CN111401347B

CN111401347B - Information positioning method and device based on picture

Info

Publication number: CN111401347B
Application number: CN202010503039.0A
Authority: CN
Inventors: 吴参森
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Ant Shengxin (Shanghai) Information Technology Co.,Ltd.
Priority date: 2020-06-05
Filing date: 2020-06-05
Publication date: 2020-11-10
Anticipated expiration: 2040-06-05
Also published as: CN111401347A

Abstract

The embodiment of the specification provides an information positioning method and device based on pictures, wherein the information positioning method based on pictures comprises the following steps: acquiring a service picture of a target service; detecting the service picture to obtain service information contained in the service picture and first position information of characters in the service information in the service picture; identifying an entity in the service information based on the service knowledge graph of the target service, and acquiring target service information corresponding to the target entity in the service knowledge graph and second position information of the target service information in the service information; and determining the target position information of the target service information in the service picture according to the first position information and the second position information.

Description

Information positioning method and device based on picture

Technical Field

The embodiment of the specification relates to the technical field of data processing, in particular to an information positioning method and device based on pictures.

Background

With the development of the internet, more and more services are processed on line, and in the service processing process, service auditing is often performed on uploaded service pictures, however, due to the diversity and complexity of the service pictures, the efficiency of locating key information in the service pictures is low and errors are prone to occur, so a more reliable scheme needs to be provided.

Disclosure of Invention

In view of this, embodiments of the present specification provide a method for positioning information based on pictures. One or more embodiments of the present disclosure also relate to a picture-based information positioning apparatus, a computing device, and a computer-readable storage medium, which are used to solve the technical problems of the prior art.

In a first aspect of the embodiments of the present specification, there is provided a method for positioning information based on a picture, including:

acquiring a service picture of a target service;

detecting the service picture to obtain service information contained in the service picture and first position information of characters in the service information in the service picture;

identifying an entity in the service information based on the service knowledge graph of the target service, and acquiring target service information corresponding to the target entity in the service knowledge graph and second position information of the target service information in the service information;

and determining the target position information of the target service information in the service picture according to the first position information and the second position information.

Optionally, the identifying, by the service knowledge graph based on the target service, an entity in the service information to obtain target service information corresponding to the target entity in the service knowledge graph includes:

extracting a first object in the service information according to a preset entity type;

screening a target entity from first entities corresponding to the first object based on the service knowledge graph;

and taking the target object corresponding to the target entity as the target service information.

Optionally, the screening, based on the service knowledge graph, a target entity from the first entities corresponding to the first object includes:

comparing the similarity of the first object with an entity in the service knowledge graph to determine the first entity;

and searching in the service knowledge graph according to the first entity, and determining a target entity reaching a conclusion entity.

Optionally, the extracting the first object in the service information according to the preset entity type includes:

performing sentence division processing on the service information;

performing word segmentation on the sentence segmentation processing result to obtain a word unit set consisting of word units;

calculating the matching degree of each word unit in the word unit set and the entity type;

and selecting word units meeting a matching degree threshold value as the first object according to the calculation result.

Optionally, the detecting the service picture to obtain service information included in the service picture and first position information of characters in the service information in the service picture includes:

detecting the service picture to obtain service information contained in the service picture and corresponding line position information of the line service information in the service picture;

and performing information splicing on the business information to obtain the business information, and performing region segmentation on a picture region corresponding to the line position information to obtain the first position information.

Optionally, the determining, according to the first location information and the second location information, the target location information of the target service information in the service picture includes:

according to the second position information and the business information, calculating a line code corresponding to the target business information in the business picture and a start-stop code corresponding to the line code in the target line information;

and determining the target position information according to the line code, the start-stop code and the first position information.

Optionally, after the step of determining the target location information of the target service information in the service picture according to the first location information and the second location information is executed, the method further includes:

according to the target position information, highlighting the target area of the business picture;

and storing the service picture after the highlighting processing in a picture library corresponding to the target service.

Optionally, when there are a plurality of pieces of target service information, there are a plurality of pieces of target location information;

correspondingly, after the step of determining the target location information of the target service information in the service picture according to the first location information and the second location information is executed, and before the step of performing highlighting processing on the target area of the service picture according to the target location information is executed, the method further includes:

judging whether the target areas corresponding to the target position information in the service picture are overlapped or not;

and if so, performing region fusion on the overlapped target regions to obtain fusion position information after the region fusion, and updating the target position information according to the fusion position information.

receiving a viewing instruction aiming at the business picture;

acquiring the service picture and the target position information based on the picture identification carried in the viewing instruction;

and according to the target position information, highlighting and displaying the target area of the service picture.

