CN113282761A - Department information pushing method, device, equipment and storage medium - Google Patents
Department information pushing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113282761A CN113282761A CN202110585543.4A CN202110585543A CN113282761A CN 113282761 A CN113282761 A CN 113282761A CN 202110585543 A CN202110585543 A CN 202110585543A CN 113282761 A CN113282761 A CN 113282761A
- Authority
- CN
- China
- Prior art keywords
- information
- entity information
- entity
- department
- intention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Animal Behavior & Ethology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a pushing method of department information, which comprises the following steps: acquiring a main complaint text for recording the user condition; inputting the main complaint text into a preset intention entity recognition model for analysis to obtain entity information contained in the main complaint text and an intention label corresponding to each entity information; searching a preset knowledge graph based on all the entity information and the intention label corresponding to each entity information to obtain department information to be pushed; and pushing the department information to a terminal corresponding to the user. Therefore, the method and the device can extract more sufficient information from the main complaint text to analyze the department information to be pushed, so that the pushing accuracy of the department information is improved. The invention also relates to the technical field of block chains.
Description
Technical Field
The invention relates to the technical field of neural networks, in particular to a pushing method and device of department information, computer equipment and a storage medium.
Background
In the management of hospitals, triage of personnel (i.e. assignment of personnel to appropriate departments according to their specific circumstances) is an important part. With the development of computer technology, it has become possible to use computer technology to assist in triage of personnel. Specifically, a chief complaint text in which the user condition is recorded may be collected, then symptom information in which the user symptom is recorded may be directly extracted from the chief complaint text using a preset neural network model, and finally, a preset knowledge graph may be searched according to the symptom information, thereby determining the department information to be pushed. For example, the complaint text of the user is that "i feel weak and sleepless but do not have other symptoms, and see that the traditional Chinese medicine wants to adjust one time before, the symptom information of the weak and sleepless can be extracted, then the knowledge graph is searched according to the symptom information, so that the department information to be pushed is determined, and finally the department information is pushed to the terminal (such as the personal mobile phone of the user) corresponding to the user to guide the user to go to the corresponding department. However, the information contained in the main complaint text of the user is various (for example, the main complaint text also contains information that the user has no other symptoms and has visited the traditional Chinese medicine department before), and if only the symptom information in the main complaint text is extracted as the basis for pushing the department information, the last pushed department information may be inaccurate due to insufficient information amount (for example, the main complaint text also contains information that the user has visited the traditional Chinese medicine department, and if the information is synthesized for analysis, the user can continue to be diagnosed to the traditional Chinese medicine department). Therefore, the pushing accuracy of the current pushing method for department information still has a space for further improvement.
Disclosure of Invention
The technical problem to be solved by the invention is that the pushing accuracy of the current pushing method of department information is low.
In order to solve the technical problem, a first aspect of the present invention discloses a method for pushing department information, where the method includes:
acquiring a main complaint text for recording the user condition;
inputting the main complaint text into a preset intention entity recognition model for analysis to obtain entity information contained in the main complaint text and an intention label corresponding to each entity information, wherein the intention label corresponding to each entity information is one of a preset chief complaint intention label, an accompanying complaint intention label, a past medical history intention label and a historical visit intention label, and the entity information at least comprises chief complaint entity information which is entity information of which the corresponding intention label is the chief complaint intention label;
searching a preset knowledge graph based on all the entity information and the intention label corresponding to each entity information to obtain department information to be pushed;
and pushing the department information to a terminal corresponding to the user.
The invention discloses a department information pushing device in a second aspect, which comprises:
the acquisition module is used for acquiring a main complaint text for recording the user condition;
the analysis module is used for inputting the main complaint text into a preset intention entity identification model for analysis to obtain entity information contained in the main complaint text and an intention label corresponding to each entity information, wherein the intention label corresponding to each entity information is one of a preset chief complaint intention label, an accompanying complaint intention label, a past medical history intention label and a historical visit intention label, the entity information at least comprises chief complaint entity information, and the chief complaint entity information is entity information of which the corresponding intention label is the chief complaint intention label;
the search module is used for searching a preset knowledge graph based on all the entity information and the intention labels corresponding to the entity information to obtain department information to be pushed;
and the pushing module is used for pushing the department information to a terminal corresponding to the user.
