Word segmentation method, device and electronic equipment for electronic medical records

Abstract

The present invention provides a word segmentation method, device and electronic device for electronic medical records, the method comprising: obtaining an initial word segmentation set corresponding to an initial sentence in an electronic medical record, judging whether an initial symptom name contains words representing a body part, if so, performing a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name, and determining a target symptom name corresponding to the initial sentence and a target body part name corresponding to the initial sentence according to the first word segmentation set and a medical word library. On the basis of obtaining the initial word segmentation set, the present invention judges if the initial symptom name in the initial word segmentation set contains words representing a body part, further word segmenting the initial symptom name, further extracting the words representing a body part in the initial symptom name, obtaining an accurate target symptom name and a target body part name, avoiding the situation where the word segmentation result is inaccurate due to the existence of compound words, and improving the accuracy of the word segmentation result.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a word segmentation method, device and electronic equipment for electronic medical records. Background Art

[0002] In the medical field, entity extraction of symptoms plays a very important role in the effective decomposition of electronic medical records. The existing extraction process is to use word segmentation tools and domain-specific vocabulary to extract symptom information from electronic medical records, and determine the location attributes based on the symptom information.

[0003] However, some compound words often do not exist in the vocabulary, which will lead to incorrect word segmentation results of the sentence, and incorrect word segmentation results will affect the accuracy of the patient's condition assessment results. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a word segmentation method, device and electronic device for electronic medical records to improve the accuracy of word segmentation results.

[0005] In a first aspect, an embodiment of the present invention provides a word segmentation method for an electronic medical record, which is applied to an electronic device, and the method includes: obtaining an initial word segmentation set corresponding to an initial sentence in an electronic medical record to be processed; wherein the initial word segmentation set includes an initial symptom name and an initial part name corresponding to the initial sentence; judging whether the initial symptom name contains a word representing a part, and if so, performing a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name; wherein the text length of each first word included in the first word segmentation set is less than the text length of the initial symptom name; determining a target symptom name corresponding to the initial sentence and a target part name corresponding to the initial sentence according to the first word segmentation set and a pre-stored medical vocabulary; wherein the pre-stored medical vocabulary includes symptom information and non-specific symptom information, and the non-specific symptom information is used to represent the patient's feelings about the disease.

[0006] Furthermore, the above-mentioned step of obtaining an initial word segmentation set corresponding to the initial sentence in the electronic medical record to be processed includes: obtaining the initial sentence from the electronic medical record to be processed; performing structured processing on the initial sentence to obtain an initial word segmentation set corresponding to the initial sentence; wherein the structured processing is used to extract text content that matches multiple preset field types from the initial sentence.

[0007] Furthermore, the above-mentioned step of performing a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name includes: performing multiple segmentation operations at different positions on the initial symptom name; and determining the first word segmentation set corresponding to the initial symptom name based on the segmentation results of the segmentation operation.

[0008] Furthermore, the above-mentioned step of determining the first set of segmented words corresponding to the initial symptom name based on the segmentation results of the segmentation operation includes: traversing the segmented words in the segmentation results, and determining the segmented words matching the medical vocabulary as target segmented words; and determining the first set of segmented words corresponding to the initial symptom name based on the target segmented words.

[0009] Furthermore, the above step of determining the target symptom name corresponding to the initial sentence based on the first word segmentation set and the medical vocabulary includes: reversely traversing the first word in the first word segmentation set, and determining the first word that matches the symptom information or non-specific symptom information in the medical vocabulary as the target symptom name corresponding to the initial sentence.

[0010] Furthermore, the above step of determining the target part name corresponding to the initial sentence based on the first participle set and the medical vocabulary includes: determining the first part name contained in the first participle set based on the first participle set and the target symptom name; determining the target part name corresponding to the initial sentence based on the first part name and the initial part name.

[0011] Furthermore, the above-mentioned step of determining the first part name contained in the first participle set based on the first participle set and the target symptom name includes: deleting the first word corresponding to the target symptom name in the first participle set; splicing the remaining first words in the first participle set, and determining the splicing result as the first part name contained in the first participle set.