Optionally, before the step of obtaining the service picture of the target service is executed, the method further includes:

receiving the service picture uploaded by a user;

and storing the service picture in a picture library corresponding to the target service.

Optionally, the target service includes a mutual aid service; correspondingly, the service pictures comprise mutual service pictures.

In a second aspect of the embodiments of the present specification, there is provided a picture-based information positioning apparatus, including:

the acquisition module is configured to acquire a service picture of a target service;

the detection module is configured to detect the service picture to obtain service information contained in the service picture and first position information of characters in the service information in the service picture;

an entity identification module configured to identify an entity in the service information based on a service knowledge graph of the target service, and obtain target service information corresponding to the target entity in the service knowledge graph and second position information of the target service information in the service information;

and the position determining module is configured to determine target position information of the target service information in the service picture according to the first position information and the second position information.

In a third aspect of embodiments of the present specification, there is provided a computing device comprising:

a memory and a processor;

the memory is to store computer-executable instructions, and the processor is to execute the computer-executable instructions to:

acquiring a service picture of a target service;

In a fourth aspect of the embodiments of the present specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the picture-based information positioning method are implemented.

The present specification provides a method for positioning information based on pictures, which, on the basis of obtaining a service picture of a target service, detecting the service picture to obtain service information contained in the service picture and first position information of characters in the service information in the service picture, and identifies the entity in the service information based on the service knowledge graph of the target service, obtains target service information corresponding to the target entity in the service knowledge graph and second position information of the target service information in the service information, and further, and determining the target position information of the target service information in the service picture according to the first position information and the second position information, thereby realizing the positioning of the target service information in the service picture and further increasing the auditing efficiency and the auditing accuracy of the service picture.

Drawings

FIG. 1 is a flowchart illustrating a method for locating information based on pictures according to an embodiment of the present disclosure;

FIG. 2 is a business knowledge graph of a picture-based information positioning method according to an embodiment of the present disclosure;

FIG. 3 is a flowchart illustrating a method for positioning picture-based information for mutual aid service according to an embodiment of the present disclosure;

FIG. 4 is a diagram illustrating an apparatus for locating information based on pictures according to an embodiment of the present disclosure;

fig. 5 is a block diagram of a computing device according to an embodiment of the present disclosure.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, as those skilled in the art will be able to make and use the present disclosure without departing from the spirit and scope of the present disclosure.

The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

In this specification, a picture-based information positioning method is provided, and one or more embodiments of the specification relate to a picture-based information positioning apparatus, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.

An embodiment of an information positioning method based on pictures provided in this specification is as follows:

fig. 1 shows a processing flow chart of a picture-based information positioning method according to an embodiment of the present specification, which specifically includes the following steps:

step S102, obtaining a service picture of the target service.

In practical application, due to the diversity and complexity of the service pictures processed in the service, the time for locating the key information in the service pictures is long, and errors are easy to occur.

Specifically, the target service refers to a service that needs to check or verify a service picture in a service processing process, such as a health care service, a mutual aid service, a loan service, a resource application service, or a qualification service, and is not limited herein. Correspondingly, the service picture refers to a picture that needs to be checked or audited in the process of service processing, such as a certificate picture, a doctor-seeing picture, a certification material, a report material, a certificate picture, and the like, and is not limited herein.

In specific implementation, before obtaining a service picture of a target service, a service picture uploaded by a user needs to be received, and the steps of uploading the service picture and obtaining the service picture by the user may be sequentially executed in time, or may be asynchronously executed at different time intervals, in order to ensure the integrity and the security of the service picture before being processed, before obtaining the service picture and processing the service picture, the service picture is stored first, in an optional implementation manner provided in the embodiment of the present specification, before obtaining the service picture of the target service, the method further includes:

receiving the service picture uploaded by a user;

Specifically, the picture library may be a database, a folder, a disk, and the like, which is not limited herein.

Taking a medical security service in the health care service as an example, the user U is taken as a secured party of the medical security service, and the medical security service is applied, and then the user U suffers from the disease a, so that a medical security fund for the disease a is applied to the secured party of the medical security service, in the process of applying the medical security fund for the disease a, a discharge summary picture of the user U for the disease a is uploaded, and after the discharge summary picture uploaded by the user U is received, the discharge summary picture is stored in a picture library of the medical security service, and after the discharge summary picture is stored, the discharge summary picture is obtained.

