CN117827925A

CN117827925A - Data management method and related device

Info

Publication number: CN117827925A
Application number: CN202211186331.XA
Authority: CN
Inventors: 臧振飞; 滕腾; 陈玉梅
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2022-09-27
Filing date: 2022-09-27
Publication date: 2024-04-05
Also published as: WO2024067442A1

Abstract

The embodiment of the application discloses a data management method and a related device, which are characterized in that the method comprises the following steps: identifying index type data and non-index type data of each physical examination report in the N physical examination reports; generating index type structured data corresponding to N physical examination reports based on a first database and index type data in each physical examination report, wherein the index type structured data comprises structured data of a plurality of index items, and the first database comprises index type sample data; and generating non-index type structured data corresponding to the N physical examination reports based on the second database and the non-index type data in each physical examination report, wherein the non-index type structured data comprises structured data of a plurality of non-index items, and the second database comprises non-index type sample data. By adopting the embodiment of the application, the health data of the user can be classified, standardized and managed, and the user experience is improved.

Description

Data management method and related device

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a data management method and related devices.

Background

Under the background of general enhancement of health management consciousness, the average physical examination frequency is increased year by year, and the average physical examination reports are more and more, so that the reasonable utilization and the enabling of various physical examination report data resources are of great market value for the construction of health research platforms and the medical health data management industry.

Because of the numerous physical examination institutions in the market at present, the report types and styles are different, the consistency of similar data caused by the difference of physical examination equipment/methods is low, and a method for uniformly managing report data of different types is hardly available in the market at present. The existing intelligent identification and management of physical examination report data mainly comprises the following steps:

1) Carrying out text content analysis of region template matching type on a physical examination report transmitted by a user in a fixed template matching mode;

2) Performing character recognition (Optical Character Recognition, OCR) on the full text content of the physical examination report, and extracting information in a regular or mechanism-specific pattern-based manner;

3) The index type physical examination data is structurally managed in a key value mode of index name-index value, and non-index type data is stored and managed in an original text storage mode;

therefore, the physical examination report data is intelligently identified in a mode independent of template matching, and different types of health data are classified, standardized and managed, so that the technical basis of physical examination report is effectively utilized.

Disclosure of Invention

The technical problem to be solved by the embodiments of the present application is to provide a data management method and related device, so as to perform classification standardized management on health data of a user, thereby improving user experience.

In a first aspect, embodiments of the present application provide a data management method, where the method includes: identifying index type data and non-index type data of each physical examination report in N physical examination reports, wherein the index type data comprises at least one index item, the non-index type data comprises at least one non-index item, and N is an integer greater than 0; generating index type structured data corresponding to the N parts of physical examination reports based on a first database and the index type data in each part of physical examination reports, wherein the index type structured data comprises structured data of a plurality of index items, the structured data of each index item comprises one or more of index standard names, index abbreviations, index ranges, index units and index segmentation intervals, and the first database comprises index type sample data; generating non-index type structured data corresponding to the N physical examination reports based on a second database and the non-index type data in each physical examination report, wherein the non-index type structured data comprises a plurality of structured data of non-index items, the structured data of each non-index item comprises one or more of an examination department, an examination item, an examination result and an examination suggestion, and the second database comprises non-index type sample data.

In the embodiment of the invention, any form of physical examination report can be identified, and the classification of the index type data area and the non-index type data area in the single page data can be realized based on the single page text block interval characteristic and the gray level continuous difference variability calculation of the interested area, so as to determine the index type data and the non-index type data in each physical examination report. Further, the index class data can be output as multi-class structured index items with standard structures based on the content of the index class data and an index class knowledge base; the non-index data can be output as standard structure data items with complete data links based on the physical examination specific disease knowledge graph constructed by combining physical examination health data standards. In summary, the method and the device can identify and extract index type data and non-index type data in a plurality of types of physical examination reports in the form of pictures or electronic files under the condition of not limiting physical examination institutions, report types and specific templates, and can rapidly generate standardized and structured physical examination health data so as to conduct classified standardized management on the health data of users, thereby improving user experience.

In one possible implementation manner, the identifying index class data and non-index class data of each physical examination report in the N physical examination reports includes: identifying text information and image information in each physical examination report and position information corresponding to the text information; and determining the index type data and the non-index type data in each physical examination report based on the text information, the image information and the position information.

In the embodiment of the invention, the physical examination reports with different formats can be identified based on the intelligent physical examination report identification algorithm so as to obtain the text information, the image information and the position information corresponding to the text information in each physical examination report, thereby determining the index type data and the non-index type data in each physical examination report and facilitating the subsequent classified management of the physical examination data of the user.

In one possible implementation manner, the generating, based on the first database and the index class data in each of the physical examination reports, index class structured data corresponding to the N physical examination reports includes: performing correlation matching on the one or more index items in each physical examination report and the first database respectively to obtain structured data of a plurality of index items; the method further comprises the steps of: and summarizing the structured data corresponding to the same index item in the structured data of the index items to obtain summarized index type structured data.

In the embodiment of the invention, because the index data formats, index names, index values and the like of the same index in different physical examination reports may not be unified, the index data extracted from the original physical examination report can be subjected to correlation matching and extraction processing by combining with a pre-built index data special knowledge base (namely the first database), and then the index data extracted from different reports can be subjected to specific structure output, namely the structured index data items which can be standardized such as index standard names, index values, index ranges, index units and interval attributes to which the index belongs are output, so that the standardized management of the index data is realized. Meanwhile, the index data with the same index name can be arranged, so that data management of cross reports is realized.

In one possible implementation, the structured data of each of the index items includes an index segmentation section, and the method further includes: determining the index segmentation section corresponding to each index item from a plurality of preset segmentation sections, wherein the plurality of preset segmentation sections comprise a plurality of low-limit sections, low-limit early-warning sections, ideal sections, high-limit early-warning sections and high-limit sections.

In the embodiment of the invention, when the structured data corresponding to each index item is determined, the segmented interval attribute marking can be performed based on the index value corresponding to each index item, namely, the index segmented interval corresponding to each index item can be determined from a plurality of preset segmented intervals, so that analysis on the physical examination result of the user index item is realized, and the user experience is improved.

In a possible implementation manner, the generating, based on the second database and the non-index class data in each physical examination report, non-index class structured data corresponding to the N individual examination reports includes: extracting target keywords of each non-index item of each physical examination report; and matching the target keywords respectively corresponding to the non-index items with the non-index sample data in the second database to obtain structured data of the non-index items.

In the embodiment of the invention, since the non-index data in each physical examination report has no fixed format output, the non-index data extracted from the original report can be identified by keywords and can be matched with a pre-constructed non-index physical examination specific disease knowledge graph (namely, the pre-constructed non-index physical examination specific disease knowledge graph can be understood as the second database), so that the non-index data extracted from different reports are output with a specific structure, namely, the output can be a standardized structured non-index data item of 'inspection department, inspection detail item, inspection conclusion and inspection suggestion', thereby realizing standardized management of the non-index data.

In a possible implementation manner, the method is applied to a terminal device, where the terminal device includes a display screen, and the method further includes: generating an index trend graph aiming at target index items in the summarized index-type structured data, wherein the target index items are any one of a plurality of index items in the summarized index-type structured data; displaying the index trend graph corresponding to the target index item through the display screen; and receiving a first operation, and responding to the first operation, and displaying a physical examination report corresponding to the target index item through the display screen.

In the embodiment of the invention, for index data, the transformation trend of the index can be displayed through the interval index trend statistical graph, and one-key jump to index detail data pages of the same index in different institutions and different reports can be realized, so that unified trend management and data viewing can be facilitated.

In one possible implementation, the method further includes: displaying the structured data of a plurality of non-index items through the display screen; and receiving a second operation, and responding to the second operation, and displaying a physical examination report corresponding to a target non-index item through the display screen, wherein the target non-index item is one of the non-index items.

In the embodiment of the invention, for non-index data, a user can be supported to jump between the extracted structured data and the original data by one key, and related content can be accurately highlighted in the original data, so that the steps that the user needs to frequently switch and reserve paper original reports among different reports are avoided, and the interaction convenience and experience intuitiveness of report management and data association are improved.