A third aspect of the present invention discloses a computer apparatus, comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program code stored in the memory to execute part or all of the steps in the pushing method of department information disclosed by the first aspect of the invention.
In a fourth aspect of the present invention, a computer storage medium is disclosed, which stores computer instructions for executing some or all of the steps of the pushing method of department information disclosed in the first aspect of the present invention when the computer instructions are called.
In the embodiment of the invention, the subject text is input into the intention entity recognition model for analysis to obtain the entity information contained in the subject text and the intention label corresponding to each entity information, then the knowledge graph is searched based on all the entity information and the intention label corresponding to each entity information to obtain the department information to be pushed, and finally the department information is pushed to the terminal corresponding to the user, so that the entity information of the preset type and the intention labels corresponding to the entity information of different types can be extracted from the subject text for analysis of the department information to be pushed, and as the intention labels comprise the preset four labels (the main symptom intention label, the accompanying symptom intention label, the past medical history intention label and the historical visit intention label), more sufficient information can be extracted from the subject text for analysis of the department information to be pushed, thereby improving the pushing accuracy of the department information.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a pushing method of department information disclosed in an embodiment of the present invention;
FIG. 2 is an exemplary diagram of the output of the intent entity recognition model disclosed in the embodiments of the present invention;
FIG. 3 is a schematic diagram of a knowledge-graph in an embodiment of the invention;
fig. 4 is a schematic structural diagram of a department information pushing device disclosed in the embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a computer storage medium according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or article.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase 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. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention discloses a method, a device, computer equipment and a storage medium for pushing department information, which are characterized in that a main complaint text is input into an intention entity recognition model for analysis to obtain entity information contained in the main complaint text and intention labels corresponding to each entity information, a knowledge graph is searched based on all the entity information and the intention labels corresponding to each entity information to obtain the department information to be pushed, and finally the department information is pushed to a terminal corresponding to a user, so that preset type entity information and intention labels corresponding to different types of entity information can be extracted from the main complaint text for analysis of the department information to be pushed, and as the intention labels comprise four preset labels (a main symptom intention label, an accompanying symptom intention label, a past medical history intention label and a historical diagnosis intention label), therefore, more sufficient information can be extracted from the main complaint text to analyze the department information to be pushed, so that the pushing accuracy of the department information is improved. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a pushing method of department information according to an embodiment of the present invention. As shown in fig. 1, the pushing method of department information may include the following operations:
101. and acquiring a main complaint text for recording the condition of the user.
In the above step 101, the main complaint text can be obtained by: the method includes the steps of obtaining a voice of a user appealing to a user through a terminal (for example, a personal mobile phone of the user) corresponding to the user, and then converting the voice into a text (i.e., a complaint text) by using an asr (automatic Speech recognition) technology. Specifically, the user can tell the condition of the user's personal mobile phone to the microphone, and after the user's personal mobile phone collects the speech, the user's personal mobile phone can use the ASR technology to convert the collected speech into the complaint text.
102. And inputting the main complaint text into a preset intention entity recognition model for analysis to obtain entity information contained in the main complaint text and an intention label corresponding to each entity information.
