wherein T (x, y) represents a degree of matching, x_iRepresenting the i-th disease entity, y, of said disease entities screened_iRepresenting the ith disease entity in the disease entity dictionary library.

In order to solve the above problems, the present invention also provides a department recommendation device, comprising:

the cleaning module is used for cleaning the inquiry data in the inquiry text to obtain a standard text;

the screening module is used for identifying the disease entities in the standard text by using the pre-trained disease entity identification model, constructing an entity relation map for the identified disease entities, and screening the disease entities meeting preset conditions from the identified disease entities according to the entity relation map to obtain a first disease entity;

the selecting module is used for screening disease entities from the standard text by utilizing a pre-constructed disease entity regular expression, calculating the matching degree of the screened disease entities and the disease entities in a preset disease entity dictionary library, and selecting the disease entities with the matching degree larger than a preset threshold value from the screened disease entities to obtain second disease entities;

the summarizing module is used for respectively reducing dimensions of the first disease entity and the second disease entity, summarizing the first disease entity and the second disease entity after dimension reduction to obtain a target disease entity;

and the calculation module is used for calculating the association degree of the target disease entity and departments in a pre-constructed medical department library, and selecting the departments with the association degree larger than the preset association degree from the medical departments to obtain the target departments.

In order to solve the above problem, the present invention also provides an electronic device, including:

at least one processor; and the number of the first and second groups,

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

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to implement the department recommendation method described above.

In order to solve the above problem, the present invention also provides a computer-readable storage medium having at least one computer program stored therein, the at least one computer program being executed by a processor in an electronic device to implement the department recommendation method described above.

According to the embodiment of the invention, firstly, the data in the obtained inquiry text is cleaned to obtain the standard text, so that the processing speed of the data in the subsequent inquiry text can be improved; secondly, the disease entities are respectively screened from the standard text by utilizing the pre-trained disease entity recognition model and the disease entity regular expression, so that the comprehensiveness of the disease entity acquisition is guaranteed, the problems that medical information is not matched in the disease entity process and noise data in the text is difficult to distinguish are solved, and the recommendation accuracy of an inquiry department is improved; furthermore, the embodiment of the invention improves the speed of subsequent calculation by performing dimension reduction on the disease entity, and selects departments with the association degree greater than the preset association degree from the medical departments according to the association degree of the target disease entity and the departments in the medical department library, so as to further improve the accuracy of the recommendation of the inquiry department. Therefore, the department recommendation method, the department recommendation device, the electronic equipment and the storage medium provided by the invention can reduce the difficulty of department recommendation.

Drawings

Fig. 1 is a schematic flow chart of a department recommendation method according to an embodiment of the present invention;

FIG. 2 is a detailed flowchart of one step of the department recommendation method provided in FIG. 1 according to a first embodiment of the present invention;

FIG. 3 is a block diagram of a department recommendation device according to an embodiment of the present invention;

fig. 4 is a schematic internal structural diagram of an electronic device for implementing a department recommendation method according to an embodiment of the present invention;

the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The embodiment of the application provides a department recommending method. The execution subject of the department recommendation method includes, but is not limited to, at least one of the electronic devices that can be configured to execute the method provided by the embodiment of the present application, such as a server, a terminal, and the like. In other words, the department recommendation method may be performed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

Fig. 1 is a schematic flow chart of a department recommendation method according to an embodiment of the present invention. In an embodiment of the present invention, the department recommendation method includes:

and S1, cleaning the inquiry data in the inquiry text to obtain a standard text.

In this embodiment of the present invention, the inquiry text may be understood as a summary of data generated in a business scenario, for example, a summary of basic data and behavior data of a user in a medical inquiry scenario, where the inquiry data refers to medical data input by the user and needs to be consulted, and includes: disease symptoms, disease category, and disease name, among others. Further, it should be understood that data generated in an actual service scene are complex and large in data amount, and in order to better analyze and process the inquiry text, the inquiry data in the inquiry text is cleaned by the method, so that useless data of the inquiry text are screened out, and the efficiency of subsequent text processing is improved.

In detail, the cleaning of the inquiry data in the inquiry text to obtain a standard text includes: performing duplication removal operation on the inquiry data in the inquiry text, and detecting whether a data missing value exists in the inquiry text after duplication removal; if no data missing value exists, the query text after duplication removal is used as a standard text; and if the data missing value exists, performing data filling on the data missing value to obtain a standard text.