In a second aspect, embodiments of the present application provide a data management apparatus, where the apparatus includes: the first identification unit is used for identifying index type data and non-index type data of each of N physical examination reports, wherein the index type data comprises at least one index item, the non-index type data comprises at least one non-index item, and N is an integer greater than 0; the first processing unit is used for generating index type structured data corresponding to the N parts of physical examination reports based on a first database and the index type data in each part of physical examination reports, wherein the index type structured data comprises structured data of a plurality of index items, the structured data of each index item comprises one or more of index standard names, index abbreviations, index ranges, index units and index segmentation intervals, and the first database comprises index type sample data; the second processing unit is configured to generate non-index type structured data corresponding to the N physical examination reports based on a second database and the non-index type data in each physical examination report, where the non-index type structured data includes a plurality of structured data of non-index items, each structured data of non-index items includes one or more of an inspection department, an inspection item, an inspection result, and an inspection suggestion, and the second database includes non-index type sample data.

In a possible implementation manner, the first processing unit is specifically configured to: identifying text information and image information in each physical examination report and position information corresponding to the text information; and determining the index type data and the non-index type data in each physical examination report based on the text information, the image information and the position information.

In a possible implementation manner, the first processing unit is specifically configured to: performing correlation matching on the one or more index items in each physical examination report and the first database respectively to obtain structured data of a plurality of index items; the method further comprises the steps of: and summarizing the structured data corresponding to the same index item in the structured data of the index items to obtain summarized index type structured data.

In one possible implementation, the structured data of each of the index items includes an index segmentation section, and the apparatus further includes: the third processing unit is used for determining the index segmentation section corresponding to each index item from a plurality of preset segmentation sections, wherein the preset segmentation sections comprise a plurality of low-limit early warning sections, ideal sections, high-limit early warning sections and high-limit sections.

In a possible implementation manner, the second processing unit is specifically configured to: extracting target keywords of each non-index item of each physical examination report; and matching the target keywords respectively corresponding to the non-index items with the non-index sample data in the second database to obtain structured data of the non-index items.

In one possible implementation, the apparatus includes a display screen, and the apparatus further includes: a fourth processing unit, configured to generate an index trend graph for a target index item in the summarized index-class structured data, where the target index item is any one of a plurality of index items in the summarized index-class structured data; displaying the index trend graph corresponding to the target index item through the display screen; and receiving a first operation, and responding to the first operation, and displaying a physical examination report corresponding to the target index item through the display screen.

In one possible implementation, the apparatus further includes: a fifth processing unit, configured to display, through the display screen, structured data of a plurality of non-index items; and receiving a second operation, and responding to the second operation, and displaying a physical examination report corresponding to a target non-index item through the display screen, wherein the target non-index item is one of the non-index items.

In a third aspect, the present application provides a computer storage medium, wherein the computer storage medium stores a computer program which, when executed by a processor, implements the method according to any one of the first aspects.

In a fourth aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor configured to support the electronic device to implement a corresponding function in a data management method provided in the first aspect. The electronic device may also include a memory for coupling with the processor that holds the program instructions and data necessary for the electronic device. The electronic device may also include a communication interface for the electronic device to communicate with other devices or communication networks.

In a fifth aspect, the present application provides a chip system comprising a processor for supporting an electronic device to implement the functions referred to in the first aspect above, e.g. to generate or process information referred to in the data management method above. In one possible design, the chip system further includes a memory to hold the necessary program instructions and data for the electronic device. The chip system can be composed of chips, and can also comprise chips and other discrete devices.

In a sixth aspect, the present application provides a computer program comprising instructions which, when executed by a computer, cause the computer to perform the method of any one of the first aspects above.

Drawings

Fig. 1 is a schematic structural diagram of an electronic device 100 according to an embodiment of the present invention.

Fig. 2 is a block diagram of a software architecture of the electronic device 100 according to an embodiment of the present invention.

Fig. 3 is an application scenario schematic diagram of a data management method according to an embodiment of the present invention.

Fig. 4 is a flow chart of a data identification method in an embodiment of the present application.

Fig. 5 is a schematic diagram of a single page data region classification according to an embodiment of the present invention.

Fig. 6 is a schematic diagram of index type physical examination data processing according to an embodiment of the present invention.

Fig. 7 is a schematic diagram of non-index data processing according to an embodiment of the present invention.

Fig. 8 is a flowchart of an application of intelligent identification to a physical examination report according to an embodiment of the present invention.

Fig. 9 is a flow chart of multi-region physical examination index trend statistics according to an embodiment of the present invention.

Fig. 10 is a schematic flow chart of labeling an index value segment interval at a server according to an embodiment of the present invention.

Fig. 11 is a schematic diagram of generating a multi-interval index trend statistical chart according to an embodiment of the present invention.

Fig. 12 is a schematic diagram of a trend statistical chart of multi-region physical examination indexes according to an embodiment of the present invention.

Fig. 13 is a schematic diagram of one embodiment of the present invention for skip forwarding of index type data.

Fig. 14 is a schematic flow chart of non-index type data labeling management according to an embodiment of the present invention.

Fig. 15 is a schematic diagram of presentation and user interaction of labeled non-index data in a terminal application according to an embodiment of the present invention.

Fig. 16 is a schematic flow chart of a data management method provided in the present application according to an embodiment of the present invention.

Fig. 17 is a schematic diagram of a data management apparatus provided in the present application according to an embodiment of the present invention.

Detailed Description

Embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

The terms "first," "second," "third," and "fourth" and the like in the description and in the claims of this application and in the drawings, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

Fig. 1 shows a schematic configuration of an electronic device 100.

The embodiment will be specifically described below taking the electronic device 100 as an example. It should be understood that electronic device 100 may have more or fewer components than shown, may combine two or more components, or may have a different configuration of components. The various components shown in the figures may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and/or application specific integrated circuits.

The electronic device 100 may include: processor 110, external memory interface 120, internal memory 121, universal serial bus (universal serial bus, USB) interface 130, charge management module 140, power management module 141, battery 142, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headset interface 170D, sensor module 180, keys 190, motor 191, indicator 192, camera 193, display 194, and subscriber identity module (subscriber identification module, SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, and the like.

It should be understood that the illustrated structure of the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, electronic device 100 may include more or fewer components than shown, or certain components may be combined, or certain components may be split, or different arrangements of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The processor 110 may include one or more processing units, such as: the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural network processor (neural-network processing unit, NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors.

The controller may be a neural hub and a command center of the electronic device 100, among others. The controller can generate operation control signals according to the instruction operation codes and the time sequence signals to finish the control of instruction fetching and instruction execution.

A memory may also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may hold instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to reuse the instruction or data, it can be called directly from the memory. Repeated accesses are avoided and the latency of the processor 110 is reduced, thereby improving the efficiency of the system.

In some embodiments, the processor 110 may include one or more interfaces. The interfaces may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver transmitter (universal asynchronous receiver/transmitter, UART) interface, a mobile industry processor interface (mobile industry processor interface, MIPI), a general-purpose input/output (GPIO) interface, a subscriber identity module (subscriber identity module, SIM) interface, and/or a universal serial bus (universal serial bus, USB) interface, among others.

It should be understood that the interfacing relationship between the modules illustrated in the embodiments of the present invention is only illustrative, and is not meant to limit the structure of the electronic device 100. In other embodiments of the present application, the electronic device 100 may also use different interfacing manners, or a combination of multiple interfacing manners in the foregoing embodiments.

The charge management module 140 is configured to receive a charge input from a charger. The charger can be a wireless charger or a wired charger.

The power management module 141 is used for connecting the battery 142, and the charge management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and/or the charge management module 140 and provides power to the processor 110, the internal memory 121, the external memory, the display 194, the camera 193, the wireless communication module 160, and the like.

The wireless communication function of the electronic device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, a modem processor, a baseband processor, and the like.