Step S104, detecting the service picture, and obtaining service information contained in the service picture and first position information of characters in the service information in the service picture.

On the basis of obtaining the service picture of the target service, the service picture is detected, the service information of the service picture is identified, and first position information of each character in the service information in the service picture is detected.

Specifically, the detecting the service picture refers to identifying the text content in the service picture and detecting first position information of each text in the service picture; correspondingly, the first position information may be coordinate information of a positioning frame where the text is located in the service picture, for example, a coordinate system is established with a vertex of an upper left corner of the service picture as a coordinate origin (or other vertices of the service picture as coordinate origins), a wide side of the service picture as an X axis, and a long side as a Y axis (or a coordinate system is established with a long side of the service picture as an X axis and a wide side as a Y axis), and a two-dimensional coordinate representation of a rectangular positioning frame where each text is located in the foregoing coordinate system is detected.

In practical application, the detection of the service picture may be performed by performing Character Recognition on the service picture through Optical Character Recognition (OCR), detecting a coordinate representation of a location frame where characters in the service picture are located through an object detection algorithm, and detecting the service picture through other algorithms or models, which is not limited herein.

In order to more accurately determine first position information corresponding to each character included in service information in a service picture, in an optional implementation manner provided in an embodiment of this specification, the service picture is detected, which is specifically implemented by the following method:

In practical application, if a service picture may include multiple lines of service information, in the process of detecting the service picture, firstly detecting the service information of each line in the service picture and the line position information corresponding to each line of service information (for example, the coordinate representation of a rectangular positioning frame corresponding to each line of service information in the service picture), then performing information splicing on the service information of each line, and splicing to form service information formed by all characters included in the service picture; and carrying out region segmentation on the picture region corresponding to the coordinate representation of the rectangular positioning frame of each business information to obtain the position information of each character in each line.

In specific implementation, since the sizes of each line of characters are generally the same or similar, the image region corresponding to each business information is subjected to region segmentation, and equidistant segmentation can be adopted.

Along the above example, on the basis of obtaining the discharge summary picture uploaded by the user U, the discharge summary picture is detected, and three lines of characters contained in the discharge summary picture, that is, three lines of service information are obtained, the service information in the first line is "name U", the service information in the second line is "radiotherapy for the disease a", the service information in the third line is "take a rest to pay attention", and the coordinates of the rectangular positioning boxes corresponding to the three lines of service information in the discharge summary picture are respectively: [

，

，

，

]，[

，

，

，

]，[

，

，

，

](the coordinate system of the coordinate takes the vertex at the upper left corner of the discharge summary picture as the origin of coordinates, the broadside of the discharge summary picture as the X axis, and the long side as the Y axis), and the three lines of service information are spliced to obtain the service information contained in the discharge summary picture: the name U carries out radiotherapy attention rest aiming at the disease A, and area division is carried out on picture areas corresponding to coordinate representations of rectangular positioning frames of three lines of business information respectively, so that first position information corresponding to each character in the business information 'the name U carries out radiotherapy attention rest aiming at the disease A' is obtained.

Step S106, identifying the entity in the service information based on the service knowledge graph of the target service, and obtaining target service information corresponding to the target entity in the service knowledge graph and second position information of the target service information in the service information.

On the basis of detecting a service picture and obtaining service information contained in the service picture, entity identification is performed on the detected service information based on a service knowledge graph, and key information, namely target service information, in the service picture and second position information of the target service information in the service information are identified, wherein the second position information refers to initial character coding of the target service information in the service information, or includes both initial character coding and termination character coding, for example, the target service information is located in 6 th to 8 th characters in the service information.

It should be noted that, due to the diversity of the target services and the diversity of the service pictures, in order to identify the key information in the service pictures, the service knowledge maps constructed in advance are also diverse, taking the health care services as an example, the health care services also include medical care services, mutual support services, serious disease services, and other support services, and since the service processing logic of each type of support service is different, the corresponding service knowledge map is constructed for each type of support service.

On the basis of detecting the service information contained in the service picture, further identifying target service information in the service information according to a service knowledge graph, and comparing with keyword matching to identify the target service information, the identification accuracy of the target service information is improved, in an optional implementation manner provided by the embodiment of the present specification, the service knowledge graph based on the target service identifies the entity in the service information to obtain the target service information corresponding to the target entity in the service knowledge graph, and the following manner is specifically adopted to implement:

In practical application, the entity is an abstraction of an objective individual, a user, a hospital, a disease, and the like can be regarded as one entity, and the entity type is an abstraction of a set of entities having the same characteristics or attributes, for example, a disease a is an entity, a disease B is an entity, a disease C is an entity, and these diseases all have characteristics of a diseased part, a symptom, and the like, so that entities having characteristics of a diseased part, a symptom, and the like, such as a disease a, a disease B, a disease C, and the like, can be abstracted as an entity type being a disease type.