In detail, the performing a deduplication operation on the inquiry data in the inquiry text includes: and calculating the similarity of any two pieces of inquiry data in the inquiry text, if the similarity is greater than the preset similarity, simultaneously keeping any two pieces of inquiry data in the inquiry text, and if the similarity is not greater than the preset similarity, deleting one piece of inquiry data of any two pieces of inquiry data in the inquiry text.

It should be noted that, before calculating the similarity between any two pieces of inquiry data in the inquiry text, the embodiment of the present invention further includes: and converting the inquiry data in the inquiry text into a corresponding hash value by using a hash algorithm so as to realize the calculation of the similarity of the subsequent inquiry data.

In an alternative embodiment, the similarity between any two pieces of inquiry data in the inquiry text is calculated by the following method:

wherein d represents the similarity of any two inquiry data in the inquiry text, and w_1jAnd w_2jRepresenting the hash value of any two pieces of interrogation data in the interrogation text.

Further, it should be understood that in an actual service scenario, when a user performs medical consultation, there may be a situation that input data is missing, for example, one or more identity cards or mobile phone numbers of the user are missing, which causes incomplete user information, and thus affects the integrity of the whole inquiry text.

In an alternative embodiment, the detection of the missing data value may be implemented by a detection function in a currently known missing data value detection tool, such as a mismap function detection function in an Amelia package tool.

In an optional embodiment, the populating the data missing value includes: acquiring a missing position of data to be filled, presetting a filling parameter at the missing position, calculating the missing value probability of the filling parameter, and obtaining a data missing value corresponding to filling according to the missing position, the filling parameter and the missing value probability. Optionally, the missing data value is filled by using the following formula:

wherein L (θ) represents a filled data missing value, x_iIndicating the missing position of the ith missing data value, theta indicating the filling parameter corresponding to the filled missing data value, n indicating the number of the inquiry data in the inquiry text after the duplication removal, and p (x)_i| θ) represents the missing value probability of the padding parameter.

S2, recognizing the disease entities in the standard text by using the pre-trained disease entity recognition model, constructing an entity relation map for the recognized disease entities, and screening the recognized disease entities to obtain the first disease entity, wherein the disease entities meet preset conditions according to the entity relation map.

In an embodiment of the present invention, the disease entity identification model includes a BERT neural network, configured to identify a disease entity in the standard text, where the disease entity refers to a disease name and a disease symptom in the inquiry text, and the disease name includes: gallstones, pulmonary nodules, cold, fever, and the like, including disease symptoms; nausea, dizziness, and weakness. In order to better understand the target departments to be queried in the inquiry text, the embodiment of the invention identifies the disease entities in the standard text through the pre-trained disease entity identification model so as to guarantee the premise of matching of the subsequent target departments.

In detail, referring to fig. 2, the identifying the disease entity in the standard text by using the pre-trained disease entity identification model includes:

s20, carrying out position vector coding on the characters in the standard sample by using a coding layer in the disease entity recognition model to generate a character vector;

s21, extracting a characteristic sequence of the character vector by using a feedforward attention mechanism in the disease entity recognition model to obtain a characteristic sequence vector;

and S22, carrying out disease entity recognition on the characteristic sequence vector by using a disease entity recognition module in the disease entity recognition model to obtain a disease entity.

In an alternative embodiment, the encoding layer includes Embedding, and the S20 includes: index coding is carried out on the characters in the standard sample by utilizing the coding layer to obtain a character coding index; converting the characters into corresponding character vectors by utilizing the coding layer to obtain initial character vectors; and combining the character coding index and the character vector to generate a character vector.

In an alternative embodiment, the feed forward attention mechanism comprises: a self-attention module, a convolution module, and an encoder, the S21 including: and querying the character vector by using a self-attention module in the feedforward attention mechanism, performing feature extraction on the queried character vector by using a convolution module in the feedforward attention mechanism to obtain a feature character vector, and extracting an information sequence of the feature character vector by using an encoder in the feedforward attention mechanism to obtain a feature sequence vector.

In an alternative embodiment, the disease entity identification module comprises: a full connectivity layer and an activation function, the S22 including: and detecting disease entity position information in the characteristic sequence vector by using the full connection layer, and outputting the disease entity position information by using the activation function to obtain the disease entity.