The electronic device 100 implements display functions through a GPU, a display screen 194, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 194 is used to display images, videos, and the like. The display 194 includes a display panel. The display panel may employ a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED) or an active-matrix organic light-emitting diode (matrix organic light emitting diode), a flexible light-emitting diode (flex), a mini, a Micro led, a Micro-OLED, a quantum dot light-emitting diode (quantum dot light emitting diodes, QLED), or the like. In some embodiments, the electronic device 100 may include 1 or N display screens 194, N being a positive integer greater than 1.

The electronic device 100 may implement photographing functions through an ISP, a camera 193, a video codec, a GPU, a display screen 194, an application processor, and the like.

The ISP is used to process data fed back by the camera 193. For example, when photographing, the shutter is opened, light is transmitted to the camera photosensitive element through the lens, the optical signal is converted into an electric signal, and the camera photosensitive element transmits the electric signal to the ISP for processing and is converted into an image visible to naked eyes. ISP can also optimize the noise, brightness and skin color of the image. The ISP can also optimize parameters such as exposure, color temperature and the like of a shooting scene. In some embodiments, the ISP may be provided in the camera 193.

The camera 193 is used to capture still images or video. The object generates an optical image through the lens and projects the optical image onto the photosensitive element. The photosensitive element may be a charge coupled device (charge coupled device, CCD) or a Complementary Metal Oxide Semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, which is then transferred to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV, or the like format. In some embodiments, electronic device 100 may include other cameras. The electronic device may further comprise a matrix emitter (not shown in the figures) for emitting light. The camera collects light reflected by the face to obtain a face image, and the processor processes and analyzes the face image and performs verification by comparing the face image with stored information of the face image.

The digital signal processor is used for processing digital signals, and can process other digital signals besides digital image signals. For example, when the electronic device 100 selects a frequency bin, the digital signal processor is used to fourier transform the frequency bin energy, or the like.

Video codecs are used to compress or decompress digital video. The electronic device 100 may support one or more video codecs. In this way, the electronic device 100 may play or record video in a variety of encoding formats, such as: dynamic picture experts group (moving picture experts group, MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

The NPU is a neural-network (NN) computing processor, and can rapidly process input information by referencing a biological neural network structure, for example, referencing a transmission mode between human brain neurons, and can also continuously perform self-learning. Applications such as intelligent awareness of the electronic device 100 may be implemented through the NPU, for example: image recognition, face recognition, speech recognition, text understanding, etc.

The external memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to enable expansion of the memory capabilities of the electronic device 100. The external memory card communicates with the processor 110 through an external memory interface 120 to implement data storage functions. For example, files such as music, video, etc. are stored in an external memory card.

The internal memory 121 may be used to store computer executable program code including instructions. The processor 110 executes various functional applications of the electronic device 100 and data processing by executing instructions stored in the internal memory 121. The internal memory 121 may include a storage program area and a storage data area. The storage program area may store applications (such as a face recognition function, a fingerprint recognition function, a mobile payment function, etc.) required for at least one function of the operating system. The storage data area may store data created during use of the electronic device 100 (e.g., face information template data, fingerprint information templates, etc.). In addition, the internal memory 121 may include a high-speed random access memory, and may further include a nonvolatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), and the like.

The electronic device 100 may implement audio functions through an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, an application processor, and the like. Such as music playing, recording, etc.

The audio module 170 is used to convert digital audio information into an analog audio signal output and also to convert an analog audio input into a digital audio signal.

The speaker 170A, also referred to as a "horn," is used to convert audio electrical signals into sound signals.

A receiver 170B, also referred to as a "earpiece", is used to convert the audio electrical signal into a sound signal.

Microphone 170C, also referred to as a "microphone" or "microphone", is used to convert sound signals into electrical signals.

The earphone interface 170D is used to connect a wired earphone. The headset interface 170D may be a USB interface 130 or a 3.5mm open mobile electronic device platform (open mobile terminal platform, OMTP) standard interface, a american cellular telecommunications industry association (cellular telecommunications industry association of the USA, CTIA) standard interface.

The pressure sensor 180A is used to sense a pressure signal, and may convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 180A may be disposed on the display screen 194. The pressure sensor 180A is of various types, such as a resistive pressure sensor, an inductive pressure sensor, a capacitive pressure sensor, and the like.

The gyro sensor 180B may be used to determine a motion gesture of the electronic device 100. In some embodiments, the angular velocity of electronic device 100 about three axes (i.e., x, y, and z axes) may be determined by gyro sensor 180B.

The proximity light sensor 180G may include, for example, a Light Emitting Diode (LED) and a light detector, such as a photodiode. The light emitting diode may be an infrared light emitting diode.

The ambient light sensor 180L is used to sense ambient light level. The electronic device 100 may adaptively adjust the brightness of the display 194 based on the perceived ambient light level. The ambient light sensor 180L may also be used to automatically adjust white balance when taking a photograph.

The fingerprint sensor 180H is used to collect a fingerprint. The electronic device 100 may utilize the collected fingerprint feature to unlock the fingerprint, access the application lock, photograph the fingerprint, answer the incoming call, etc. The fingerprint sensor 180H may be disposed below the touch screen, the electronic device 100 may receive a touch operation of a user on the touch screen in an area corresponding to the fingerprint sensor, and the electronic device 100 may collect fingerprint information of a finger of the user in response to the touch operation.

The temperature sensor 180J is for detecting temperature. In some embodiments, the electronic device 100 performs a temperature processing strategy using the temperature detected by the temperature sensor 180J.

The touch sensor 180K, also referred to as a "touch panel". The touch sensor 180K may be disposed on the display screen 194, and the touch sensor 180K and the display screen 194 form a touch screen, which is also called a "touch screen". The touch sensor 180K is for detecting a touch operation acting thereon or thereabout. The touch sensor may communicate the detected touch operation to the application processor to determine the touch event type. Visual output related to touch operations may be provided through the display 194. In other embodiments, the touch sensor 180K may also be disposed on the surface of the electronic device 100 at a different location than the display 194.

The keys 190 include a power-on key, a volume key, etc. The keys 190 may be mechanical keys. Or may be a touch key. The electronic device 100 may receive key inputs, generating key signal inputs related to user settings and function controls of the electronic device 100.

The indicator 192 may be an indicator light, may be used to indicate a state of charge, a change in charge, a message indicating a missed call, a notification, etc.

The SIM card interface 195 is used to connect a SIM card. The SIM card may be inserted into the SIM card interface 195, or removed from the SIM card interface 195 to enable contact and separation with the electronic device 100. In some embodiments, the electronic device 100 employs esims, i.e.: an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100.

The software system of the electronic device 100 may employ a layered architecture, an event driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture. In the embodiment of the invention, taking an Android system with a layered architecture as an example, a software structure of the electronic device 100 is illustrated.

Fig. 2 is a software configuration block diagram of the electronic device 100 according to the embodiment of the present invention.

The layered architecture divides the software into several layers, each with distinct roles and branches. The layers communicate with each other through a software interface. In some embodiments, the Android system is divided into four layers, from top to bottom, an application layer, an application framework layer, an Zhuoyun row (Android run) and system libraries, and a kernel layer, respectively.

The application layer may include a series of application packages.

As shown in fig. 2, the application package may include applications (also referred to as applications) such as cameras, gallery, calendar, phone calls, maps, navigation, WLAN, bluetooth, music, video, short messages, etc.

The application framework layer provides an application programming interface (application programming interface, API) and programming framework for application programs of the application layer. The application framework layer includes a number of predefined functions.

As shown in FIG. 2, the application framework layer may include a window manager, a content provider, a view system, a telephony manager, a resource manager, a notification manager, and the like.

The window manager is used for managing window programs. The window manager can acquire the size of the display screen, judge whether a status bar exists, lock the screen, intercept the screen and the like.

The content provider is used to store and retrieve data and make such data accessible to applications. The data may include video, images, audio, calls made and received, browsing history and bookmarks, phonebooks, etc.

The view system includes visual controls, such as controls to display text, controls to display pictures, and the like. The view system may be used to build applications. The display interface may be composed of one or more views. For example, a display interface including a text message notification icon may include a view displaying text and a view displaying a picture.

The telephony manager is used to provide the communication functions of the electronic device 100. Such as the management of call status (including on, hung-up, etc.).

The resource manager provides various resources for the application program, such as localization strings, icons, pictures, layout files, video files, and the like.