[0012] In a second aspect, an embodiment of the present invention further provides a word segmentation device for electronic medical records, the device comprising: an acquisition module, used to acquire an initial word segmentation set corresponding to an initial sentence in an electronic medical record to be processed; wherein the initial word segmentation set includes an initial symptom name and an initial part name corresponding to the initial sentence; a first word segmentation module, used to determine whether the initial symptom name contains a word representing a part, and if so, perform a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name; wherein the text length of each first word included in the first word segmentation set is less than the text length of the initial symptom name; a determination module, used to determine the target symptom name corresponding to the initial sentence and the target part name corresponding to the initial sentence based on the first word segmentation set and a pre-stored medical vocabulary; wherein the pre-stored medical vocabulary includes symptom information and non-specific symptom information, and the non-specific symptom information is used to represent the patient's perception of the disease.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the electronic medical record word segmentation method of the first aspect mentioned above.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the electronic medical record word segmentation method of the first aspect mentioned above.

[0015] Compared with the prior art, the present invention has the following beneficial effects:

[0016] The above-mentioned electronic medical record word segmentation method, device and electronic device provided by the embodiment of the present invention first obtains the initial word segmentation set corresponding to the initial sentence in the electronic medical record, and determines whether the initial symptom name contains words representing the body part. If so, the initial symptom name is subjected to the first word segmentation operation to obtain the first word segmentation set corresponding to the initial symptom name. Finally, the target symptom name corresponding to the initial sentence and the target body part name corresponding to the initial sentence are determined according to the first word segmentation set and the medical vocabulary. On the basis of obtaining the initial word segmentation set, the present invention determines if the initial symptom name in the initial word segmentation set contains words representing the body part, further segmenting the initial symptom name, further extracting the words representing the body part in the initial symptom name, and obtaining the accurate target symptom name and target body part name, thereby avoiding the situation where the word segmentation result is inaccurate due to the existence of compound words, and improving the accuracy of the word segmentation result.

[0017] Other features and advantages of the present disclosure will be set forth in the following description, or some features and advantages may be inferred or unambiguously determined from the description, or may be learned by implementing the above-mentioned technology of the present disclosure.

[0018] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic diagram of the structure of an electronic system provided by an embodiment of the present invention;

[0021] Figure 2 A flowchart of a word segmentation method for electronic medical records provided by an embodiment of the present invention;

[0022] Figure 3A flowchart of another electronic medical record word segmentation method provided by an embodiment of the present invention;

[0023] Figure 4 A flowchart of another electronic medical record word segmentation method provided by an embodiment of the present invention;

[0024] Figure 5 A schematic diagram of the structure of a word segmentation device for electronic medical records provided by an embodiment of the present invention;

[0025] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In the prior art, the usual method for word segmentation of medical electronic medical records is: pre-processing the text to be processed according to the business scenario to obtain the input text; using the word segmentation tool + vocabulary method or the word segmentation model trained by statistical methods or neural networks, the input text is segmented and the segmentation results are marked.

[0028] Generally speaking, medical vocabulary contains relatively standard words such as symptoms, drugs, signs, and surgical names. However, since the vocabulary cannot contain all words such as symptoms, such as common symptom compound words, there is a problem that the part determined by logical judgment does not match the current symptom name.

[0029] In order to solve the above problems existing in the prior art, the embodiments of the present invention provide a word segmentation method, device and electronic device for electronic medical records to improve the accuracy of word segmentation results.

[0030] Reference Figure 1 The electronic system 100 is a schematic diagram of the structure of the electronic system 100. The electronic system can be used to implement the electronic medical record word segmentation method and device of the embodiment of the present invention.

[0031] like Figure 1 The electronic system 100 includes one or more processing devices 102, one or more storage devices 104, an input device 106, an output device 108, and one or more data acquisition devices 110. These components are interconnected via a bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that Figure 1 The components and structure of the electronic system 100 shown are merely exemplary and not limiting. The electronic system may also have other components and structures as required.

[0032] The processing device 102 can be a server, an intelligent terminal, or a device including a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities. It can process data of other components in the electronic system 100 and can also control other components in the electronic system 100 to perform the word segmentation function of the electronic medical record.