It should be noted that the business knowledge graph includes a plurality of entities and the association relationship between the entities.

Specifically, the first object is information extracted from the service information and matched with at least one entity type in preset entity types; the first entity is an entity corresponding to the first object in the service knowledge graph, and because the first object has corresponding text information in the service information, the first entity also has corresponding text information in the service information; the target entity refers to an entity which is screened from the first entity and has high relevance with the target service; the target service information refers to the corresponding text information of the target entity in the service information.

In specific implementation, the Entity in the service information may be identified by using NER (Named Entity identification), which is also called Named Entity identification, and is a common task in natural language processing, and is used for identifying a specific type of Entity in the service information.

In the process of extracting a first object from service information, sentence-segmentation and word-segmentation processing needs to be performed on the service information, and on the basis of sentence-segmentation and word-segmentation, a first object matched with a preset entity type is extracted from a word unit after word-segmentation processing, so that accuracy of extracting the first object is improved.

Performing sentence division processing on the service information;

In practical application, because the service difference of different target services is very large, the difference of service expressions is also large, and in order to improve the accuracy of sentence segmentation and word segmentation of service information, a corresponding corpus can be constructed according to the service expressions of the target services, and sentence segmentation and word segmentation processing is performed on the service information based on the constructed corpus.

In specific implementation, on the basis of sentence and word segmentation of the service information, the matching degree of each word unit contained in the service information with a preset entity type is respectively calculated, wherein the matching degree can be a percentage value, and under the condition that the matching degree between the word unit and any entity type in the preset entity types is greater than a preset matching degree threshold value, the word unit is used as a first object corresponding to any entity type.

Along the use example, on the basis of obtaining the business information 'name U performs radiotherapy attention rest for the disease A', the business information is subjected to sentence division processing and word division processing, a word unit set { name U, aim at, disease A, proceeding, radiotherapy, attention, rest } is obtained, the preset entity types are time types, disease types, hospital types and diagnosis and treatment types, the matching degree of each word unit contained in the word unit set { name U, aim at, disease A, proceeding, radiotherapy, attention, rest } and the aforementioned entity types is respectively calculated, and the preset matching degree threshold is 90%, then no word unit with the time type or hospital type matching degree greater than 90% exists in the word unit, the word unit with the disease type matching degree greater than 90% is the disease A, the word unit with the diagnosis and treatment type matching degree greater than 90% is the radiotherapy, then "disease a" and "reflex therapy" are taken as the first subjects.

Further, on the basis of extracting the first object in the service information, in an optional implementation manner provided by the embodiment of the present specification, the screening, based on the service knowledge graph, of the target entity in the first entity corresponding to the first object is specifically implemented by adopting the following manner:

The entity information refers to an entity in the service knowledge graph, and specifically, as shown in fig. 2, the service knowledge graph includes 4 entities, where the 4 entities are: "disease a 1", "hospital", "radiation therapy", "free medical treatment"; the conclusion entity is an entity for determining a business conclusion in the target business, the target entity which reaches the conclusion entity through retrieval in the business knowledge graph is used as a key entity which is closely related to the business in the business knowledge graph, and the target business information corresponding to the target entity is used as the key business information in the business information.

In specific implementation, the obtained first object is compared with each entity according to the similarity obtained by the similarity comparison, an entity with the similarity larger than a similarity threshold value is selected as a first entity according to the similarity obtained by the similarity comparison, the first object extracted from the service information is standardized into the first entity in the service knowledge graph according to the entity in the service knowledge graph, the service knowledge graph is retrieved according to the first entity, and a target entity which reaches a conclusion entity in the first entity is determined.

Following the above example, the first object is extracted from the traffic information: on the basis of the disease a and the reflex therapy, the similarity between the two first objects and the four entities included in the business knowledge graph shown in fig. 2 is calculated, and the first object is determined according to the calculated similarity: the entities corresponding to "disease a" in the business knowledge map are: the "disease a 1" and the first object "reflection therapy" are "reflection therapy" in the business knowledge graph, the two entities are used as the first entity, the first entity is used as the search condition, the business knowledge graph is searched, the conclusion entity "free medical treatment" is obtained in the search result, the first entity "disease a 1" and "reflection therapy" are used as the target entities, the target objects corresponding to the target entities are further determined as "disease a" and "reflection therapy", and the target objects "disease a" and "reflection therapy" are used as the target business information.

Step S108, determining the target position information of the target service information in the service picture according to the first position information and the second position information.

Specifically, the target position information of the target service information in the service picture is further determined on the basis of determining the first position information of the characters in the service information in the service picture and determining the second position information of the target service information in the service information.

The target location information is similar to the first location information, and refers to coordinate information of a location frame where the target service information is located in the service picture, which is not described herein again.

In a specific implementation, in an optional implementation manner provided by this embodiment of the present disclosure, the determining, according to the first location information and the second location information, target location information of the target service information in the service picture specifically is implemented by:

The line coding means that the target service information is in the second row in a service picture; correspondingly, the target line information refers to text information contained in a line where the target service information is located in the service picture; the start-stop code includes a line start character code and a line stop character code, and specifically means that the target service information starts from a few words to a few words in the target line information.

In specific implementation, according to the line code corresponding to the target service information in the service picture and the start-stop code corresponding to the target service information in the target line information corresponding to the line code, and the coordinate representation of each character in the service information in the service picture, the target position information corresponding to each target service information is determined.

Along with the above example, the target position information of the target service information "disease a" in the discharge summary picture is determined, where the initial text code of the target service information "disease a" in the service information is 6, that is, the 6 th text in the service information starts to be the target service information "disease a", the offset of the first row in the discharge summary picture is 3, and the offset of the second row is 3+11=14, then the initial text code is within the offset range of the second row, and the corresponding row code of the target service information "disease a" in the discharge summary picture can be determined to be 2;

the corresponding line code 2 of the target business information 'disease A' in the discharge summary picture, the starting character code is 6, and the number of characters contained in the target business information is 3, further determining the corresponding line starting character code 3 and the line ending character code 5 of the target business information 'disease A' in the target line information 'carrying out radiotherapy aiming at the disease A' corresponding to the line code 2;

and finally, according to the line start character code 3, the line end character code 5 and the first position information, determining coordinate representation of a rectangular positioning frame of the three characters of 'disease A' in the first position information in the discharge summary picture respectively, and then taking the upper left corner coordinate of the first character and the lower right corner coordinate of the third character in the three characters as target position information of the rectangular positioning frame of the target service information 'disease A' in the discharge summary picture.

In practical application, on the basis of determining target position information of target service information in a service picture, a picture region corresponding to the target service information in the service picture is highlighted, so that the target service information in the service picture is quickly positioned, auditing efficiency of the service picture is improved, and auditing accuracy of the service picture is improved.

The target area refers to an image area corresponding to target position information in a service image, on the basis of the target area, the highlighting of the target area of the service image refers to highlighting the target area in a manner of font color, ground color or positioning frame adding and the like, and the service image after highlighting is stored in an image library, so that when a viewing instruction of a user for the service image is received, the service image after highlighting can be directly obtained from the image library and displayed.

According to the above example, on the basis of determining the target position information corresponding to the target service information "disease A" and "radiotherapy" in the discharge summary picture, the two target position information are highlighted in a manner that yellow shading is added to the corresponding target area in the discharge summary picture, and the discharge summary picture with the yellow shading added to the target area is stored in the picture library.

In practical application, there may be one or more target service information corresponding to a target entity, and when there are a plurality of target service information, there are a plurality of target location information corresponding to the target service information, in an optional implementation manner provided in this specification, after determining that the target location information of the target service information in the service picture is executed according to the first location information and the second location information, and before performing highlighting processing on the target area of the service picture according to the target location information, it is further required to fuse location areas where the target location information overlaps, which is specifically implemented by the following manners:

if so, performing region fusion on the overlapped target regions to obtain fusion position information after the region fusion, and updating the target position information according to the fusion position information;

if not, the operation is not required.

In practical application, if the result of determining whether the target areas corresponding to the target position information in the service picture overlap is yes, the overlapped target areas are subjected to area fusion, so that the condition that the plurality of target position information are highlighted is avoided, the highlighting effects conflict with each other, and the viewing experience of a user on the service picture is influenced.