It should be noted that the training process of the disease entity recognition model belongs to the current mature technology, and is not further described here.

Further, it should be understood that, in the identified disease entities, certain entity relationships may exist, such as correspondence between disease symptoms and disease names (for example, cold contains weakness), and in order to more intuitively understand the relationships between the identified disease entities, the embodiment of the present invention constructs an entity relationship map for the identified disease entities, and in detail, the constructing an entity relationship map for the identified disease entities includes: performing relation vector modeling on the identified disease entity by using a translation model to obtain an entity relation map vector space; and converting the entity relationship map vector space into an entity relationship map of a visual interface to obtain the entity relationship map.

Wherein the utilizing translation model (Trans) comprises: multivariate relational data embedding (TransE for short), knowledge embedding into a hyperplane (TransH for short), entity and relationship separate embedding (TransR), embedding through a dynamic mapping matrix (TransD), and adaptive metric function (TransA). It should be noted that the implementation of entity-relationship vector modeling using the Trans is a current mature technology and is not further described here.

In an alternative embodiment, the transformation of the visualization interface of the entity relationship graph vector space is implemented by the currently known TensorBoard tool.

Further, in the embodiment of the present invention, the association relationship between disease entities may be determined through the entity relationship map, so that in the embodiment of the present invention, a disease entity meeting a preset condition is screened from the identified disease entities according to the entity relationship map, and the first disease entity is obtained. The preset condition may be set according to an actual service scenario, for example, whether a disease entity has two or more associated disease entities is set, and if so, the corresponding disease entity is screened out to generate the first disease.

In an optional embodiment, the screening of the disease entity may be implemented by a currently preset entity screening script, and the preset entity screening script may be compiled by a currently known JavaScript scripting language.

S3, screening disease entities from the standard text by using the pre-constructed regular expression of the disease entities, calculating the matching degree of the screened disease entities and the disease entities in a preset disease entity dictionary library, and selecting the disease entities with the matching degree larger than a preset threshold value from the screened disease entities to obtain second disease entities.

In the embodiment of the present invention, the pre-constructed regular expression of the disease Entity may be constructed by a currently known Entity naming Recognition (NER) tool, for example, words describing a main disease Entity with high frequency are found according to statistical analysis or a disease Entity automatically selected by a user at the front end of the system is found.

Further, it should be understood that in an actual service scenario, due to different factors such as different expression habits of users, the disease entities extracted through the regular expression of the disease entities do not meet the disease entities of the standard in the industry, and therefore, in the embodiment of the present invention, the second disease entity is obtained by calculating the matching degree between the screened disease entities and the disease entities in the preset disease entity dictionary library, and selecting the disease entities with the matching degree greater than the preset threshold value from the screened disease entities, so as to ensure the extraction accuracy of the disease entities. Optionally, the disease entity dictionary database is constructed by a database and is used for realizing rapid storage and reading of data.

In an alternative embodiment, the matching degree of the screened disease entity with the disease entity in the preset disease entity dictionary library is calculated by the following method:

In an optional embodiment, the preset threshold is 0.9, and may also be set according to an actual service scenario.

S4, performing dimensionality reduction on the first disease entity and the second disease entity respectively, and summarizing the first disease entity and the second disease entity subjected to dimensionality reduction to obtain a target disease entity.

In an embodiment of the present invention, dimension reduction is performed on the first disease entity and the second disease entity to map the first disease entity and the second disease entity into an interval [0,1], so as to increase the processing speed of subsequent disease entities.

In an alternative embodiment, the dimension reduction of the first disease entity is performed using the following method:

x'＝(X-X_min)/(X_max-X_min)

wherein X' represents the first disease entity after dimensionality reduction, X represents the first disease entity, X _ max represents the largest-dimensional disease entity of the first disease entities, and X _ min represents the smallest-dimensional disease entity of the first disease entities.

Further, the dimension reduction method of the second disease entity may refer to the dimension reduction method of the first disease entity, which is not further described herein.

Further, the embodiment of the invention summarizes the first disease entity and the second disease entity after dimensionality reduction to obtain a target disease entity, so as to ensure information comprehensiveness of the disease entity when subsequently matched with a target department, and improve accuracy of matching of the target department.

Further, to ensure reusability and privacy of the target disease entity, the target disease entity may also be stored in a blockchain node.

S5, calculating the association degree of the target disease entity and departments in a pre-constructed medical department library, and selecting the departments with the association degree larger than the preset association degree from the medical departments to obtain the target departments.

In an embodiment of the present invention, the department in the medical department library refers to doctor diagnosis and treatment position information in the medical field, for example: skin department, chest examination department, electrocardiogram department, etc., the medical department library is also constructed based on the database, which facilitates the rapid access of data.

Further, in the embodiment of the present invention, the target department is obtained by calculating the association degree between the target disease entity and the departments in the medical department library, and selecting the department with the association degree greater than the preset association degree from the medical departments, so as to realize the target department matching of the disease entity. The calculation method of the association degree may refer to the calculation method of the matching degree in S3, which is not further described herein, and the optional preset association degree is 0.85, which may also be set according to an actual service scenario.

Fig. 3 is a functional block diagram of the department recommendation device of the present invention.

The department recommendation device 100 of the present invention can be installed in an electronic device. According to the realized functions, the department recommending device can comprise a cleaning module 101, a screening module 102, a selecting module 103, a summarizing module 104 and a calculating module 105. A module according to the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.

In the present embodiment, the functions regarding the respective modules/units are as follows:

the cleaning module 101 is configured to clean the inquiry data in the inquiry text to obtain a standard text;

the screening module 102 is configured to identify a disease entity in the standard text by using a pre-trained disease entity identification model, construct an entity relationship map for the identified disease entity, and screen a disease entity meeting a preset condition from the identified disease entity according to the entity relationship map to obtain a first disease entity;

the selecting module 103 is configured to screen disease entities from the standard text by using a pre-constructed disease entity regular expression, calculate matching degrees between the screened disease entities and disease entities in a preset disease entity dictionary library, and select a disease entity with the matching degree greater than a preset threshold value from the screened disease entities to obtain a second disease entity;

the summarizing module 104 is configured to perform dimension reduction on the first disease entity and the second disease entity respectively, and summarize the dimension-reduced first disease entity and second disease entity to obtain a target disease entity;

the calculating module 105 is configured to calculate a degree of association between the target disease entity and departments in a pre-constructed medical department library, and select a department with the degree of association greater than a preset degree of association from the medical departments to obtain a target department.

In detail, when the department recommending device 100 in the embodiment of the present invention is used, the same technical means as the department recommending method described in fig. 1 and fig. 2 are used, and the same technical effects can be produced, which is not described herein again.

Fig. 4 is a schematic structural diagram of an electronic device for implementing a department recommendation method according to the present invention.

The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a department recommendation program 12, stored in the memory 11 and executable on the processor 10.

The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of the department recommendation program 12, but also to temporarily store data that has been output or is to be output.

The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., executing a department recommendation program 12, etc.) stored in the memory 11 and calling data stored in the memory 11.

The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.

Fig. 4 only shows an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 4 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.

For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.

Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.

It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.

The department recommendation program 12 stored in the memory 11 of the electronic device 1 is a combination of a plurality of programs, which when executed in the processor 10, may implement:

cleaning the inquiry data in the inquiry text to obtain a standard text;

Specifically, the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the foregoing program, which is not described herein again.

Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-volatile computer-readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).

The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:

cleaning the inquiry data in the inquiry text to obtain a standard text;

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.

The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an 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.

Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A department recommendation method, the method comprising:

cleaning the inquiry data in the inquiry text to obtain a standard text;

2. The department recommendation method of claim 1, wherein said cleaning the inquiry data in said inquiry text to obtain a standard text comprises:

3. The department recommendation method of claim 2, wherein said performing deduplication operations on the interrogation data in the interrogation text comprises:

4. The department recommendation method of claim 1, wherein said identifying disease entities in said standard text using a pre-trained disease entity recognition model comprises:

5. The departmental recommendation method of claim 4, wherein said extracting feature sequences from said character vectors using a feed forward attention mechanism in said disease entity recognition model to obtain feature sequence vectors comprises:

6. The department recommendation method of any of claims 1-5, wherein said constructing an entity relationship map of said identified disease entities comprises:

7. The department recommendation method of claim 1, wherein said calculating a match between said screened disease entity and a disease entity in a predetermined dictionary of disease entities comprises:

calculating the matching degree by using the following method:

8. A department recommendation device, the device comprising:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

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

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the department recommendation method of any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the department recommendation method of any one of claims 1 to 7.