In the step 102, the intention label corresponding to each entity information is one of a preset chief complaint intention label, a concomitant complaint intention label, a past medical history intention label and a historical visit intention label, and the entity information at least includes chief complaint entity information, where the corresponding intention label is the entity information of the chief complaint intention label. The intention entity recognition model can be composed of an Attention structure and a CRF structure, wherein the Attention structure is used for capturing entity information in a main complaint text, and the CRF structure is used for outputting an intention label corresponding to the captured entity information. An intention entity recognition model is formed by adding a CRF structure behind the Attention structure, so that entity information extraction and entity information intention recognition can be simultaneously realized through the intention entity recognition model, and only one round of data labeling can be performed in the process of training the intention entity recognition model, so that the workload of data labeling and model training is reduced. As shown in fig. 2, when the main complaint text is "i recently felt that i is totally weak, sleepless, but has no other symptoms, and previously seen that chinese medicine wants to adjust again", the output obtained after analysis of the intention entity recognition model may be as shown in fig. 2. In the task of intention recognition, the labeling of an intention label is carried out for each character in the main complaint text, wherein the main symptom intention label is a letter Z, the accompanying symptom intention label is a letter B, the past medical history intention label is a letter G, the historical visit intention label is a letter H, and the intention label of the text without clear intention is a letter N. In the task of extracting the entity information, labeling an entity label for each character in the main complaint text, wherein the part from the entity label Z-B to the entity label Z-I is the extracted entity information, and the entity label corresponding to the irrelevant character in the main complaint text is the letter O. It can be seen that the intention of "i recently felt the whole body is weak" in fig. 2 is a main symptom, and the entity information therein is "weak whole body", the intention of "drowsiness" is a concomitant symptom, and the entity information therein is "drowsiness", but there is no other symptom "is not clear intention", the intention of having seen the traditional chinese medicine before to turn up again "is a historical visit, and the entity information therein is" traditional chinese medicine ".
103. Searching a preset knowledge graph based on all the entity information and the intention labels corresponding to all the entity information to obtain department information to be pushed.
In the step 103, as shown in fig. 3, entities such as various symptoms, diseases, departments, and the like and association relations between the entities may be stored in the preset knowledge graph. Searching the knowledge graph based on the entity information and the intention labels corresponding to the entity information, namely searching out related diseases and departments, and then determining department information to be pushed. The search process for a specific knowledge-graph is described later.
104. And pushing the department information to a terminal corresponding to the user.
In step 104, after the department information is determined, the department information can be pushed to a terminal (e.g., a personal mobile phone of the user) corresponding to the user, and the user can go to the corresponding department for medical treatment after seeing the department information. The department information may include the name of the department, the attending physician of the department, the number of persons reserved in the department, the floor of the department, and the like.
It can be seen that, with the method for pushing department information described in fig. 1, the chief complaint text is input to the intention entity recognition model for analysis, so as to obtain the entity information contained in the chief complaint text and the intention label corresponding to each entity information, then the knowledge graph is searched based on all the entity information and the intention label corresponding to each entity information, so as to obtain the department information to be pushed, and finally the department information is pushed to the terminal corresponding to the user, so that the entity information of the preset type and the intention labels corresponding to different types of entity information can be extracted from the chief complaint text, so as to analyze the department information to be pushed, since the intention labels include the preset four labels (main symptom intention label, accompanying symptom intention label, past medical history intention label and historical visit intention label), so that more sufficient information can be extracted from the chief complaint text for analysis of the department information to be pushed, thereby improving the pushing accuracy of the department information.
In an optional embodiment, after the complaint text is input to a preset intention entity recognition model for analysis, and entity information included in the complaint text and an intention label corresponding to each entity information are obtained, the method further includes, before searching a preset knowledge graph based on all the entity information and the intention labels corresponding to each entity information and obtaining department information to be pushed:
judging whether corresponding target entity information to be matched exists in a preset synonym matching table of each entity information, wherein the synonym matching table comprises a plurality of entity information to be matched, each entity information to be matched has synonym entity information which has a mapping relation with the entity information to be matched in the synonym matching table, and the target entity information to be matched refers to the entity information to be matched which is matched with the entity information in the synonym matching table;
and when judging that the entity information has corresponding target entity information to be matched in the synonym matching table, updating the entity information into the synonym entity information which has a mapping relation with the target entity information to be matched, and triggering and executing the step of searching a preset knowledge graph based on all the entity information and the intention labels corresponding to all the entity information to obtain the department information to be pushed.
