured to: determining the position information of each attribute and the target entity on the preset screen in the medical record text according to the size information of the preset screen; and determining the relative position between each attribute and the target entity according to the position information of each attribute and the target entity on the preset screen.

In some optional implementations of the present embodiment, labeling style information includes: labeling text and/or labeling lines; the labeling text is used for labeling the target relation information, and the labeling lines are used for pointing to the attributes and the target entities corresponding to the target relation information.

In some optional implementations of this embodiment, the labeling lines include: the first inflection point and the second inflection point are displayed on the marked text in the preset direction of the connecting line of the first inflection point and the second inflection point.

In some optional implementations of the present embodiment, the means for determining the labeling style information further comprises: the information acquisition module is configured to acquire preset relation information; the information display module is configured to display doctor advice quality control prompt information in response to the fact that the target relation information does not accord with the preset relation information.

In some optional implementations of the present embodiment, the means for determining the labeling style information further comprises: and the generating style module is configured to generate the labeling style information on a preset screen by using the span label or the SVG.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

Fig. 7 illustrates a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the apparatus 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in device 700 are connected to I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the respective methods and processes described above, for example, a method for determining the labeling style information. For example, in some embodiments, the method for determining annotation style information may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 700 via ROM 702 and/or communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method for determining the annotation style information described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the method for determining the labeling style information by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

Artificial intelligence is the discipline of studying computers to simulate certain mental processes and intelligent behaviors (e.g., learning, reasoning, thinking, planning, etc.) of humans, both hardware-level and software-level techniques. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural voice processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions mentioned in the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A method for determining annotation style information, comprising:

acquiring a medical record text;

identifying the medical record text to obtain target relation information between a target medical entity in the medical record text and each attribute in at least one attribute;

determining corresponding labeling style information according to the target relation information and the relative position between the position information of each attribute on a preset screen and the position information of the target medical entity on the preset screen, wherein the labeling style information is used for labeling the target relation information through labeling texts and/or labeling lines, the labeling texts are used for labeling the target relation information, and the labeling lines are used for pointing to the attributes corresponding to the target relation information and the target medical entity;

when the size information of the preset screen changes, determining the relative position between the determined position information of each attribute on the new screen and the position information of the target medical entity on the new screen according to the new size information, and re-determining the labeling style information; or, acquiring an image of the marking style information, and displaying the image of the marking style information on the new screen when the size information of the preset screen is changed, wherein the new screen is a screen corresponding to the new size information.

2. The method of claim 1, wherein the determining corresponding labeling style information based on the target relationship information and the relative position between the location information of each attribute on a preset screen and the location information of the target medical entity on the preset screen comprises:

determining the relative position between each attribute and the target medical entity according to the position information of each attribute in the at least one attribute on the preset screen and the position information of the target medical entity on the preset screen;

and determining the labeling style information according to the target relation information and the relative position corresponding to each attribute.

3. The method of claim 2, wherein the determining the relative position between each of the at least one attribute and the target medical entity based on the location information of each of the at least one attribute on the preset screen and the location information of the target medical entity on the preset screen comprises:

determining each attribute in the medical record text and the position information of the target medical entity on the preset screen according to the size information of the preset screen;

And determining the relative position between each attribute and the target medical entity according to the position information of each attribute and the target medical entity on the preset screen.

4. The method of claim 1, wherein the annotation line comprises: and the marked text is displayed in a preset direction of a connecting line of the first inflection point and the second inflection point.

5. The method according to claim 1 or 4, wherein if at least two attributes included in at least one attribute are displayed on the preset screen in a same line, a height of a marking line corresponding to each of the at least two attributes is different on the preset screen.

6. The method of claim 5, wherein a height of a markup line corresponding to each of the at least two attributes on the preset screen is a product of a display order of each attribute on the preset screen and a preset height.

7. The method of claim 1, the method further comprising:

acquiring preset relation information;

and displaying the doctor advice quality control prompt information in response to the target relation information not conforming to the preset relation information.

8. The method of claim 1 or 7, the method further comprising:

And generating the labeling style information on the preset screen by using span labels or SVG.

9. An apparatus for determining annotation style information, comprising:

the text acquisition module is configured to acquire medical record text;

the text recognition module is configured to recognize the medical record text to obtain target relation information between a target medical entity in the medical record text and each attribute in at least one attribute;

the style determining module is configured to determine corresponding labeling style information according to the target relation information and the relative position between the position information of each attribute on a preset screen and the position information of the target medical entity on the preset screen, wherein the labeling style information is used for labeling the target relation information through labeling texts and/or labeling lines, the labeling texts are used for labeling the target relation information, and the labeling lines are used for pointing to the attributes corresponding to the target relation information and the target medical entity;

a redetermining style module configured to redetermine labeling style information according to the new size information, the determined relative position between the position information of each attribute on the new screen and the position information of the target medical entity on the new screen when the size information of the preset screen changes; or, acquiring an image of the marking style information, and displaying the image of the marking style information on the new screen when the size information of the preset screen is changed, wherein the new screen is a screen corresponding to the new size information.

10. The apparatus of claim 9, wherein the pattern determination module comprises:

a position determining unit configured to determine a relative position between each of the at least one attribute and the target medical entity based on the position information of the each attribute on the preset screen and the position information of the target medical entity on the preset screen;

and the style determining unit is configured to determine the labeling style information according to the target relation information and the relative position corresponding to each attribute.

11. The apparatus of claim 10, wherein the location determination unit is further configured to:

12. The apparatus of claim 9, wherein the annotation line comprises: and the marked text is displayed in a preset direction of a connecting line of the first inflection point and the second inflection point.

13. The apparatus according to claim 9 or 12, wherein if at least two attributes included in at least one attribute are displayed on the preset screen in a same line, a height of a marking line corresponding to each of the at least two attributes is different on the preset screen.

14. The apparatus of claim 13, wherein a height of a markup line corresponding to each of at least two attributes on the preset screen is a product of a display order of each attribute on the preset screen and a preset height.

15. The apparatus of claim 9, the apparatus further comprising:

the information acquisition module is configured to acquire preset relation information;

and the information display module is configured to display doctor advice quality control prompt information in response to the target relation information not conforming to preset relation information.

16. The apparatus according to claim 9 or 15, the apparatus further comprising:

and the generating style module is configured to generate the labeling style information on the preset screen by using span labels or SVGs.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.