[0033] The storage device 104 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processing device 102 may run the program instructions to implement the client functions and / or other desired functions in the embodiments of the present invention (implemented by the processing device) described below. Various applications and various data, such as various data used and / or generated by the application, may also be stored in the computer-readable storage medium.

[0034] The input device 106 may be a device used by a user to input instructions, and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.

[0035] The output device 108 may output various information (eg, images or sounds) to the outside (eg, a user), and may include one or more of a display, a speaker, and the like.

[0036] The data acquisition device 110 can acquire data to be processed and store the data in the storage device 104 for use by other components.

[0037] Exemplarily, the components in the word segmentation method, device and electronic device for implementing the electronic medical record according to the embodiment of the present invention can be integrated or dispersed, such as integrating the processing device 102, the storage device 104, the input device 106 and the output device 108 into one body, and setting the data acquisition device 110 at a designated location where data can be collected. When the components in the above electronic system are integrated, the electronic system can be implemented as an intelligent terminal such as a camera, a smart phone, a tablet computer, a computer, a vehicle-mounted terminal, etc.

[0038] Figure 2A flowchart of a word segmentation method for electronic medical records provided by an embodiment of the present invention, the method is applied to electronic equipment, see Figure 2 , the method comprises the following steps:

[0039] S202: Acquire an initial segmentation set corresponding to an initial sentence in the electronic medical record to be processed; wherein the initial segmentation set includes an initial symptom name and an initial part name corresponding to the initial sentence;

[0040] In this step, an initial sentence is obtained from the electronic medical record to be processed, and an initial word segmentation set corresponding to the initial sentence is obtained. The initial sentence is a text in the electronic medical record involving patient disease information, and multiple initial sentences can be obtained from one electronic medical record.

[0041] The initial word segmentation set of the initial sentence can be a set of words obtained by pre-segmenting the initial sentence. Specifically, it can be a set of word segments obtained using a word segmentation tool, a set of word segments obtained through a natural text segmentation processing algorithm, or a set of word segments obtained by structured processing of the initial sentence.

[0042] S204: Determine whether the initial symptom name contains a word representing a body part; if so, perform a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name; wherein the text length of each first word contained in the first word segmentation set is shorter than the text length of the initial symptom name;

[0043] When a certain part is closely related to the symptom set, the initial participle set obtained by the word segmentation method and the participle set corresponding to the symptom name may contain unnecessary part information. For example, an initial sentence is "pain in the left lower limb and right upper limb". After the word segmentation tool, the word segmentation result obtained is: symptom "pain in the right upper limb", part "left lower limb". Obviously, this is an unreasonable word segmentation result. In order to solve the problem of compound words in the word segmentation results, the embodiment of the present invention first determines whether the initial symptom name contains words representing the part, for example, a semantic matching algorithm can be used to calculate text similarity.

[0044] If it is determined that the first symptom contains words representing a body part, the initial symptom name is further segmented, that is, a first segmentation operation is performed to obtain a first segmentation set corresponding to the initial symptom name. The segmentation method may be the same as or different from the segmentation method for obtaining the initial segmentation set, and the embodiment of the present invention is not limited to this.

[0045] S206: Determine the target symptom name corresponding to the initial sentence and the target part name corresponding to the initial sentence based on the first word segmentation set and the pre-stored medical vocabulary; wherein the pre-stored medical vocabulary includes symptom information and non-specific symptom information, and the non-specific symptom information is used to characterize the patient's feelings about the disease.

[0046] The medical vocabulary is a database including medical information obtained through electronic devices, and the medical information includes common symptom names, body part names, etc. When doctors actually generate cases, they usually combine body parts with non-specific symptoms to describe the patient's condition, such as numbness of the upper limbs. Therefore, in order to better distinguish similar non-specific symptom information, in the embodiment of the present invention, the medical vocabulary is first expanded, and entities corresponding to non-specific symptoms, i.e., fields, are added to the medical vocabulary. Specifically, a new entity name can be added to the vocabulary: non-specific symptoms. The characteristics of this type of words are usually that the part + non-specific symptoms is a symptom name, such as: "pain, swelling, numbness, swelling, lump", etc. The purpose of adding this type of words is to be able to distinguish them from symptom words or fine-grained results.