In this alternative embodiment, in the preset synonym matching table, the entity information to be matched may include "all-around stiff children" and "drowsiness", the synonymous entity information having a mapping relationship with "all-around stiff children" is "weak", and the synonymous entity information having a mapping relationship with "drowsiness" is "sleepy". In connection with the above example, the entity information "weak whole body" output by the entity recognition model is intended to be updated to "weak", the entity information "sleepless" is intended to be updated to "sleepy", and the searching of the knowledge map is performed after the updating of the entity information is completed. Chinese expressions are various, and the same meaning can be expressed by using various expressions, for example, "sleeplessness", "sleepless" and "snooze" are symptoms expressing sleepiness, but the symptom entity in the knowledge graph is usually "sleepy", and if the words with the same meaning but different forms, such as "sleeplessness", "sleepless" and "snooze", are searched, the obtained search result may be inaccurate. By the synonym matching table, after entity information such as sleeplessness, sleeplessness and snooze is aligned to the entity information sleepiness, the knowledge graph is searched, and the searching accuracy can be improved.
Therefore, by implementing the optional embodiment, before searching the knowledge graph based on the entity information, the entity information is aligned through the synonym matching table, and then the knowledge graph is searched, so that the searching accuracy can be improved, and the pushing accuracy of the department information is improved.
In an optional embodiment, the searching a preset knowledge graph based on all the entity information and the intention tag corresponding to each entity information to obtain department information to be pushed includes:
searching a preset knowledge graph based on all the entity information and the intention label corresponding to each entity information to obtain disease inference information for recording a disease inference result of the user;
and searching the knowledge graph based on the disease reasoning information to obtain the department information to be pushed.
In this alternative embodiment, assuming that the intent entity recognition model extracts only one chief complaint entity information "weakness" from the complaint text, the knowledge-graph can be searched by:
MATCH (m: Disease) - [ r: has _ Symptom ] - > (n: Symptom) where n.name ═ powerless' return m.name, r.name, n.name;
if the searched related disease is "cold", the "cold" can be used as the disease inference information.
Then searching the knowledge graph through the following sentences:
"MATCH (m: Disease) - [ r: belongs _ to ] - > (n: Department) where m.name ═ cold' return m.name, r.name, n.name";
if the searched related department is the department, the department can be used as the department information to be pushed.
Therefore, when the department information is searched from the knowledge graph based on the entity information, the corresponding disease reasoning information is searched from the knowledge graph based on the entity information, and then the corresponding department information is searched from the knowledge graph based on the disease reasoning information, so that the department information can be searched from the knowledge graph.
In an optional embodiment, the searching a preset knowledge graph based on all the entity information and the intention label corresponding to each entity information to obtain disease inference information includes:
searching the knowledge graph based on each chief symptom entity information to obtain alternative disease reasoning information corresponding to each chief symptom entity information;
and determining disease reasoning information according to the alternative disease reasoning information corresponding to each main symptom entity information.
In this alternative embodiment, there may be multiple chief complaint entity information extracted from the complaint text by the intended entity recognition model, e.g., the extracted chief complaint entity information may include "weakness" and "somnolence". Then, the inference information of the candidate disease obtained by searching the knowledge base based on the "inability" is [ cold and low blood pressure ], and the inference information of the candidate disease obtained by searching the knowledge base based on the "sleepiness" is [ early pregnancy and cold ]. At this time, the intersection "cold" of the two corresponding candidate disease inference information may be determined as the disease inference information.
Therefore, by implementing the optional embodiment, when a plurality of extracted entity information of the chief complaints exist, the alternative disease inference information corresponding to each entity information of the chief complaints is searched from the knowledge graph, and then the intersection of the alternative disease inference information is determined as the disease inference information, so that the accuracy of the disease inference information searched from the knowledge graph can be improved.
In an optional embodiment, the entity information includes chief symptom entity information and past medical history entity information, the past medical history entity information refers to entity information whose corresponding intention label is a past medical history intention label, and,
the determining of the disease inference information according to the alternative disease inference information corresponding to each cardinal symptom entity information includes:
determining a plurality of first target alternative disease inference information according to the alternative disease inference information corresponding to each chief symptom entity information;
and screening out first target alternative disease inference information matched with the past medical history entity information from the plurality of first target alternative disease inference information to be used as disease inference information.