The notification manager allows the application to display notification information in a status bar, can be used to communicate notification type messages, can automatically disappear after a short dwell, and does not require user interaction. Such as notification manager is used to inform that the download is complete, message alerts, etc. The notification manager may also be a notification presented in the form of a chart or scroll bar text in the system top status bar, such as a notification of a background running application, or a notification presented on a screen in the form of a dialog interface. For example, a text message is prompted in a status bar, a prompt tone is emitted, the electronic device vibrates, and an indicator light blinks, etc.

Android run time includes a core library and virtual machines. Android run time is responsible for scheduling and management of the Android system.

The core library consists of two parts: one part is a function which needs to be called by java language, and the other part is a core library of android.

The application layer and the application framework layer run in a virtual machine. The virtual machine executes java files of the application program layer and the application program framework layer as binary files. The virtual machine is used for executing the functions of object life cycle management, stack management, thread management, security and exception management, garbage collection and the like.

The system library may include a plurality of functional modules. For example: surface manager (surface manager), media Libraries (Media Libraries), three-dimensional graphics processing Libraries (e.g., openGL ES), 2D graphics engines (e.g., SGL), etc.

The surface manager is used to manage the display subsystem and provides a fusion of 2D and 3D layers for multiple applications.

Media libraries support a variety of commonly used audio, video format playback and recording, still image files, and the like. The media library may support a variety of audio and video encoding formats, such as MPEG4, h.264, MP3, AAC, AMR, JPG, PNG, etc.

The three-dimensional graphic processing library is used for realizing three-dimensional graphic drawing, image rendering, synthesis, layer processing and the like.

The 2D graphics engine is a drawing engine for 2D drawing.

The kernel layer is a layer between hardware and software. The inner core layer at least comprises a display driver, a camera driver, an audio driver and a sensor driver.

Based on the technical problems set forth above, in order to facilitate understanding of the embodiments of the present invention, an application scenario of the embodiments of the present invention is described below.

Referring to fig. 3, fig. 3 is an application scenario schematic diagram of a data management method according to an embodiment of the present invention, where the method can perform classification standardized management on health data of a user, so as to improve user experience. The method can be applied to terminal equipment capable of performing man-machine interaction, such as mobile phones, tablet computers, personal computers (Personal Computer, PC) and the like. The main use scene can upload a physical examination report (one or more physical examination reports) for a terminal device user, then intelligently identify and extract page-by-page physical examination health data of the physical examination report of the user by the method provided by the application, and respectively carry out structural management and interactive presentation of a user terminal interface on index type health data and non-index type health data.

In the terminal equipment with the man-machine interaction function and the use scene, the intelligent identification of the physical examination report and the health data management of the user can be divided into the following steps: and uploading a physical examination report, intelligently identifying the physical examination report, extracting and processing health data and interactively presenting the health data by a user. The detailed description is as follows:

the user uploads a physical examination report: the user can upload the physical examination report pictures or files of the user through the terminal equipment with the functions of collecting, uploading and interacting pictures or electronic files, such as a mobile phone, a tablet, a personal portable computer and the like.

Intelligent identification of physical examination report: the server side can identify text information and space position information of the text in the physical examination report page by page after the physical examination report uploaded by the user from the client side. When the physical examination report intelligent identification is carried out, each page of content can be classified firstly, namely index type data and non-index type data in each page of content and the respective areas thereof can be classified and marked based on the single page text block area interval characteristic and the gray level continuous difference value variability calculation method of the interested areas (Region of Interest, ROI). And then, applying an index extraction algorithm capable of combining with a pre-constructed index knowledge base to index data, and applying a non-index pattern reasoning algorithm capable of combining with a pre-constructed specific disease knowledge pattern to non-index data to respectively and structurally identify and extract the two types of data. The intelligent recognition of the physical examination report will be described in detail later, and will not be described in detail here.

Health data extraction processing: after the index type data and the non-index type data are obtained, the two data can be respectively processed in an output structure. Specifically, the index data can be output as multi-category structured index data items of index names, index values, index ranges, index units, interval attributes to which the indexes belong and the like through the specification of a special index knowledge base; the non-index data can be output as standard structured non-index data items with complete data links of 'inspection departments, inspection items, inspection conclusions, inspection suggestions and the like' through the pre-constructed specific disease knowledge graph specification. The health data extraction process will be described in detail later, and will not be described in detail here.

Health data interactive presentation: after two types of structured data items (i.e., multi-category structured index-type data items and standard structured non-index-type data items) are obtained, user interface interaction and presentation processing may be performed based on the two types of data items. For index data (i.e. multi-category structured index data items), indexes of different periods can be arranged according to interval attributes and connected and drawn to form an index trend statistical graph crossing the report by combining different interval attribute labeling values of the same index on reports of different periods or different institutions, and a user can be supported to click a specific point on the graph to carry out single index value jump (namely jump to a physical examination report corresponding to the index value). For non-index data (i.e. standard structured non-index data items), the user can directly jump to the position of the original report and highlight the region by clicking the item physical examination data items by linking the item physical examination data items with the specific position in the report original image uploaded by the user by combining the item physical examination data items with the text position reserved by intelligent recognition. The health data interactive presentation will be described in detail later and will not be described in detail here.

It should be understood that the application scenario shown in fig. 3 is only one kind provided in the embodiment of the present invention, and should not be construed as limiting the embodiment of the present invention.

The following describes the architecture of a specific method on which the embodiments of the present invention are based.

Referring to fig. 4, fig. 4 is a flowchart of a data identification method in an embodiment of the present application, and the data management method in an embodiment of the present application will be described below with reference to fig. 4 and based on the application scenario in fig. 3. The method can be run in a software system architecture of the electronic device 100, and can be divided into two parts, namely terminal interface interaction and cloud background service. The terminal interface can provide the user with physical examination report original data uploading, health data structured presentation and interaction functions; the cloud background service can provide intelligent identification and data processing functions for physical examination reports uploaded by users. The detailed flow is as follows:

step 1: the user can upload the original physical examination report on the terminal application interface through photographing, local album, file reading and other modes.

It should be noted that, the original physical examination report may include multiple physical examination reports, and different physical examination reports may come from different physical examination institutions. In the application, the scanning identification can be performed on the physical examination report in any format.

Step 2: after the original physical examination report uploaded by the user, the server can identify and extract the physical examination report page by page. This process may include: single page data region classification, index type data processing based on content and space position, and non-index type data processing based on specific disease knowledge graph. Wherein,

single page data region classification:

in the cloud background service processing process, a processing process of classifying a single page data area is shown in fig. 5, fig. 5 is a schematic diagram of classifying a single page data area according to an embodiment of the present invention, where single page data area classification processing logic may be divided into four steps: reading images and texts, calculating spatial positions and spacing characteristics of index areas, calculating continuous gray difference variability of non-index areas and classifying content areas. In particular, the method comprises the steps of,

(1) Reading images and text: and reading the user input physical examination report image acquired from the terminal application and the full text and coordinate information recognized by the OCR technology.

(2) Calculating the spatial position and the spacing characteristic of the index region: after the physical examination report image and the text information are determined, the relative position distribution and the distance distribution of the text boxes in the ROI area can be obtained through horizontal and vertical text coordinate distribution and text box distance feature extraction contained in the whole area after the ROI area of the image is expanded, and whether the report content of index types exists in the current area can be judged by combining the two.

(3) Non-index region continuous gray difference variability calculation: after the report image and the text information are received, the gray level continuous difference change coefficient of the text in the region can be obtained through the region continuous difference variability calculation after converting the gray level map to the ROI region, and then whether the report content of non-index type exists in the current ROI region can be judged.

It should be noted that, the spatial position and spacing feature calculation of the index region and the continuous gray difference variability calculation of the non-index region may be performed simultaneously without distinguishing the sequence in the execution process, which is not limited herein.

(4) Content area classification: after the index type data and the non-index type data are determined, the index type data and the non-index type data contained in the current processing page are classified and summarized in the region labels and coordinates where the non-index type data are located.