[0047] Based on the expanded medical vocabulary, the parts and symptoms / non-specific symptom information in the first word segmentation set are further segmented to obtain more accurate target symptom names and target part names.

[0048] The above-mentioned word segmentation method of the electronic medical record provided by the embodiment of the present invention first obtains the initial word segmentation set corresponding to the initial sentence in the electronic medical record, and determines whether the initial symptom name contains words representing the body part. If so, the first word segmentation operation is performed on the initial symptom name to obtain the first word segmentation set corresponding to the initial symptom name. Finally, according to the first word segmentation set and the medical vocabulary, the target symptom name corresponding to the initial sentence and the target body part name corresponding to the initial sentence are determined. On the basis of obtaining the initial word segmentation set, the present invention determines if the initial symptom name in the initial word segmentation set contains words representing the body part, further segmenting the initial symptom name, further extracting the words representing the body part in the initial symptom name, and obtaining accurate target symptom names and target body part names, thereby avoiding the situation where the word segmentation results are inaccurate due to the existence of compound words, and improving the accuracy of the word segmentation results.

[0049] In order to improve the accuracy of word segmentation results, the present invention further provides another electronic medical record word segmentation method based on the above embodiment, such as Figure 3 As shown, the method focuses on how to obtain an initial word segmentation set and how to obtain a first word segmentation set. The method specifically includes:

[0050] S302: Obtaining an initial statement from the electronic medical record to be processed;

[0051] S304: Performing structural processing on the initial sentence to obtain an initial word segmentation set corresponding to the initial sentence; wherein the structural processing is used to extract text content matching multiple preset field types from the initial sentence;

[0052] After the initial sentence is structured, a data set is obtained. Each word in the set includes the category of the word and the text content corresponding to the word. For example, after the initial sentence "A dark red rash appeared on the face on October 2" is structured, the first word segmentation result is:

[0053] Time: October 2;

[0054] Location: Face

[0055] Symptoms: Dark red rash.

[0056] S306: Determine whether the initial symptom name contains a word representing a body part.

[0057] S308: If yes, perform multiple segmentation operations at different positions on the initial symptom name;

[0058] When the symptom name is a compound word, the symptom name will include words that represent the body part. For example, the first symptom obtained by segmentation, "right upper limb pain", includes the "right upper limb" that represents the body part. In this case, the initial symptom name needs to be further segmented. In the embodiment of the present invention, the word formation function of the word segmentation tool jieba is used to perform different word formation processing on the first symptom. For example, for "dark red rash", possible word formation includes: dark red, red, dark red rash, red rash, rash.

[0059] S310: Determine a first segmentation set corresponding to the initial symptom name according to the segmentation result of the segmentation operation.

[0060] In some possible implementations, this step can be specifically determined by the following method:

[0061] (1) traversing the segmentation words in the segmentation results, and determining the segmentation words that match the medical vocabulary as the target segmentation words;

[0062] For each segmented word, a match is performed in the medical vocabulary. When a matching word is found, the word is determined as the target segmented word. The relevance between the segmented word and the words contained in the medical vocabulary can be calculated respectively, and the words with a relevance greater than a preset relevance threshold are determined as the target segmented words. Continuing with the above example, after searching, it is determined that "rash" matches the words in the medical vocabulary, and the target segmented word is determined to be rash.

[0063] (2) According to the target segmented words, determine the first segmented word set corresponding to the initial symptom name.

[0064] Furthermore, the words in the initial symptom name other than the target segmentation words are determined as other words, and the set of the target segmentation words and the other words is the first segmentation set corresponding to the initial symptom name. For example, "dark red" in the above words is determined as other words, so that the first segmentation set of the first symptom is: dark red, rash.

[0065] S312: Determine the target symptom name corresponding to the initial sentence and the target part name corresponding to the initial sentence according to the first word segmentation set and the pre-stored medical vocabulary.