In this optional embodiment, when there are a plurality of chief complaint entity information and the intersection of the candidate disease inference information corresponding to each chief complaint entity information has a plurality of diseases, a disease matched with the past medical history entity information may be selected from the plurality of intersected diseases as the final disease inference information. For example, the candidate disease inference information obtained by searching the knowledge graph based on "inability" is [ cold and hypotension cold ], the candidate disease inference information obtained by searching the knowledge graph based on "sleepiness" is [ early pregnancy cold ], at this time, the intersection of the candidate disease inference information corresponding to the two is [ cold ] (that is, there are two first target candidate disease inference information), and if past medical history entity information indicates that the user has had a medical history of cold, the "cold" is screened out of the two first target candidate disease inference information as the disease inference information.
Therefore, when the entity information includes the entity information of the chief complaints and the entity information of the past medical history, and a plurality of first target candidate disease inference information is determined according to the candidate disease inference information corresponding to each of the entity information of the chief complaints, the disease inference information is screened out from the plurality of first target candidate disease inference information according to the entity information of the past medical history, so that the accuracy of the determined disease inference information can be improved.
In an alternative embodiment, the entity information includes chief symptom entity information and accompanying symptom entity information, the accompanying symptom entity information refers to entity information whose corresponding intention label is an accompanying symptom intention label, and,
the determining of the disease inference information according to the alternative disease inference information corresponding to each cardinal symptom entity information includes:
determining a plurality of second target alternative disease inference information according to the alternative disease inference information corresponding to each chief symptom entity information;
searching the knowledge graph based on each second target alternative disease inference information to obtain symptom information corresponding to each second target alternative disease inference information;
and using the second target candidate disease inference information with the highest matching degree of the corresponding symptom information and the accompanying symptom entity information as disease inference information.
In this optional embodiment, when there are a plurality of chief complaint entity information and the intersection of the candidate disease inference information corresponding to each chief complaint entity information has a plurality of diseases, the final disease inference information may be screened from the plurality of diseases intersected according to the accompanying symptom of the user. For example, the candidate disease inference information obtained by searching the knowledge base based on "inability" is [ cold and hypotension cold ], the candidate disease inference information obtained by searching the knowledge base based on "sleepiness" is [ early pregnancy cold ], and at this time, the intersection of the two corresponding candidate disease inference information is [ cold ] (i.e., there are two second target candidate disease inference information). Then, symptom information corresponding to the cold and the cold is searched from the knowledge graph. If the searched symptom information corresponding to the cold is headache and running nose, the searched symptom information corresponding to the cold is dizziness and running nose, and the accompanying symptom entity information indicates that the user has accompanying symptoms of the dizziness, the matching degree of the symptom information corresponding to the cold and the accompanying symptom entity information is the highest, so that the cold is determined as disease inference information.
Therefore, when the entity information includes the chief symptom entity information and the incidental symptom entity information, and a plurality of second target candidate disease inference information determined according to the candidate disease inference information corresponding to each chief symptom entity information is provided, the disease inference information is screened out from the plurality of second target candidate disease inference information according to the incidental symptom entity information, so that the accuracy of the determined disease inference information can be improved.
In an alternative embodiment, the entity information includes chief symptom entity information and historical visit entity information, the historical visit entity information refers to entity information whose corresponding intention label is a historical visit intention label, and,
the searching of the knowledge graph based on the disease reasoning information to obtain the department information to be pushed comprises the following steps:
searching the knowledge graph based on the disease reasoning information to obtain a plurality of candidate department information corresponding to the disease reasoning information;
and screening out alternative department information matched with the historical clinic entity information from the alternative department information to serve as department information to be pushed.
In this optional embodiment, there may be a plurality of candidate department information obtained after searching the knowledge graph based on the disease inference information, and at this time, the department information to be pushed may be screened from the plurality of candidate department information according to the historical visit entity information. For example, the alternative department information obtained by searching the knowledge graph based on the disease reasoning information "cold" is "internal medicine" and "traditional Chinese medicine", if the historical visiting entity information indicates that the user visits a doctor in the traditional Chinese medicine department once, the alternative department information "traditional Chinese medicine" is matched with the historical visiting entity information, and the alternative department information "traditional Chinese medicine" is used as the department information to be pushed.