Suppose that the target location information of the target business information "disease a" in the discharge summary picture is: [

，

，

，

]The target business information "radiotherapy" is the target position information in the discharge bar picture of [, ]

，

，

，

]Wherein, in the step (A),

at the position of

And

in the above-mentioned manner,

is greater than

，

And

the phase of the two phases is equal to each other,

and

is less than

If the coordinates of the rectangular positioning frame of the target business information disease A and the target position information radiotherapy in the discharge bar picture are determined to have an overlapping part, the target area of the target business information disease A in the discharge bar picture and the target area of the target business information radiotherapy in the discharge bar picture are subjected to area fusion, and the fusion position information after the area fusion is [ ] [, ]

，

，

，

]The fused position information is used as the target position information of the target business information 'disease A' and 'radiotherapy' in the discharge summary picture.

In addition to the foregoing, after determining the target location information in the service picture, storing the service picture after highlighting the target region corresponding to the target location information, after determining the target location information in the service picture, the target location information may be stored, and after receiving a viewing instruction for the service picture, the service picture may be highlighted, only the target location information is stored, the service picture after highlighting is not required to be stored, and the storage pressure is reduced.

Receiving a viewing instruction aiming at the business picture;

In practical application, after the target position information of the target service information in the service picture is determined, if the service picture is viewed, the highlighted processing may be performed in a target area corresponding to the target position information in the service picture, and the highlighted service picture is displayed.

To sum up, the present specification provides an information positioning method based on a picture, which detects a service picture of a target service on the basis of obtaining the service picture, obtains service information included in the service picture and first position information of characters in the service information in the service picture, identifies an entity in the service information based on a service knowledge graph of the target service, obtains target service information corresponding to a target entity in the service knowledge graph and second position information of the target service information in the service information, further determines target position information of the target service information in the service picture according to the first position information and the second position information, and performs a highlight display process on a target area corresponding to the target position information in the service picture, the target service information in the service picture is positioned, and the auditing efficiency and the auditing accuracy of the service picture are further increased.

The following description will further describe the image-based information positioning method with reference to fig. 3 by taking an application of the image-based information positioning method provided in this specification in a mutual aid service as an example. Fig. 3 shows a processing flow chart of an image-based information positioning method applied to a mutual aid service according to an embodiment of the present specification, which specifically includes the following steps:

step S302, a mutual aid service picture of the mutual aid service is obtained.

Specifically, the mutual aid service is participated by a group of service members with common homogeneous guarantee requirements and willing to share guarantee risks, and when accidents, disabilities or diseases and the like occurring during the participation of the service members in the mutual aid service reach conditions agreed by the mutual aid service, the service members can submit related materials such as mutual aid service pictures in case form and apply mutual aid relief funds.

The mutual aid service pictures comprise claim settlement material pictures, such as a doctor seeing picture, a discharge summary picture and the like, and further comprise health notice pictures in the health notice process, such as a past medical history picture and a physical examination picture and the like.

Step S304, the mutual aid service picture is detected, and the business information contained in the mutual aid service picture and the corresponding line position information of the business information in the mutual aid service picture are obtained.

And S306, performing information splicing on the business information to obtain business information, and performing region segmentation on a picture region corresponding to the line position information to obtain first position information of characters in the business information in the mutual aid business picture.

Step S308, extracting a first object in the service information according to a preset entity type.

Specifically, the extracting of the first object in the service information according to the preset entity type is specifically implemented in the following manner:

performing sentence division processing on the service information;

Step S310, comparing the similarity of the first object and the entity in the mutual aid service knowledge map to determine the first entity.

Step S312, according to the first entity, searching is carried out in the mutual aid service knowledge graph, and a target entity reaching the mutual aid conclusion entity is determined.

Specifically, if the mutual aid service picture is a claim settlement material picture, the mutual aid conclusion entity may be an entity that is not claimed, and if the mutual aid service picture is a health notice picture, the mutual aid conclusion entity may be an entity that is not in violation of health notice.

Step S314, using the target object corresponding to the target entity as the target service information, and determining the second location information of the target service information in the service information.

Step S316, according to the second position information and the business information, calculating a line code corresponding to the target business information in the mutual aid business picture and a start-stop code in the target line information corresponding to the line code.

Step S318, determining the corresponding target location information of the target service information in the mutual aid service picture according to the line code, the start-stop code and the first location information.

Step S320, judging whether the target areas corresponding to the target position information in the mutual aid service picture are overlapped or not;

if yes, go to step S322;

if not, the processing is not required.

Step S322, performing area fusion on the overlapped target areas to obtain fusion position information after the area fusion, and updating the target position information according to the fusion position information.

Step S324, according to the target position information, highlighting the target area of the mutual aid service picture.