[0066] The above embodiment of the present invention obtains an accurate first segmentation set by further fine-grained segmentation of the first symptom and matches each segmented word with a medical vocabulary, thereby ensuring the accuracy of the target symptom name and target part name obtained based on the first segmentation set.

[0067] After obtaining the first segmented word set, it is necessary to further extract the accurate target symptom name and target part name from the first segmented word set. Therefore, the embodiment of the present invention also provides another electronic medical record segmentation method, such as Figure 4 As shown, the method includes:

[0068] S402: Obtaining an initial word segmentation set corresponding to an initial sentence in the electronic medical record to be processed;

[0069] S404: Determine whether the initial symptom name contains a word representing a body part, and if so, perform a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name;

[0070] The above steps and Figure 2 Steps S202-S204 in the illustrated embodiment are the same and will not be described in detail herein.

[0071] S406: Reversely traverse the first word in the first word segmentation set, and determine the first word that matches the symptom information or non-specific symptom information in the medical word library as the target symptom name corresponding to the initial sentence;

[0072] Each first word in the first word segmentation set is traversed in reverse order and matched with the symptom information or non-specific symptom information in the medical word library. If a matching word is found, the word is determined as the final target symptom name.

[0073] S408: Determine a first part name included in the first participle set according to the first participle set and the target symptom name;

[0074] S410: Determine a target part name corresponding to the initial sentence according to the first part name and the initial part name.

[0075] In some examples, this may specifically include:

[0076] (1) deleting the first word corresponding to the target symptom name in the first word segmentation set;

[0077] (2) The remaining first words in the first word segmentation set are concatenated, and the concatenated result is determined as the first part name included in the first word segmentation set.

[0078] The method provided by the embodiment of the present invention is explained below in combination with actual application scenarios:

[0079] Step 1: First, extract the symptoms and their location attributes, for example, obtain an initial segmentation set through a segmentation tool, such as {"symptom name": "right lower limb pain", "symptom location": "left upper limb"}.

[0080] Step 2: After judging, if it is found that the symptom name has a part name, then check the first participle set corresponding to the symptom word;

[0081] For example, the first participle set of "right lower limb pain" is: [('right upper limb','organ'),('pain','non-specific symptoms')],

[0082] Step 3: If "symptom name" or "non-specific symptom name" exists in the first word segmentation set, the name under the "symptom name" field is changed to a word included in the first word segmentation set;

[0083] That is, pain is identified as the target symptom name.

[0084] In summary, after modification, the corresponding result of information extraction is {"symptom name": "pain", "symptom location": "right lower limb left upper limb"}, and a reasonable word segmentation result is obtained.

[0085] By replacing the words in the original symptom name field with the words in the first word segmentation set, the final word segmentation result is more accurate.

[0086] In summary, it can be found that the method mentioned in the present invention, compared with the model training method, can accurately extract the symptom name and its location attributes at a lower cost, and also greatly reduces the dependence on the vocabulary. This method can also be extended to the extraction of attribute information of entities such as diseases, surgeries, and examinations in medical data.

[0087] Based on the above method embodiment, the present invention also provides a word segmentation device for electronic medical records, see Figure 5 As shown, the device comprises:

[0088] The acquisition module 502 is used to acquire an initial segmentation set corresponding to the initial sentence in the electronic medical record to be processed; wherein the initial segmentation set includes an initial symptom name and an initial part name corresponding to the initial sentence;

[0089] The first word segmentation module 504 is used to determine whether the initial symptom name contains words representing the body part. If so, perform a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name; wherein the text length of each first word included in the first word segmentation set is less than the text length of the initial symptom name;

[0090] The determination module 506 is used to determine the target symptom name corresponding to the initial sentence and the target part name corresponding to the initial sentence based on the first word segmentation set and the pre-stored medical vocabulary; wherein the pre-stored medical vocabulary includes symptom information and non-specific symptom information, and the non-specific symptom information is used to characterize the patient's feelings about the disease.