Therefore, when the entity information comprises the entity information of the chief symptoms and the historical information of the department, and a plurality of candidate department information is obtained after the knowledge graph is searched based on the disease reasoning information, the department information to be pushed is screened from the plurality of candidate department information according to the historical information of the department, so that the accuracy of the determined department information can be improved.
Optionally, it is also possible: and uploading the pushing information of the department information of the pushing method of the department information to a block chain.
Specifically, the pushing information of department information is obtained by operating a pushing method of the department information, and is used for recording the pushing situation of the department information, for example, the obtained main complaint text, the entity information output by the intention entity identification model, the intention label corresponding to the entity information, the searched department information, and the like. Uploading the pushing information of the department information to the block chain can ensure the safety and the just transparency to the user. The user can download the pushed information of the department information from the blockchain so as to verify whether the pushed information of the department information of the pushing method of the department information is tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Example two
Referring to fig. 4, fig. 4 is a schematic structural diagram of a pushing device for department information according to an embodiment of the present invention. As shown in fig. 4, the department information pushing device may include:
an obtaining module 401, configured to obtain a main complaint text used for recording a user condition;
an analysis module 402, configured to input the main complaint text into a preset intention entity identification model for analysis, so as to obtain entity information included in the main complaint text and an intention label corresponding to each entity information, where an intention label corresponding to each entity information is one of a preset chief complaint intention label, an accompanying complaint intention label, a past medical history intention label, and a history visit intention label, and the entity information at least includes chief complaint entity information, where the chief complaint entity information is entity information whose corresponding intention label is a chief complaint intention label;
the searching module 403 is configured to search a preset knowledge graph based on all the entity information and the intention tag corresponding to each entity information to obtain department information to be pushed;
a pushing module 404, configured to push the department information to a terminal corresponding to the user.
For the specific description of the department information pushing device, reference may be made to the specific description of the department information pushing method, and for avoiding repetition, details are not repeated herein.
EXAMPLE III
Referring to fig. 5, fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 5, the computer apparatus may include:
a memory 501 in which executable program code is stored;
a processor 502 connected to the memory 501;
the processor 502 calls the executable program code stored in the memory 501 to execute the steps of the pushing method of department information disclosed in the embodiment of the present invention.
Example four
The embodiment of the invention discloses a computer storage medium 601, wherein a computer instruction is stored in the computer storage medium 601 and is used for executing the steps in the pushing method of department information disclosed by the embodiment of the invention when being called.
The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above detailed description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, where the storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc-Read-Only Memory (CD-ROM), or other magnetic disk memories, magnetic tape memories, magnetic disk drives, magnetic tape drives, and magnetic tape drives, Or any other medium which can be used to carry or store data and which can be read by a computer.
Finally, it should be noted that: the method, apparatus, computer device and storage medium for pushing department information disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used for illustrating the technical solutions of the present invention, not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A pushing method of department information is characterized by comprising the following steps:
acquiring a main complaint text for recording the user condition;
inputting the main complaint text into a preset intention entity recognition model for analysis to obtain entity information contained in the main complaint text and an intention label corresponding to each entity information, wherein the intention label corresponding to each entity information is one of a preset chief complaint intention label, an accompanying complaint intention label, a past medical history intention label and a historical visit intention label, and the entity information at least comprises chief complaint entity information which is entity information of which the corresponding intention label is the chief complaint intention label;
searching a preset knowledge graph based on all the entity information and the intention label corresponding to each entity information to obtain department information to be pushed;
and pushing the department information to a terminal corresponding to the user.
2. The method for pushing department information according to claim 1, wherein after the complaint text is input to a preset intention entity recognition model for analysis, and entity information contained in the complaint text and an intention tag corresponding to each entity information are obtained, the method further comprises the following steps of searching a preset knowledge graph based on all the entity information and the intention tags corresponding to each entity information, and before the department information to be pushed is obtained:
judging whether corresponding target entity information to be matched exists in a preset synonym matching table of each entity information, wherein the synonym matching table comprises a plurality of entity information to be matched, each entity information to be matched has synonym entity information which has a mapping relation with the entity information to be matched in the synonym matching table, and the target entity information to be matched refers to the entity information to be matched which is matched with the entity information in the synonym matching table;
and when judging that the entity information has corresponding target entity information to be matched in the synonym matching table, updating the entity information into the synonym entity information which has a mapping relation with the target entity information to be matched, and triggering and executing the step of searching a preset knowledge graph based on all the entity information and the intention labels corresponding to all the entity information to obtain the department information to be pushed.