(II) index class data processing based on content and space positions:

after the index data content of which the single page classification is completed is obtained, a processing procedure of the index data is shown in fig. 6, and fig. 6 is a schematic diagram of index physical examination data processing provided by the embodiment of the invention, where the processing procedure of the index physical examination data can be divided into the following three steps: constructing an index special knowledge base, processing index physical examination data and outputting the index physical examination data in a standardized way. In particular, the method comprises the steps of,

(1) Constructing a special knowledge base of index types: the standard index parameter information obtained by statistics from a large number of real report samples is included, and like a plurality of index names, index ranges and the like where one index may appear, the combination parameter capable of marking the uniqueness of the index can be statistically induced from the large number of samples; and according to the interval distribution of the same index in a massive report, five types of segmented intervals (a lower interval, a lower limit early warning interval, an ideal interval, a higher limit early warning interval and a higher interval) of each index and critical values of the intervals are counted. Furthermore, the knowledge information can be persisted as an index type data special knowledge base stored in the cloud.

(2) Index type physical examination data processing: and carrying out correlation matching and extraction processing on the index data extracted from the original physical examination report by combining a pre-constructed index data special knowledge base which is stored in the cloud in a lasting manner. The matching coefficients of a plurality of candidate values of the same index can be calculated through the index uniqueness combination parameters contained in the index knowledge base so as to judge whether the current index is a pseudo index of the target index. In addition, the method can be combined with five types of segment interval critical values in the index type knowledge base to label the value of each index for interval attribute, and can be used as a data base for drawing a cross-report index trend statistical graph after processing is completed.

(3) Standardized output of index physical examination data: the index class data may be output as standardized structured index class data items of "index standard name, index value, index range, index unit, interval attribute to which the index belongs, and the like".

And (III) non-index data processing based on the specific disease knowledge graph:

after obtaining the non-index data content of the single page classification, the processing procedure of the non-index data is shown in fig. 7, and fig. 7 is a schematic diagram of non-index data processing provided by the embodiment of the invention, where the processing procedure of non-index physical examination data can be divided into the following three steps: and constructing a non-index type physical examination specific disease knowledge graph, processing non-index type physical examination data and outputting the non-index type physical examination data in a standardized way. In particular, the method comprises the steps of,

(1) Constructing a non-index physical examination specific disease knowledge graph: the knowledge framework for the specific disease knowledge graph can be built according to the standard combination of physical sign data elements; the method can be used for combining the medical field with each specific disease definition and standard grading of physical examination and a non-index type physical examination sample library, extracting the specific disease definition, specific disease type, specific disease result classification, specific disease quantitative grading and other knowledge entities in the physical examination specific disease field, and mapping the specific disease knowledge entity, entity attribute and entity relation to the corresponding node positions of the knowledge frame according to the knowledge filling entity attribute and entity relation in the medical field to complete entity embedding and map completion. Furthermore, the constructed physical examination specific disease knowledge graph can be stored to the cloud server in a lasting mode.

(2) Non-index type physical examination data processing: after the extraction result of the non-index physical examination data is obtained, matching and extracting the specific disease keywords contained in the non-index text content through text keyword segmentation, and taking the specific disease keywords as candidate entities for searching the specific disease knowledge graph; secondly, the similarity between different candidate entities and entity units of the same type of map can be obtained by carrying out shallow semantic feature calculation on the output candidate entities so as to remove the candidate entities with interference; aiming at the entity which completes screening, the standard structure data item with the complete data link can be obtained through the pre-constructed physical examination specific disease knowledge graph reasoning.

(3) Standardized output of non-index physical examination data: the non-index data is output as standardized structured non-index data items such as examination departments, examination items, examination conclusions, examination suggestions and the like.

Step 3: after the server processes the physical examination report text information, a multi-category index data result with a standard structure can be output aiming at index type physical examination data, and indexes in different periods can be arranged according to interval attributes and connected and drawn to form an index trend statistical graph crossing the report by combining a special index knowledge base and index interval attribute labeling values; for non-index class physical examination data, an item non-index class data result with a complete data link can be output, and the item non-index class data result can be synchronously linked to the position coordinates of the original report corresponding to the item non-index class data.

Step 4: after receiving the index data result and the index trend graph processed by the server, the terminal application can present relevant information to the user at a terminal interface, and provide any index recording point on the click graph for the index trend graph, so that the terminal application can directly jump to the interactive function of jumping of the current index detail page; and aiming at the non-index data, clicking any item data item can be provided, and the interactive function of directly jumping to the position where the original report is located and highlighting the area where the original report is located can be realized.

In the method, any form of physical examination report can be identified, and index type data areas and non-index type data areas in single page data can be classified based on single page text block interval characteristics and gray level continuous difference variability calculation of the interested areas, so that index type data and non-index type data in each physical examination report can be determined. Further, the index class data can be output as multi-class structured index items with standard structures based on the content of the index class data and an index class knowledge base; the non-index data can be output as standard structure data items with complete data links based on the physical examination specific disease knowledge graph constructed by combining physical examination health data standards.

In summary, the method and the device can identify and extract index type data and non-index type data in a plurality of types of physical examination reports in the form of pictures or electronic files under the condition of not limiting physical examination institutions, report types and specific templates, and can rapidly generate standardized and structured physical examination health data so as to conduct classified standardized management on the health data of users, thereby improving user experience.

Next, an explanation will be given with reference to fig. 8, where fig. 8 is a flowchart of an application for intelligent identification of a physical examination report, and the application mainly includes an end user operation of a physical examination report of a user, a background server process, and an application for interaction with the user. The detailed description is as follows:

1. after the user opens the mobile terminal application, the user can enter an interface with the intelligent identification function of the physical examination report. Further, the physical examination report to be processed can be selected and uploaded by taking report photos through the handheld device, selecting existing photos from a local album, or selecting electronic files of the physical examination report from a local storage.

2. After receiving the physical examination report uploaded by the user, the server can identify two types of health data, namely index type data and non-index type data, page by page. Specific classification and identification processes can be found in the above detailed description of fig. 6 and 7, and the detailed description is not repeated here.

3. After the server side obtains the index type and non-index type data after the identification is completed, the index type data can be summarized and a cross-report index trend statistical chart can be generated, and meanwhile, the non-index type data can be generated to be linked with the position of the original file.

4. After receiving the data processed by the server, the user terminal can present the processing results of the two types of data to the user, and the user can check and manage the interactive operations through the index trend graph and the non-index labeled data.

By applying the single page report classification algorithm and the special index extraction algorithm and the non-index specific disease knowledge graph which are included in the intelligent physical examination report identification method, the identification of the physical examination report is separated from the template limitation related to the organization and the layout type, and the physical examination report can be adapted to any form. Meanwhile, index data and non-index data in the physical examination report can be extracted and processed into structured output. Whereas prior art analysis is only directed to reporting conforming to a particular template framework or a particular institution, identification and data structured extraction capabilities are not provided for physical examination reports that are not within this defined range. In addition, for the supported report types, the existing scheme only extracts and processes the index type data contained in the report types, and the non-index type data cannot be extracted and processed in a structured mode, so that a user cannot perceive complete physical examination data management experience from the existing terminal application.

In summary, the end-to-end improvements of the present application ameliorate the above-described disadvantages of the prior art. For the physical examination report selected by the user, the structural identification and extraction of the physical examination report in any form are supported by applying a single page report classification algorithm and a special index extraction algorithm and a non-index specific disease knowledge graph which are included in the physical examination report intelligent identification method related to the application, and the identification of the physical examination report is separated from the template limitation related to the organization and the layout type. In addition, in the method, the index type and non-index type data in the physical examination report can be identified and extracted in a structured mode, so that the functional experience of the physical examination report is more complete, and the user experience is more comprehensive.

Next, a scheme of identifying the data management application and interaction of the health data of the index class after the completion of the extraction will be described in detail.

For the health data of the index class, the index value can be subjected to section interval classification by combining with a special knowledge base of the index class, and interval labeling can be performed on the index value, so that the numerical difference among the indexes of the same kind of report can be compatible, and the reports of the same index of the same individual in different periods of different institutions can be subjected to trend statistics and comparison analysis. As shown in fig. 9, fig. 9 is a schematic flow chart of multi-region physical examination index trend statistics provided in the embodiment of the present invention, in which, for index type data, a server end groups attribute values marked for each index segmented interval in combination with a dedicated index knowledge base in an intelligent recognition scheme among multiple physical examination reports of the same user, the same index set in multiple reports of the same user can be divided into five types according to marked interval attributes, which are respectively an abnormal low index set, a low-limit early-warning index set, an ideal index set, a high-limit early-warning index set and an abnormal high-index set. Further, the index change trend of the user can be calculated according to the set of indexes in different periods. After receiving the related information, the terminal application can present a trend statistical graph of multiple indexes in the five-class segmented intervals to the user and support the user to click a certain point on the graph to jump to a single index detail page.

The flow of marking the index value segmented interval by the server side may be shown in fig. 10, fig. 10 is a schematic diagram of the flow of marking the index value segmented interval by the server side, where the flow of marking the segmented interval by the server side on different index data according to the dedicated index knowledge base may include the following three steps: acquiring index data, pulling an index partition critical value and judging the attribution of an index interval. Wherein,

(1) Acquiring index data: the server side obtains an index type data result from the structured data extracted from the physical examination report intelligent identification as input.

(2) Pulling an index partition critical value: the server side pulls the different partitions unique to each index and the upper and lower critical values of the respective partitions from the dedicated index knowledge base.

(3) Judging the attribution of an index interval: the interval to which the current index belongs can be judged according to the index value to be marked currently and different interval critical values of the current index, and the interval attribute is marked as the attribute value of the current index and is used as the index trend judgment basis of cross-report comparison.

After obtaining the interval attribute of each index in different period reports, the server side can generate a multi-interval physical examination index trend statistical chart of five partitions. As shown in fig. 11, fig. 11 is a schematic diagram of generating a multi-interval index trend statistical chart according to an embodiment of the present invention, where the generating step of the multi-interval index trend statistical chart may include the following three steps: acquiring index interval attributes, sequencing indexes according to physical examination report time, and drawing an index trend statistical graph of five partitions.

For example, as shown in fig. 12, fig. 12 is a schematic diagram of a multi-region physical examination index trend statistical chart provided by an embodiment of the present invention, in the chart, a single multi-region physical examination index trend statistical chart uses a single index as a statistical object, and each point in a broken line represents a region attribute to which a current index belongs in a report of each period; the trend of the line graph represents the change trend of the current index relative to the historical index; the five background areas where the broken lines are located represent interval attributes (three types of interval attributes include a lower-limit early-warning interval, an ideal interval, a higher-limit early-warning interval and a higher-limit interval) of the current index; the overall multi-region physical examination index trend statistical chart can not display specific index values, a user can click any point on the chart and jump to a detail page of a single index for browsing, as shown in fig. 13, fig. 13 is a schematic diagram of jump-to-transfer of index type data provided by the embodiment of the invention, in the figure, when the user clicks any point on the index trend statistical chart, the user can jump to the detail page of the single index for browsing, for example, the user clicks hemoglobin data corresponding to 9 months in the index trend statistical chart, and further, the user can jump directly to an original physical examination report of 9 months hemoglobin detection to display detailed hemoglobin data.

In the method, each index is classified in a segmented interval by combining with an index-type special knowledge base, and index values are labeled in intervals, so that the method can be compatible with the numerical difference among the indexes of the same kind of reports, and the reports of the same index of the same individual in different periods of different institutions are subjected to trend statistics and comparison analysis. Further, through the multi-regional physical examination index trend statistical graph generated by the server according to the index interval attribute labeling value, a unified management analysis viewing interface of the same index on different reports of different periods can be presented to a user, and cross-report index trend management capability compatible with numerical differences among the same type of indexes of different reports is provided. Meanwhile, through the one-key jump interactive capability between a plurality of index change trends of the multi-region physical examination index trend statistical chart and single index data details, the user can transversely manage index change and specific details by taking the single index as a dimension, and better user experience and convenience of data management are provided. In the prior art, the same index of the same user in reports of different institutions and different periods cannot be horizontally and uniformly managed, and the user interaction mode is single.

In summary, the embodiment of the invention can realize unified management of the same index of different reports of a user in different institutions or different periods, solve the problem that the same index cannot be uniformly managed due to different institutions or reports, and greatly improve convenience and user experience of checking multi-period index information through the unified management of the interaction mode of one-key jump between the multi-regional physical examination index trend statistical chart and the single index detail.

Next, a scheme of recognizing the data management application and interaction of the non-index class health data after the completion of extraction will be described in detail.

For non-index data, non-index data items with standard structures, which are output by a physical examination report intelligent recognition scheme, are obtained, the item data are arranged and presented for a user at a terminal application interface, and one-key jump interactive capability between different item data and the corresponding position of the original report content of the user can be provided. As shown in fig. 14, fig. 14 is a schematic flow chart of non-index type data tagging management according to an embodiment of the present invention, where the non-index type data tagging management may include the following three steps: acquiring a non-index class data set, outputting a standardized data structure and presenting terminal application labeling data. In particular, the method comprises the steps of,

(1) Acquiring a non-index class data set: the server side completes batch acquisition of the non-index type data items of the physical examination report, and associates each non-index type extraction result with the corresponding original report position coordinates.

(2) Outputting a standardized data structure: the server side outputs the item non-index data and the corresponding original report position to the mobile application side in batches according to the standard output structure of inspection departments, inspection items, inspection conclusions and inspection suggestions.

(3) Terminal application tagged data presentation: after receiving the output data from the server, the terminal application can present tagged non-index data items to the user on the application interface, and provide clicking corresponding data items to the user to jump to the original report position corresponding to the data item by one key, and precisely highlight the report page number position of the content.

For example, as shown in fig. 15, fig. 15 is a schematic diagram showing interaction between a presentation of labeled non-index data in a terminal application and a user, and as shown in the left diagram of fig. 15, any form of non-index data in a physical examination report may be output uniformly as item data with a specific structure, and presented to the user in a labeled manner in a terminal application interface. Further, the user may click on any of the labels in the left diagram in fig. 15, and one-click jumps to the exact location of the clicked label data in the original report as shown in the right diagram in fig. 15. By the method, the user can manage the non-index data in unified standard and structure, and can check the original report content associated with the data at any time, so that the integrity of physical examination data of the user and convenience in jumping and management among different data are greatly improved.

In the method, the non-index data in any form in the physical examination report can be uniformly output as the item data with a specific structure, and the item data is presented to the user in a terminal application interface in a labeling mode, so that more complete physical examination data management capability and experience of the user are provided. Meanwhile, the method also supports that the user can click any label to jump to the accurate position of the corresponding label content in the original report by one key, and provides more convenient user experience. In the prior art, standard structured management cannot be performed on any form of non-index data in a user physical examination report, a user interaction mode is single, if a user needs to check a certain content in an original report, the user needs to search page by page and row by row manually, and the efficiency is very low.

In summary, by the embodiment of the invention, the structured extraction and management of the non-index report content of any form of the user can be realized, the labeled data content is presented on the application interface of the user terminal, and the interactive design of one-key jump of the label data and the original report is creatively applied, so that the convenience and the user experience of the user for managing and checking the non-index information are greatly improved.

Referring to fig. 16, fig. 16 is a flowchart of a data management method according to an embodiment of the present invention. The data management method includes, but is not limited to, steps S201 to S203.

Step S201: index class data and non-index class data of each of the N physical examination reports are identified.

Specifically, the index class data includes at least one index item, the non-index class data includes at least one non-index item, and N is an integer greater than 0. The index item can be understood as a blood pressure index, a blood sugar index, a blood fat index and the like, and the index data can be understood as a measured value corresponding to the index item in the user physical examination report; the non-index item can be understood as heart color ultrasound, ultrasonic examination and the like, and the non-index data can be understood as a detection result corresponding to the non-index item in the user physical examination report.

It should be noted that, how to identify and extract the index type data and the non-index type data can be referred to the above description of fig. 5, and the detailed description is not repeated here.

Step S202: and generating index type structured data corresponding to the N physical examination reports based on the first database and the index type data in each physical examination report.

Specifically, the index type structured data includes structured data of a plurality of index items, the structured data of each index item includes one or more of an index standard name, an index abbreviation, an index range, an index unit and an index segmentation section, and the first database includes index type sample data. The first database may be understood as the above-mentioned pre-constructed index knowledge base, i.e. the index knowledge base generated based on the index class sample data.

It should be noted that, how to construct the first database (i.e., the index knowledge base) can be referred to the above description of fig. 6, and the detailed description is not repeated here.

Step S203: and generating non-index type structured data corresponding to the N parts of physical examination reports based on a second database and the non-index type data in each part of physical examination reports.

Specifically, the non-index structured data includes a plurality of structured data of non-index items, each of the structured data of non-index items includes one or more of an inspection department, an inspection item, an inspection result, and an inspection suggestion, and the second database includes non-index sample data. The second database may be understood as the non-index physical examination knowledge graph mentioned above.

It should be noted that, how to construct the second database (i.e. the non-index physical examination knowledge graph) can be referred to the above description of fig. 7, and the detailed description is not repeated here.

In the prior art, physical examination report identification and health data management cannot be adapted to any form of physical examination report, index type data in the physical examination report can be managed, and structural management cannot be achieved for non-index type data in an indefinite form. In the application, the report type and the data type are not limited, and the identification and extraction of the physical examination report in any form can be realized by applying a single page report classification algorithm and a special index extraction algorithm and a non-index specific disease knowledge graph which are included in the physical examination report intelligent identification scheme provided by the application, so that the identification of the physical examination report is separated from the template limitation related to the layout type and related to the organization. Meanwhile, the index type and non-index type data in the physical examination report can be identified and extracted in a structured mode, so that the functional experience of the physical examination report is more complete, and the user experience is more comprehensive.

Specifically, the physical examination reports with different formats can be identified based on the physical examination report intelligent identification algorithm so as to obtain text information, image information and position information corresponding to the text information in each physical examination report, so that index type data and non-index type data in each physical examination report can be determined, and the physical examination data of a user can be classified and managed later.

Specifically, because the index data formats, index names, index values and the like of the same index in different physical examination reports may not be uniform, the correlation matching and extraction processing can be performed on the index data extracted from the original physical examination report by combining with a pre-built special knowledge base (i.e. the first database mentioned above), and then the output of a specific structure can be performed on the index data extracted from different reports, namely, the structured index data item which can be standardized "index standard name, index value, index range, index unit, and interval attribute to which the index belongs" is output, thereby realizing standardized management on the index data. Meanwhile, the index data with the same index name can be arranged, so that data management of cross reports is realized.

It should be noted that, for a detailed description of the structuring process of the index class data, reference may be made to the description of fig. 6, and a detailed description is not repeated here.

Specifically, when the structured data corresponding to each index item is determined, the segmented interval attribute marking can be performed based on the index value corresponding to each index item, namely, the index segmented interval corresponding to each index item can be determined from a plurality of preset segmented intervals, so that analysis on the physical examination result of the user index item is realized, and user experience is improved.

It should be noted that, how to determine the index segment interval corresponding to each index item may refer to the description of fig. 10, and the detailed description is not repeated here.

Specifically, since the non-index data in each physical examination report has no output in a fixed format, the non-index data extracted from the original report can be identified by keywords and can be matched with a pre-constructed non-index physical examination specific disease knowledge graph (namely, the second database mentioned above) so as to output non-index data extracted from different reports in a specific structure, namely, output a structured non-index data item which can be standardized 'inspection department, inspection detail item, inspection conclusion and inspection suggestion', thereby realizing standardized management of the non-index data.

It should be noted that, for a detailed description of the structuring process of the non-index data, reference may be made to the description of fig. 7, and a detailed description is not repeated here.

Specifically, for index data, the transformation trend of the index can be shown through the interval index trend statistical graph, and one-key jump to index detail data pages of the same index in different institutions and different reports can be realized, so that unified trend management and data viewing can be facilitated.

It should be noted that, how the terminal device displays the processed index class data may refer to the description of fig. 11, and the description is not repeated here.

In the prior art, in the application of physical examination index trend statistics, the same index item of a user in a fixed mechanism or a report of the same type can be managed and counted, the same index of the same user in reports of different mechanisms and different periods can not be horizontally and uniformly managed, and the user interaction mode is single. In the application, based on the inter-report index trend management of the special knowledge base and index interval attribute labeling, the user can uniformly manage the same index of different institutions or different reports in different periods by carrying out the subsection interval labeling on the index type data in the user report and generating the inter-report index trend statistical chart according to the subsection interval labeling, so that the problem that the same index cannot be uniformly managed due to the fact that institutions or reports are different is solved. Meanwhile, the convenience and the user experience of checking the multi-period index information through user management are greatly improved through the one-key jump interaction mode between the multi-period index trend statistical chart and the single index details which are managed in a unified mode.

Specifically, for non-index data, the method can support one-key jump between the extracted structured data and the original data by a user, and can accurately highlight related contents in the original data, so that the steps that the user needs to frequently switch between different reports and reserve paper original reports are avoided, and the interaction convenience and experience intuitiveness of report management and data association are improved.

It should be noted that, how the terminal device displays the processed non-index data may refer to the description of fig. 14, and the description is not repeated here.

In the prior art, physical examination report data management and interaction modes only provide basic functions such as extracted index data and content browsing, and the like, and have lower supportability and convenience in use experience for user jump among multiple data (such as extracted data and original report content) and different data dimension association (such as single index data and all index data in a period). In the application, the user interaction mode of one-key skip of different data is supported, and for non-index data, the interaction mode of one-key skip of the extracted structured data and the original data by a user can be supported, and related content can be accurately highlighted in the original data, so that the user is prevented from frequently switching and reserving paper original reports among different reports, and the interaction convenience and experience intuitiveness of report management and data association are greatly improved; for index data, the multi-region index trend statistical graph special for the invention can be supported, and one key is used for jumping to index detail data pages of the same index in different institutions and different reports, so that the index data on different reports of different institutions are compatible, and unified trend management and data viewing are convenient.

In the embodiment of the invention, any form of physical examination report can be identified, and index type data areas and non-index type data areas in single page data can be classified based on single page text block interval characteristics and gray level continuous difference variability calculation of the interested areas, so that index type data and non-index type data in each physical examination report can be determined. Further, the index class data can be output as multi-class structured index items with standard structures based on the content of the index class data and an index class knowledge base; the non-index data can be output as standard structure data items with complete data links based on the physical examination specific disease knowledge graph constructed by combining physical examination health data standards.

The foregoing details the method according to the embodiments of the present invention, and the following provides relevant apparatuses according to the embodiments of the present invention.

Referring to fig. 17, fig. 17 is a schematic diagram of a data management device according to an embodiment of the present application, where the data management device 30 may include a first identification unit 301, a first processing unit 302, a second processing unit 303, a third processing unit 304, a fourth processing unit 305, and a fifth processing unit 306.

Wherein, the detailed description of each module is as follows:

a first identifying unit 301, configured to identify index class data and non-index class data of each of N physical examination reports, where the index class data includes at least one index item, and the non-index class data includes at least one non-index item, and N is an integer greater than 0;

a first processing unit 302, configured to generate index class structured data corresponding to the N pieces of physical examination reports based on a first database and the index class data in each piece of physical examination report, where the index class structured data includes structured data of a plurality of index items, and each of the structured data of the index items includes one or more of an index standard name, an index abbreviation, an index range, an index unit, and an index segmentation section, and the first database includes index class sample data;

The second processing unit 303 is configured to generate non-index type structured data corresponding to the N physical examination reports based on a second database and the non-index type data in each physical examination report, where the non-index type structured data includes a plurality of structured data of the non-index items, and each structured data of the non-index items includes one or more of an inspection department, an inspection item, an inspection result, and an inspection suggestion, and the second database includes non-index type sample data.

In one possible implementation manner, the first processing unit 302 is specifically configured to: identifying text information and image information in each physical examination report and position information corresponding to the text information; and determining the index type data and the non-index type data in each physical examination report based on the text information, the image information and the position information.

In one possible implementation manner, the first processing unit 302 is specifically configured to: performing correlation matching on the one or more index items in each physical examination report and the first database respectively to obtain structured data of a plurality of index items; the method further comprises the steps of: and summarizing the structured data corresponding to the same index item in the structured data of the index items to obtain summarized index type structured data.

In one possible implementation, the structured data of each of the index items includes an index segmentation section, and the apparatus further includes: the third processing unit 304 is configured to determine the index segment interval corresponding to each index item from a plurality of preset segment intervals, where the plurality of preset segment intervals include a plurality of low-limit pre-warning intervals, ideal intervals, high-limit pre-warning intervals, and high-limit pre-warning intervals.

In a possible implementation manner, the second processing unit 303 is specifically configured to: extracting target keywords of each non-index item of each physical examination report; and matching the target keywords respectively corresponding to the non-index items with the non-index sample data in the second database to obtain structured data of the non-index items.

In one possible implementation, the apparatus includes a display screen, and the apparatus further includes: a fourth processing unit 305, configured to generate an index trend graph for a target index item in the summarized index-class structured data, where the target index item is any one of a plurality of index items in the summarized index-class structured data; displaying the index trend graph corresponding to the target index item through the display screen; and receiving a first operation, and responding to the first operation, and displaying a physical examination report corresponding to the target index item through the display screen.

In one possible implementation, the apparatus further includes: a fifth processing unit 306, configured to display, through the display screen, structured data of a plurality of non-index items; and receiving a second operation, and responding to the second operation, and displaying a physical examination report corresponding to a target non-index item through the display screen, wherein the target non-index item is one of the non-index items.

It should be noted that, the functions of the functional units in the data management device 30 described in the embodiment of the present invention may be referred to the related descriptions of step S201 to step S203 in the method embodiment described in fig. 16, and are not repeated here.

The present application provides a computer storage medium storing a computer program which when executed by a processor implements any one of the above-mentioned data management methods.

The embodiment of the application provides electronic equipment, which comprises a processor, wherein the processor is configured to support the electronic equipment to realize the corresponding functions in any one of the data management methods. The electronic device may also include a memory for coupling with the processor that holds the program instructions and data necessary for the electronic device. The electronic device may also include a communication interface for the electronic device to communicate with other devices or communication networks.

The present application provides a chip system comprising a processor for supporting an electronic device for performing the functions referred to above, e.g. generating or processing information referred to in a data management method as described above. In one possible design, the chip system further includes a memory to hold the necessary program instructions and data for the electronic device. The chip system can be composed of chips, and can also comprise chips and other discrete devices.

The present application provides a computer program characterized in that the computer program comprises instructions which, when executed by a computer, cause the computer to perform a data management method as described above.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, such as the above-described division of units, merely a division of logic functions, and there may be additional manners of dividing in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be essentially or a part contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc., in particular may be a processor in the computer device) to perform all or part of the steps of the above-described method of the various embodiments of the present application. Wherein the aforementioned storage medium may comprise: various media capable of storing program codes, such as a U disk, a removable hard disk, a magnetic disk, a compact disk, a Read-Only Memory (abbreviated as ROM), or a random access Memory (Random Access Memory, abbreviated as RAM), are provided.

The above embodiments are merely for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. A method of data management, the method comprising:

identifying index type data and non-index type data of each physical examination report in N physical examination reports, wherein the index type data comprises at least one index item, the non-index type data comprises at least one non-index item, and N is an integer greater than 0;

generating index type structured data corresponding to the N parts of physical examination reports based on a first database and the index type data in each part of physical examination reports, wherein the index type structured data comprises structured data of a plurality of index items, the structured data of each index item comprises one or more of index standard names, index abbreviations, index ranges, index units and index segmentation intervals, and the first database comprises index type sample data;

generating non-index type structured data corresponding to the N physical examination reports based on a second database and the non-index type data in each physical examination report, wherein the non-index type structured data comprises a plurality of structured data of non-index items, the structured data of each non-index item comprises one or more of an examination department, an examination item, an examination result and an examination suggestion, and the second database comprises non-index type sample data.

2. The method of claim 1, wherein identifying the index-like data and the non-index-like data for each of the N physical examination reports comprises:

identifying text information and image information in each physical examination report and position information corresponding to the text information;

and determining the index type data and the non-index type data in each physical examination report based on the text information, the image information and the position information.

3. The method of claim 2, wherein generating the index class structured data corresponding to the N physical examination reports based on the first database and the index class data in each of the physical examination reports comprises:

performing correlation matching on the one or more index items in each physical examination report and the first database respectively to obtain structured data of a plurality of index items; the method further comprises the steps of:

and summarizing the structured data corresponding to the same index item in the structured data of the index items to obtain summarized index type structured data.

4. A method according to claim 3, wherein the structured data for each of the index items comprises an index segmentation interval, the method further comprising:

Determining the index segmentation section corresponding to each index item from a plurality of preset segmentation sections, wherein the plurality of preset segmentation sections comprise a plurality of low-limit sections, low-limit early-warning sections, ideal sections, high-limit early-warning sections and high-limit sections.

5. The method of claim 3 or 4, wherein generating non-index class structured data corresponding to the N individual examination reports based on the second database and the non-index class data in each of the examination reports, comprises:

extracting target keywords of each non-index item of each physical examination report;

and matching the target keywords respectively corresponding to the non-index items with the non-index sample data in the second database to obtain structured data of the non-index items.

6. The method according to claims 3-5, applied to a terminal device, the terminal device comprising a display screen, the method further comprising:

generating an index trend graph aiming at target index items in the summarized index-type structured data, wherein the target index items are any one of a plurality of index items in the summarized index-type structured data;

Displaying the index trend graph corresponding to the target index item through the display screen;

and receiving a first operation, and responding to the first operation, and displaying a physical examination report corresponding to the target index item through the display screen.

7. The method of claim 6, wherein the method further comprises:

displaying the structured data of a plurality of non-index items through the display screen;

and receiving a second operation, and responding to the second operation, and displaying a physical examination report corresponding to a target non-index item through the display screen, wherein the target non-index item is one of the non-index items.

8. A data management apparatus, the apparatus comprising:

the first identification unit is used for identifying index type data and non-index type data of each of N physical examination reports, wherein the index type data comprises at least one index item, the non-index type data comprises at least one non-index item, and N is an integer greater than 0;

the first processing unit is used for generating index type structured data corresponding to the N parts of physical examination reports based on a first database and the index type data in each part of physical examination reports, wherein the index type structured data comprises structured data of a plurality of index items, the structured data of each index item comprises one or more of index standard names, index abbreviations, index ranges, index units and index segmentation intervals, and the first database comprises index type sample data;

The second processing unit is configured to generate non-index type structured data corresponding to the N physical examination reports based on a second database and the non-index type data in each physical examination report, where the non-index type structured data includes a plurality of structured data of non-index items, each structured data of non-index items includes one or more of an inspection department, an inspection item, an inspection result, and an inspection suggestion, and the second database includes non-index type sample data.

9. The apparatus of claim 8, wherein the first processing unit is configured to:

10. The apparatus according to claim 9, wherein the first processing unit is specifically configured to:

11. The apparatus of claim 10, wherein the structured data for each of the index items comprises an index segmentation interval, the apparatus further comprising:

the third processing unit is used for determining the index segmentation section corresponding to each index item from a plurality of preset segmentation sections, wherein the preset segmentation sections comprise a plurality of low-limit early warning sections, ideal sections, high-limit early warning sections and high-limit sections.

12. The apparatus according to claim 10 or 11, wherein the second processing unit is specifically configured to:

13. The apparatus of claims 10-12, wherein the apparatus comprises a display screen, the apparatus further comprising:

A fourth processing unit, configured to generate an index trend graph for a target index item in the summarized index-class structured data, where the target index item is any one of a plurality of index items in the summarized index-class structured data;

14. The apparatus of claim 13, wherein the apparatus further comprises:

a fifth processing unit, configured to display, through the display screen, structured data of a plurality of non-index items;

15. A computer storage medium, characterized in that the computer storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-7.

16. A computer program comprising instructions which, when executed by a computer, cause the computer to perform the method of any of claims 1-7.