[0091] The electronic medical record word segmentation device provided by the embodiment of the present invention first obtains the initial word segmentation set corresponding to the initial sentence in the electronic medical record, and determines whether the initial symptom name contains words representing the body part. If so, the initial symptom name is subjected to a first word segmentation operation to obtain the first word segmentation set corresponding to the initial symptom name. Finally, the target symptom name corresponding to the initial sentence and the target body part name corresponding to the initial sentence are determined according to the first word segmentation set and the medical word library. On the basis of obtaining the initial word segmentation set, the present invention determines if the initial symptom name in the initial word segmentation set contains words representing the body part, further word segmentation is performed on the initial symptom name, and the words representing the body part in the initial symptom name are further extracted to obtain accurate target symptom names and target body part names, thereby avoiding the situation where the word segmentation results are inaccurate due to the existence of compound words, and improving the accuracy of the word segmentation results.

[0092] The above process of obtaining the initial word segmentation set corresponding to the initial sentence in the electronic medical record to be processed includes: obtaining the initial sentence from the electronic medical record to be processed; performing structured processing on the initial sentence to obtain the initial word segmentation set corresponding to the initial sentence; wherein the structured processing is used to extract text content matching multiple preset field types from the initial sentence.

[0093] The above process of performing the first word segmentation operation on the initial symptom name to obtain the first word segmentation set corresponding to the initial symptom name includes: performing multiple segmentation operations at different positions on the initial symptom name; and determining the first word segmentation set corresponding to the initial symptom name based on the segmentation results of the segmentation operation.

[0094] The above process of determining the first set of segmented words corresponding to the initial symptom name based on the segmentation results of the segmentation operation includes: traversing the segmented words in the segmentation results, and determining the segmented words matching the medical vocabulary as target segmented words; and determining the first set of segmented words corresponding to the initial symptom name based on the target segmented words.

[0095] The above process of determining the target symptom name corresponding to the initial sentence based on the first word segmentation set and the medical vocabulary includes: reversely traversing the first word in the first word segmentation set, and determining the first word that matches the symptom information or non-specific symptom information in the medical vocabulary as the target symptom name corresponding to the initial sentence.

[0096] The above process of determining the target part name corresponding to the initial sentence based on the first participle set and the medical vocabulary includes: determining the first part name contained in the first participle set based on the first participle set and the target symptom name; determining the target part name corresponding to the initial sentence based on the first part name and the initial part name.

[0097] The above process of determining the first part name contained in the first participle set based on the first participle set and the target symptom name includes: deleting the first word corresponding to the target symptom name in the first participle set; splicing the remaining first words in the first participle set, and determining the splicing result as the first part name contained in the first participle set.

[0098] The electronic medical record word segmentation device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for parts not mentioned in the embodiment of the above-mentioned device, reference may be made to the corresponding contents in the aforementioned electronic medical record word segmentation method embodiment.

[0099] The embodiment of the present invention further provides an electronic device, such as Figure 6 As shown, it is a schematic diagram of the structure of the electronic device, wherein the electronic device includes a processor 601 and a memory 602, the memory 602 stores computer executable instructions that can be executed by the processor 601, and the processor 601 executes the computer executable instructions to implement the above-mentioned electronic medical record segmentation method.

[0100] exist Figure 6 In the illustrated embodiment, the electronic device further includes a bus 603 and a communication interface 604 , wherein the processor 601 , the communication interface 604 and the memory 602 are connected via the bus 603 .

[0101] Among them, the memory 602 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 604 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 603 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 603 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0102] The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 601 or the instruction in the form of software. The above processor 601 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor 601 reads the information in the memory and completes the steps of the electronic medical record word segmentation method of the aforementioned embodiment in combination with its hardware.

[0103] An embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned electronic medical record word segmentation method. The specific implementation can be found in the aforementioned method embodiment, which will not be repeated here.

[0104] The electronic medical record word segmentation method, device and computer program product of the electronic device provided in the embodiments of the present invention include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments, which will not be repeated here.