3. The department information pushing method according to claim 1 or 2, wherein the step of searching a preset knowledge graph based on all the entity information and the intention tag corresponding to each entity information to obtain the department information to be pushed comprises the steps of:
searching a preset knowledge graph based on all the entity information and the intention label corresponding to each entity information to obtain disease inference information for recording a disease inference result of the user;
and searching the knowledge graph based on the disease reasoning information to obtain the department information to be pushed.
4. The department information pushing method according to claim 3, wherein the step of searching a preset knowledge graph based on all the entity information and the intention labels corresponding to each entity information to obtain disease inference information comprises:
searching the knowledge graph based on each chief symptom entity information to obtain alternative disease reasoning information corresponding to each chief symptom entity information;
and determining disease reasoning information according to the alternative disease reasoning information corresponding to each main symptom entity information.
5. The department information pushing method according to claim 4, wherein the entity information includes chief complaint entity information and past medical history entity information, the past medical history entity information being entity information whose corresponding intention label is a past medical history intention label, and,
the determining of the disease inference information according to the alternative disease inference information corresponding to each cardinal symptom entity information includes:
determining a plurality of first target alternative disease inference information according to the alternative disease inference information corresponding to each chief symptom entity information;
and screening out first target alternative disease inference information matched with the past medical history entity information from the plurality of first target alternative disease inference information to be used as disease inference information.
6. The department information pushing method according to claim 4, wherein the entity information includes chief symptom entity information and accompanying symptom entity information, the accompanying symptom entity information being entity information whose corresponding intention label is an accompanying symptom intention label, and,
the determining of the disease inference information according to the alternative disease inference information corresponding to each cardinal symptom entity information includes:
determining a plurality of second target alternative disease inference information according to the alternative disease inference information corresponding to each chief symptom entity information;
searching the knowledge graph based on each second target alternative disease inference information to obtain symptom information corresponding to each second target alternative disease inference information;
and using the second target candidate disease inference information with the highest matching degree of the corresponding symptom information and the accompanying symptom entity information as disease inference information.
7. The department information pushing method according to claim 3, wherein the entity information includes chief complaint entity information and historical visit entity information, the historical visit entity information being entity information whose corresponding intention label is a historical visit intention label, and,
the searching of the knowledge graph based on the disease reasoning information to obtain the department information to be pushed comprises the following steps:
searching the knowledge graph based on the disease reasoning information to obtain a plurality of candidate department information corresponding to the disease reasoning information;
and screening out alternative department information matched with the historical clinic entity information from the alternative department information to serve as department information to be pushed.
8. A pushing device of department information, characterized in that the device comprises:
the acquisition module is used for acquiring a main complaint text for recording the user condition;
the analysis module is used for inputting the main complaint text into a preset intention entity identification model for analysis to obtain entity information contained in the main complaint text and an intention label corresponding to each entity information, wherein the intention label corresponding to each entity information is one of a preset chief complaint intention label, an accompanying complaint intention label, a past medical history intention label and a historical visit intention label, the entity information at least comprises chief complaint entity information, and the chief complaint entity information is entity information of which the corresponding intention label is the chief complaint intention label;
the search module is used for searching a preset knowledge graph based on all the entity information and the intention labels corresponding to the entity information to obtain department information to be pushed;
and the pushing module is used for pushing the department information to a terminal corresponding to the user.