Step S326, storing the mutual aid service pictures after the highlighting processing in a picture library corresponding to the mutual aid service.

Specifically, after storing the mutual aid service picture after the highlighting processing in a picture library corresponding to the mutual aid service, the method further includes:

receiving a viewing instruction aiming at the mutual aid service picture after the highlighting processing;

and acquiring and displaying the mutual aid service picture after highlighting processing based on the picture identification carried in the viewing instruction.

To sum up, the present specification provides an information positioning method based on pictures, which detects a mutual aid service picture on the basis of obtaining the mutual aid service picture of a mutual aid service, obtains service information included in the mutual aid service picture and first position information of characters in the service information in the mutual aid service picture, performs entity identification on the service information based on a mutual aid service knowledge graph of a target service, and obtains target service information corresponding to a target entity in the mutual aid service knowledge graph and second position information of the target service information in the service information; and determining the target position information of the target service information in the mutual aid service picture according to the first position information and the second position information, thereby realizing the positioning of the target service information in the mutual aid service picture and further increasing the auditing efficiency and the auditing accuracy of the mutual aid service picture.

The embodiment of the information positioning device based on the picture provided by the specification is as follows:

corresponding to the above method embodiments, the present specification further provides an embodiment of an information positioning device based on pictures, and fig. 4 shows a schematic diagram of an information positioning device based on pictures provided in an embodiment of the present specification. As shown in fig. 4, the apparatus includes:

an obtaining module 402 configured to obtain a service picture of a target service;

a detection module 404, configured to detect the service picture, and obtain service information included in the service picture and first position information of a character in the service information in the service picture;

an entity identification module 406, configured to identify an entity in the service information based on a service knowledge graph of the target service, and obtain target service information corresponding to the target entity in the service knowledge graph and second location information of the target service information in the service information;

a location determining module 408 configured to determine, according to the first location information and the second location information, target location information of the target service information in the service picture.

Optionally, the entity identifying module 406 includes:

the extraction submodule is configured to extract a first object in the service information according to a preset entity type;

a screening submodule configured to screen a target entity from first entities corresponding to the first object based on the service knowledge graph;

and the information determining submodule is configured to take a target object corresponding to the target entity as the target service information.

Optionally, the screening submodule includes:

an entity determining unit configured to compare the similarity of the first object with an entity in the business knowledge graph to determine the first entity;

and the target entity determining unit is configured to search in the service knowledge graph according to the first entity, and determine a target entity reaching the conclusion entity.

Optionally, the extracting sub-module includes:

a clause unit configured to perform clause processing on the service information;

the word segmentation unit is configured to perform word segmentation on the sentence segmentation processing result to obtain a word unit set consisting of word units;

a matching degree calculating unit configured to calculate matching degrees of each word unit in the word unit set and the entity type;

a selecting unit configured to select a word unit satisfying a threshold of a degree of matching as the first object according to a calculation result.

Optionally, the detecting module 404 includes:

the detection information submodule is configured to detect the service picture, and obtain service information contained in the service picture and corresponding row position information of the row service information in the service picture;

and the segmentation submodule is configured to perform information splicing on the business information to obtain the business information, and perform region segmentation on a picture region corresponding to the row position information to obtain the first position information.

Optionally, the module 408 for determining a location includes:

the calculation coding sub-module is configured to calculate a line code corresponding to the target service information in the service picture and a start-stop code in the target line information corresponding to the line code according to the second position information and the service information;

a determination information submodule configured to determine the target location information based on the line code, the start-stop code, and the first location information.

Optionally, the image-based information positioning apparatus further includes:

the highlight module is configured to perform highlight processing on a target area of the business picture according to the target position information;

and the storage module is configured to store the highlighted service picture in a picture library corresponding to the target service.

correspondingly, the picture-based information positioning device further comprises:

the judging module is configured to judge whether target areas corresponding to the target position information in the service picture are overlapped or not;

and if so, operating a fusion module, wherein the fusion module is configured to perform region fusion on the overlapped target regions, obtain fusion position information after the region fusion, and update the target position information according to the fusion position information.

Optionally, the image-based information positioning apparatus further includes:

a receiving instruction module configured to receive a viewing instruction for the business picture;

the image obtaining module is configured to obtain the service image and the target position information based on an image identifier carried in the viewing instruction;

and the display module is configured to perform highlighting processing on the target area of the business picture according to the target position information and display the target area.

Optionally, the image-based information positioning apparatus further includes:

the image receiving module is configured to receive the service image uploaded by the user;

and the picture storage module is configured to store the service picture in a picture library corresponding to the target service.

The above is a schematic solution of the image-based information positioning apparatus of this embodiment. It should be noted that the technical solution of the image-based information positioning apparatus and the technical solution of the image-based information positioning method belong to the same concept, and details that are not described in detail in the technical solution of the image-based information positioning apparatus can be referred to the description of the technical solution of the image-based information positioning method.

The present specification provides an embodiment of a computing device as follows:

FIG. 5 illustrates a block diagram of a computing device 500 provided in accordance with one embodiment of the present description. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. Processor 520 is coupled to memory 510 via bus 530, and database 550 is used to store data.

Computing device 500 also includes access device 540, access device 540 enabling computing device 500 to communicate via one or more networks 560. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 540 may include one or more of any type of network interface, e.g., a Network Interface Card (NIC), wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 500, as well as other components not shown in FIG. 5, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 5 is for purposes of example only and is not limiting as to the scope of the present description. Those skilled in the art may add or replace other components as desired.

Computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 500 may also be a mobile or stationary server.

The present specification provides a computing device comprising a memory 510, a processor 520, and computer instructions stored on the memory and executable on the processor, the processor 520 being configured to execute the following computer-executable instructions:

acquiring a service picture of a target service;

The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the above-mentioned image-based information positioning method belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the above-mentioned image-based information positioning method.

This specification provides one example of a computer-readable storage medium, comprising:

the present specification provides a computer readable storage medium storing computer instructions that, when executed by a processor, are operable to:

acquiring a service picture of a target service;

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the above-mentioned picture-based information positioning method, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the above-mentioned picture-based information positioning method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts, but those skilled in the art should understand that the present embodiment is not limited by the described acts, because some steps may be performed in other sequences or simultaneously according to the present embodiment. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that acts and modules referred to are not necessarily required for an embodiment of the specification.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the embodiments. The specification is limited only by the claims and their full scope and equivalents.

Claims

1. An information positioning method based on pictures comprises the following steps:

acquiring a service picture to be audited of a target service;

identifying an entity in the service information based on the service knowledge graph of the target service, and obtaining target service information corresponding to the target entity in the service knowledge graph and second position information of the target service information in the service information, wherein the service knowledge graph comprises a conclusion entity for determining a service conclusion of the target service, and the target entity and the conclusion entity have a touch relationship;

2. The picture-based information positioning method according to claim 1, wherein the identifying an entity in the service information based on the service knowledge graph of the target service to obtain the target service information corresponding to the target entity in the service knowledge graph comprises:

3. The picture-based information positioning method according to claim 2, wherein the screening a target entity from the first entities corresponding to the first object based on the service knowledge graph comprises:

4. The picture-based information positioning method according to claim 2, wherein the extracting the first object in the service information according to the preset entity type comprises:

performing sentence division processing on the service information;

5. The method according to claim 1, wherein the detecting the service picture to obtain the service information included in the service picture and the first position information of the text in the service information in the service picture comprises:

6. The picture-based information positioning method according to claim 5, wherein the determining the target location information of the target service information in the service picture according to the first location information and the second location information comprises:

7. The method according to claim 1, wherein said determining the target service information according to the first location information and the second location information after the step of determining the target location information in the service picture is executed, further comprises:

8. The picture-based information positioning method according to claim 7, wherein when the target service information is plural, there are plural pieces of the target position information;

9. The method according to claim 1, wherein said determining the target service information according to the first location information and the second location information after the step of determining the target location information in the service picture is executed, further comprises:

receiving a viewing instruction aiming at the business picture;

10. The picture-based information positioning method according to claim 1, wherein before the step of obtaining the service picture to be audited of the target service is executed, the method further comprises:

receiving the service picture uploaded by a user;

11. The picture-based information positioning method according to claim 1, wherein the target service comprises a mutual aid service; correspondingly, the service pictures comprise mutual service pictures.

12. A picture-based information positioning apparatus, comprising:

the acquisition module is configured to acquire a service picture to be audited of the target service;

an entity identification module configured to identify an entity in the service information based on a service knowledge graph of the target service, and obtain target service information corresponding to a target entity in the service knowledge graph and second position information of the target service information in the service information, wherein the service knowledge graph includes a conclusion entity for determining a service conclusion of the target service, and the target entity and the conclusion entity have a reach relationship;

13. A computing device, comprising:

a memory and a processor;

acquiring a service picture to be audited of a target service;

14. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the picture-based information positioning method according to any one of claims 1 to 11.