[0105] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0107] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0108] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A word segmentation method for electronic medical records, characterized in that: The method is applied to an electronic device, and the method comprises: Acquire an initial segmentation set corresponding to an initial sentence in the electronic medical record to be processed; wherein the initial segmentation set includes an initial symptom name and an initial part name corresponding to the initial sentence, and determine the initial segmentation set by using a segmentation tool, a natural text segmentation processing algorithm, and structured processing of the initial sentence; Determine whether the initial symptom name contains words representing the body part; if so, perform a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name; wherein the text length of each first word contained in the first word segmentation set is less than the text length of the initial symptom name; Determine, according to the first word segmentation set and a pre-stored medical word library, a target symptom name corresponding to the initial sentence and a target part name corresponding to the initial sentence; wherein, the medical word library is expanded by adding non-specific symptoms to the medical word library, the pre-stored medical word library includes symptom information and non-specific symptom information, and the non-specific symptom information is used to characterize the patient's feelings about the disease; The step of determining the target symptom name corresponding to the initial sentence according to the first word segmentation set and the medical word library includes: reversely traversing the first word in the first word segmentation set, and determining the first word matching the symptom information or non-specific symptom information in the medical word library as the target symptom name corresponding to the initial sentence; Among them, the step of determining the target part name corresponding to the initial sentence according to the first participle set and the medical vocabulary includes: determining the first part name contained in the first participle set according to the first participle set and the target symptom name; determining the target part name corresponding to the initial sentence according to the first part name and the initial part name.

2. The method according to claim 1, characterized in that The step of obtaining an initial word segmentation set corresponding to an initial sentence in the electronic medical record to be processed includes: Obtain initial sentences from pending electronic medical records; The initial sentence is subjected to structural processing to obtain an initial word segmentation set corresponding to the initial sentence; wherein the structural processing is used to extract text content matching multiple preset field types from the initial sentence.

3. The method according to claim 1, characterized in that The step of performing a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name includes: Performing multiple segmentation operations at different positions on the initial symptom name; A first word segmentation set corresponding to the initial symptom name is determined according to the segmentation result of the segmentation operation.

4. The method according to claim 3, characterized in that The step of determining a first word segmentation set corresponding to the initial symptom name according to the segmentation result of the segmentation operation comprises: Traversing the segmented words in the segmentation result, and determining the segmented words matching the medical vocabulary as target segmented words; A first word segmentation set corresponding to the initial symptom name is determined according to the target segmentation words.

5. The method according to claim 1, characterized in that: The step of determining the first part name included in the first participle set according to the first participle set and the target symptom name comprises: Deleting the first word corresponding to the target symptom name in the first word segmentation set; The remaining first words in the first word segmentation set are concatenated, and the concatenation result is determined as the first part name included in the first word segmentation set.

6. A word segmentation device for electronic medical records, characterized in that: An acquisition module is used to acquire an initial segmentation set corresponding to an initial sentence in an electronic medical record to be processed; wherein the initial segmentation set includes an initial symptom name and an initial part name corresponding to the initial sentence, and the initial segmentation set is determined by using a segmentation tool, a natural text segmentation processing algorithm, and structured processing of the initial sentence; A first word segmentation module is used to determine whether the initial symptom name contains words representing the body part, and if so, perform a first word segmentation operation on the initial symptom name to obtain a first word segmentation set corresponding to the initial symptom name; wherein the text length of each first word contained in the first word segmentation set is less than the text length of the initial symptom name; a determination module, configured to determine, based on the first word segmentation set and a pre-stored medical word library, a target symptom name corresponding to the initial sentence and a target part name corresponding to the initial sentence; wherein the medical word library is expanded by adding non-specific symptoms to the medical word library, the pre-stored medical word library includes symptom information and non-specific symptom information, and the non-specific symptom information is used to characterize the patient's feelings about the disease; The step of determining the target symptom name corresponding to the initial sentence according to the first word segmentation set and the medical word library includes: reversely traversing the first word in the first word segmentation set, and determining the first word matching the symptom information or non-specific symptom information in the medical word library as the target symptom name corresponding to the initial sentence; Among them, the step of determining the target part name corresponding to the initial sentence according to the first participle set and the medical vocabulary includes: determining the first part name contained in the first participle set according to the first participle set and the target symptom name; determining the target part name corresponding to the initial sentence according to the first part name and the initial part name.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 5.

Images