9. A computer device, characterized in that the computer device comprises:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program code stored in the memory to execute the pushing method of department information according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the pushing method of department information according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110585543.4A CN113282761A (en) | 2021-05-27 | 2021-05-27 | Department information pushing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110585543.4A CN113282761A (en) | 2021-05-27 | 2021-05-27 | Department information pushing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113282761A true CN113282761A (en) | 2021-08-20 |
Family
ID=77282119
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110585543.4A Pending CN113282761A (en) | 2021-05-27 | 2021-05-27 | Department information pushing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113282761A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108231174A (en) * | 2017-12-11 | 2018-06-29 | 浪潮软件集团有限公司 | Method, device and system for determining department |
| CN111382275A (en) * | 2018-12-28 | 2020-07-07 | 医渡云（北京）技术有限公司 | Construction method, device and medium of medical knowledge graph and electronic equipment |
| CN111599488A (en) * | 2020-05-19 | 2020-08-28 | 万达信息股份有限公司 | Intelligent inquiry implementing method, system and storage medium |
| CN111813957A (en) * | 2020-07-14 | 2020-10-23 | 深圳中兴网信科技有限公司 | Medical diagnosis guiding method based on knowledge graph and readable storage medium |
| CN112035674A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Diagnosis guide data acquisition method and device, computer equipment and storage medium |
| CN112035635A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Medical field intention recognition method, device, equipment and storage medium |
-
2021
- 2021-05-27 CN CN202110585543.4A patent/CN113282761A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108231174A (en) * | 2017-12-11 | 2018-06-29 | 浪潮软件集团有限公司 | Method, device and system for determining department |
| CN111382275A (en) * | 2018-12-28 | 2020-07-07 | 医渡云（北京）技术有限公司 | Construction method, device and medium of medical knowledge graph and electronic equipment |
| CN111599488A (en) * | 2020-05-19 | 2020-08-28 | 万达信息股份有限公司 | Intelligent inquiry implementing method, system and storage medium |
| CN111813957A (en) * | 2020-07-14 | 2020-10-23 | 深圳中兴网信科技有限公司 | Medical diagnosis guiding method based on knowledge graph and readable storage medium |
| CN112035674A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Diagnosis guide data acquisition method and device, computer equipment and storage medium |
| CN112035635A (en) * | 2020-08-28 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Medical field intention recognition method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108986908B (en) | Method and device for processing inquiry data, computer equipment and storage medium | |
| CN106919793B (en) | Data standardization processing method and device for medical big data | |
| CN108877921B (en) | Medical intelligent triage method and medical intelligent triage system | |
| CN110289068A (en) | Drug recommended method and equipment | |
| US11232856B2 (en) | Methods for automatic cohort selection in epidemiologic studies and clinical trials | |
| CN112786194A (en) | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence | |
| CN109920540A (en) | Construction method, device and the computer equipment of assisting in diagnosis and treatment decision system | |
| CN109065172B (en) | Disease information acquisition method and device, computer equipment and storage medium | |
| CN109599185A (en) | Disease data processing method, device, electronic equipment and computer-readable medium | |
| US20190057773A1 (en) | Method and system for performing triage | |
| CN110910976A (en) | Medical record detection method, device, equipment and storage medium | |
| CN111710420A (en) | Complication morbidity risk prediction method, system, terminal and storage medium based on electronic medical record big data | |
| WO2022267678A1 (en) | Video consultation method and apparatus, device and storage medium | |
| CN111933291A (en) | Medical information recommendation device, method, system, equipment and readable storage medium | |
| CN110619959A (en) | Intelligent triage method and system | |
| CN112614578B (en) | Doctor intelligent recommendation method and device, electronic equipment and storage medium | |
| CN111666477A (en) | Data processing method and device, intelligent equipment and medium | |
| CN112634889B (en) | Electronic case input method, device, terminal and medium based on artificial intelligence | |
| CN112183026A (en) | ICD (interface control document) encoding method and device, electronic device and storage medium | |
| CN108899063B (en) | Physical examination data processing method and device, computer equipment and storage medium | |
| CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
| CN113409907A (en) | Intelligent pre-inquiry method and system based on Internet hospital | |
| CN111429985B (en) | Electronic medical record data processing method and system | |
| CN112201359A (en) | Artificial intelligence-based critical illness inquiry data identification method and device | |
| CN113658712A (en) | Doctor-patient matching method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |