Artificial intelligence-based medical record text translation method, device, equipment and medium

Abstract

The present invention is applicable to the field of digital medical technology, and in particular relates to a medical record text translation method, device, equipment, and medium based on artificial intelligence. The present invention extracts keywords from associated medical record texts and splices them to obtain a keyword sequence, splices a target medical record text, M associated medical record texts, and M keyword sequences to obtain a spliced ​​medical record text, extracts text features of the spliced ​​medical record text, determines a target translation direction based on the text features, decodes the text features to obtain translation features of the target medical record text, linearly transforms the translation features according to a preset linear transformation matrix corresponding to the target translation direction, and obtains a target medical record translation. By associating medical record texts with keyword sequences, the information representation capability of the target medical record text is enhanced, and the text features are specifically decoded and linearly transformed according to the target translation direction, thereby improving the accuracy of the target medical record translation and the efficiency of digital services, intelligent interaction, and other businesses in the medical process.

Description

TECHNICAL FIELD

[0001] The application is suitable for the field of digital medical technology, and particularly relates to a medical record text translation method and device based on artificial intelligence, equipment and a medium. BACKGROUND

[0002] With the development of digital medical technology, in order to facilitate the management of patient information and improve the work efficiency of doctors, hospitals with more patients generally develop internal medical systems for doctors to fill in patient medical records, check patient examination results, handle medical orders, and discharge patients. In order to improve the readability and wide applicability of medical records, translating medical records into other required languages can facilitate browsing, learning, communication and research on medical records by users of multiple languages, which is of great significance to improving the efficiency of digital services and intelligent interactions in the medical process.

[0003] The medical record text translation task requires converting the medical record of a patient from one text language to another. Based on the importance and rigor of patient medical records, and the close correlation between multiple medical records of the same patient at different times and the close correlation between multiple medical records of the same disease for different patients, text translation of the target medical record combined with the associated medical record of the target medical record can effectively improve the accuracy of the translation result.

[0004] In order to learn from the associated information between medical records, the current associated perception translation model usually simply splices the associated medical record and the target medical record, and translates the spliced result to obtain the medical record translation of the target medical record, which makes it difficult to extract effective associated information from the associated medical record to assist the translation of the target medical record, resulting in low accuracy of the medical record translation of the target medical record, and failing to meet the demand for accurate medical record text translation.

[0005] Therefore, in the field of digital medical technology, how to improve the accuracy of medical record text translation and thereby improve the efficiency of digital services and intelligent interactions in the medical process has become a problem to be solved. SUMMARY

[0006] Therefore, the embodiments of the present application provide a medical record text translation method and device based on artificial intelligence to solve the problem that the current associated perception translation model cannot extract effective associated information to assist the translation of the target medical record, resulting in low accuracy of the medical record translation of the target medical record.

[0007] In a first aspect, the embodiments of the present application provide a medical record text translation method based on artificial intelligence, which comprises:

[0008] obtaining a target medical record text to be translated and M associated medical record texts corresponding to the target medical record text, for any associated medical record text, extracting a plurality of keywords of the associated medical record text, and splicing the plurality of keywords into a keyword sequence corresponding to the associated medical record text according to the order of the plurality of keywords in the associated medical record text, where M is a positive integer;

[0009] traversing all the associated medical record texts to obtain a keyword sequence corresponding to each associated medical record text, obtaining M keyword sequences, and splicing the target medical record text, the M associated medical record texts, and the M keyword sequences to obtain a spliced medical record text;

[0010] performing feature extraction on the spliced medical record text to obtain text features of the spliced medical record text, and determining a target translation direction of the target medical record text by judging the translation direction of the text features;

[0011] obtaining a preset word table and a preset linear transformation matrix corresponding to the target translation direction, decoding the text features to obtain translation features of the target medical record text, performing linear transformation on the translation features according to the preset linear transformation matrix to obtain a target medical record translation text of the target medical record text, and all text in the target medical record translation text is contained in the preset word table.

[0012] In a second aspect, an embodiment of the present application provides a medical record text translation device based on artificial intelligence, which comprises:

[0013] a keyword splicing module configured to obtain a target medical record text to be translated and M associated medical record texts corresponding to the target medical record text, extract a plurality of keywords of any associated medical record text, and splice the plurality of keywords into a keyword sequence corresponding to the associated medical record text according to the order of the plurality of keywords in the associated medical record text, where M is a positive integer;

[0014] a text splicing module configured to traverse all the associated medical record texts to obtain a keyword sequence corresponding to each associated medical record text, obtain M keyword sequences, and splice the target medical record text, the M associated medical record texts, and the M keyword sequences to obtain a spliced medical record text;

[0015] a feature extraction module configured to perform feature extraction on the spliced medical record text to obtain text features of the spliced medical record text, and determine a target translation direction of the target medical record text by judging the translation direction of the text features;

[0016] The text translation module is configured to obtain a preset vocabulary and a preset linear transformation matrix corresponding to the target translation direction, decode the text feature to obtain a translation feature of the target medical record text, perform linear transformation on the translation feature according to the preset linear transformation matrix, and obtain a target medical record translation text of the target medical record text, wherein all the texts in the target medical record translation text are included in the preset vocabulary.

[0017] In a third aspect, an embodiment of the present application provides a computer device, which comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the medical record text translation method according to the first aspect when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the medical record text translation method according to the first aspect.

[0019] Compared with the prior art, the embodiment of the present application has the beneficial effects that: by obtaining a target medical record text to be translated and M associated medical record texts corresponding to the target medical record text, extracting a plurality of keywords from the associated medical record texts, concatenating the plurality of keywords into a keyword sequence of the corresponding associated medical record text according to the order of the plurality of keywords in the associated medical record text, concatenating the target medical record text, the M associated medical record texts, and the M keyword sequences to obtain a concatenated medical record text, extracting a text feature of the concatenated medical record text, determining a target translation direction of the target medical record text according to the judgment of the translation direction of the text feature, obtaining a preset vocabulary and a preset linear transformation matrix corresponding to the target translation direction, decoding the text feature to obtain a translation feature of the target medical record text, and performing linear transformation on the translation feature according to the preset linear transformation matrix to obtain a target medical record translation text of the target medical record text, the information representation capability of the target medical record text is strengthened through the associated medical record texts and the keyword sequences, the corresponding preset vocabulary and preset linear transformation matrix are obtained by determining the target translation direction, the text feature of the target medical record text is decoded and linearly transformed in a targeted manner, the accuracy of the translation result is improved, and the efficiency of digital services, intelligent interactions, and other businesses in the medical process is improved. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is an application environment schematic diagram of a medical record text translation method based on artificial intelligence provided by an embodiment of the application;

[0022] Figure 2 is a flow schematic diagram of a medical record text translation method based on artificial intelligence provided by an embodiment of the application;

[0023] Figure 3 is a structural schematic diagram of a medical record text translation device based on artificial intelligence provided by an embodiment of the application;

[0024] Figure 4 is a structural schematic diagram of a computer device provided by an embodiment of the application. DETAILED DESCRIPTION

[0025] In the following description, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the application. However, persons skilled in the art will understand that the application can be practiced without these specific details. In other instances, well-known structures, devices, circuits, and methods have not been described in detail in order to avoid obscuring the description of the application.

[0026] It should be understood that the term "comprises" as used in the specification and the appended claims indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0027] It should also be understood that the term "and / or" as used in the specification and the appended claims indicates any combination of one or more of the associated listed items and all possible combinations of the items.

[0028] As used in the specification and the appended claims, the term "if" can be interpreted as meaning "when" or "once" or "in response to a determination" or "in response to a detection" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted as meaning "once determined" or "in response to a determination" or "once detected [the described condition or event]" or "in response to a detection [the described condition or event]" depending on the context.

[0029] In addition, in the description of the specification and the appended claims, the terms "first", "second", "third", etc. are only used for differentiation in description and cannot be understood as indicating or implying relative importance.

[0030] Reference within the specification of this document to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places within specified

[0031] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Wherein, artificial intelligence (AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results.

[0032] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0033] It should be understood that the size of the serial number of each step in the following embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0034] In order to illustrate the technical solutions of the present application, the following will be explained by specific embodiments.

[0035] The method for translating medical record text based on artificial intelligence provided by the embodiment of the present application can be applied in application environments such as Figure 1 The client communicates with the server. The client includes but is not limited to palmtop computer, desktop computer, notebook computer, super mobile personal computer, netbook, cloud computer device, personal digital assistant, etc. The server can be realized by an independent server or a server cluster composed of multiple servers.

[0036] Referring to Figure 2Fig. 1 is a flow diagram of a medical record text translation method based on artificial intelligence according to an embodiment of the present application. The medical record text translation method can be applied to a client in Figure 1 The medical record text translation method can include the following steps:

[0037] In step S201, a target medical record text to be translated and M associated medical record texts corresponding to the target medical record text are obtained. For any associated medical record text, a plurality of keywords of the associated medical record text are extracted, and the plurality of keywords are spliced into a keyword sequence of the corresponding associated medical record text according to the order of the plurality of keywords in the associated medical record text.

[0038] A medical record is a systematic record of the occurrence, development, diagnosis and treatment of a patient's disease. It is the information obtained by a clinician through interrogation, physical examination, examination and detailed observation of the disease, and is the disease archive data obtained by induction, analysis, arrangement and writing. It can truly reflect the patient's condition and directly reflect the hospital's medical quality, academic level and management level. It not only provides valuable basic data for medical treatment, scientific research and teaching, but also provides indispensable medical information for hospital management.

[0039] The target medical record text is converted from one text language to another text language as needed in this embodiment, which can improve the readability and wide applicability of the target medical record, and facilitate browsing, learning, communication and research of the target medical record by users of multiple languages, thereby improving the efficiency of digital services, intelligent interaction and other businesses in the medical process.

[0040] The target medical record text and the M associated medical record texts corresponding to the target medical record text can be multiple medical record texts of the same patient at different times, or multiple medical record texts of the same disease for different patients, and the like. Therefore, this embodiment combines the M associated medical record texts closely related to the target medical record text to improve the information representation capability of the target medical record text, thereby improving the translation accuracy, wherein M is a positive integer.

[0041] Specifically, in order to improve the translation efficiency, the plurality of keywords of the associated medical record text are extracted, and the plurality of keywords are spliced into a keyword sequence of the corresponding associated medical record text according to the order of the plurality of keywords in the associated medical record text, so as to improve the information representation capability of the target medical record text.

[0042] Optionally, the keywords include a predicate, a predicate issuer and a predicate receiver.

[0043] The plurality of keywords of the associated medical record text are extracted, and the plurality of keywords are spliced into a keyword sequence of the corresponding associated medical record text according to the order of the plurality of keywords in the associated medical record text, including:

[0044] extract all predicates, predicate initiators and predicate receivers in the related medical record text, and concatenate all the predicates, predicate initiators and predicate receivers into a keyword sequence of the related medical record text according to the order of the predicates, predicate initiators and predicate receivers in the related medical record text.

[0045] In the embodiment, the keywords include the predicates, the predicate initiators and the predicate receivers, which can effectively capture the semantic information in the form of "who did what to whom", and be used to analyze the textual information such as the anaphora and the ellipsis in the related medical record text, thereby improving the representation ability of the related medical record text.

[0046] According to the order of the extracted keywords in the related medical record text, the keywords are concatenated into a keyword sequence of the corresponding related medical record text, which serves as a basis for the translation of the target medical record text, thereby improving the efficiency of information extraction and text translation.

[0047] The embodiment extracts the predicates, the predicate initiators and the predicate receivers in the related medical record text, analyzes the textual information such as the anaphora and the ellipsis in the related medical record text, and serves as a basis for the translation of the target medical record text, thereby improving the representation ability of the related medical record text and the efficiency of information extraction and text translation.

[0048] Optionally, the related medical record text includes an original medical record text and a medical record translation corresponding to the original medical record text.

[0049] extracting all predicates, predicate initiators and predicate receivers in the related medical record text, and concatenating all the predicates, predicate initiators and predicate receivers into a keyword sequence of the related medical record text according to the order of the predicates, predicate initiators and predicate receivers in the related medical record text.

[0050] extracting all first predicates, first predicate initiators and first predicate receivers in the original medical record text, and concatenating all the first predicates, first predicate initiators and first predicate receivers into a first keyword sequence of the original medical record text according to the order of the first predicates, first predicate initiators and first predicate receivers in the original medical record text;

[0051] extracting all second predicates, second predicate initiators and second predicate receivers in the medical record translation, and concatenating all the second predicates, second predicate initiators and second predicate receivers into a second keyword sequence of the medical record translation according to the order of the second predicates, second predicate initiators and second predicate receivers in the medical record translation;

[0052] determining the first keyword sequence and the second keyword sequence as the keyword sequence of the related medical record text.

[0053] Among them, the associated medical record text in this embodiment includes the original medical record text and the medical record translation corresponding to the original medical record text. The original medical record text and the corresponding medical record translation can assist in representing the text semantic information, text structure information and other related information of the target medical record text. The medical record translation can also assist in representing the translation information of the target medical record text, thereby improving the information representation ability of the target medical record text and further improving the accuracy of the translation results of the target medical record text.

[0054] Correspondingly, when extracting all predicates, predicate issuers, and predicate recipients from the associated medical record text, all predicates, predicate issuers, and predicate recipients from the original medical record text and the medical record translation are extracted, respectively, to obtain all first predicates, first predicate issuers, and first predicate recipients from the corresponding original medical record text, as well as all second predicates, second predicate issuers, and second predicate recipients from the corresponding medical record translation. All first predicates, first predicate issuers, and first predicate recipients are then sequentially concatenated into a first keyword sequence for the original medical record text, and all second predicates, second predicate issuers, and second predicate recipients are concatenated into a second keyword sequence for the medical record translation. This allows the determination of a keyword sequence for the associated medical record text, including the corresponding first keyword sequence and second keyword sequence, as a basis for assisting in characterizing textual semantic information, textual structural information, and translation information for the target medical record text.

[0055] The associated medical record text in this embodiment includes the original medical record text and the medical record translation corresponding to the original medical record text. The first keyword sequence corresponding to the original medical record text and the second keyword sequence corresponding to the medical record translation are extracted respectively, replacing the corresponding associated medical record text to assist in representing the text semantic information, text structure information and translation information of the target medical record text, thereby improving the information representation ability of the target medical record text and further improving the accuracy of the translation results of the target medical record text.

[0056] The above steps include obtaining the target medical record text to be translated and M associated medical record texts corresponding to the target medical record text, extracting several keywords of the associated medical record text for any associated medical record text, and splicing the several keywords into a keyword sequence corresponding to the associated medical record text according to the order of the several keywords in the associated medical record text. The M associated medical record texts closely related to the target medical record text are combined to improve the information representation ability of the target medical record text, and using the keyword sequence instead of the corresponding associated medical record text, thereby improving the efficiency of information extraction and text translation, as well as the accuracy of text translation.

[0057] Step S202, traverse all associated medical record texts, obtain the keyword sequence corresponding to each associated medical record text, obtain M keyword sequences, splice the target medical record text, the M associated medical record texts and the M keyword sequences, and obtain a spliced ​​medical record text.

[0058] wherein all the associated medical record texts are traversed to obtain M keyword sequences corresponding to the M associated medical record texts respectively, and then the target medical record text, the M associated medical record texts and the M keyword sequences are spliced to obtain a spliced medical record text as a data basis for translating the target medical record text.

[0059] Optionally, the splicing of the target medical record text, the M associated medical record texts and the M keyword sequences to obtain the spliced medical record text comprises:

[0060] a starting delimiter and a sequence end symbol are obtained, and for any associated medical record text and the keyword sequence corresponding to the associated medical record text, the starting delimiter, the keyword sequence and the associated medical record text are spliced according to a first preset order to obtain a first spliced medical record text corresponding to the associated medical record text;

[0061] the M associated medical record texts and the M keyword sequences corresponding to the M associated medical record texts are traversed to obtain M first spliced medical record texts;

[0062] the starting delimiter, the target medical record text and the sequence end symbol are spliced according to a second preset order to obtain a corresponding second spliced medical record text;

[0063] the M first spliced medical record texts and the second spliced medical record text are spliced according to a third preset order to obtain the spliced medical record text.

[0064] In order to improve the readability of the spliced medical record text and facilitate the accurate extraction of the feature information corresponding to the target medical record text, the M associated medical record texts and the M keyword sequences, the embodiment obtains a preset starting delimiter and a sequence end symbol, and splices the starting delimiter, the keyword sequence and the associated medical record text according to a first preset order to obtain a first spliced medical record text, thereby completing the splicing combination of each group of keyword sequences and the corresponding associated medical record text; the starting delimiter, the target medical record text and the sequence end symbol are spliced according to a second preset order to obtain a second spliced medical record text, thereby completing the splicing combination of the target medical record text; finally, the M first spliced medical record texts and the second spliced medical record text are spliced according to a third preset order to obtain the spliced medical record text, thereby completing the splicing combination of the target medical record text, the M associated medical record texts and the M keyword sequences.

[0065] Optionally, the first preset order comprises a fourth preset order and a fifth preset order, and the keyword sequence comprises a first keyword sequence and a second keyword sequence.

[0066] splicing the starting delimiter, the keyword sequence and the original medical record text according to the first preset order to obtain the first spliced medical record text corresponding to the associated medical record text comprises:

[0067] The starting delimiter, the first keyword sequence, and the associated medical record text are spliced according to a fourth preset order to obtain a corresponding first spliced medical record subtext;

[0068] The starting delimiter, the second keyword sequence, and the medical record translation are spliced according to a fifth preset order to obtain a corresponding second spliced medical record subtext;

[0069] The first spliced medical record subtext and the second spliced medical record subtext are spliced to obtain the first spliced medical record text corresponding to the associated medical record text.

[0070] Corresponding to the fact that the associated medical record text includes the original medical record text and the medical record translation corresponding to the original medical record text, the first preset order in this embodiment includes the fourth preset order and the fifth preset order, and the keyword sequence includes the first keyword sequence and the second keyword sequence.

[0071] Correspondingly, when splicing each group of keyword sequences and the corresponding associated medical record text, the starting delimiter, the first keyword sequence, and the associated medical record text are spliced to obtain the first spliced medical record subtext, the starting delimiter, the second keyword sequence, and the medical record translation are spliced to obtain the second spliced medical record subtext, and then the first spliced medical record subtext and the second spliced medical record subtext are spliced into the corresponding first spliced medical record text, thereby improving the representation ability of the spliced medical record text to the associated medical record text.

[0072] The above steps of traversing all the associated medical record texts to obtain the keyword sequence corresponding to each associated medical record text, obtaining M keyword sequences, and splicing the target medical record text, the M associated medical record texts, and the M keyword sequences to obtain the spliced medical record text fuse the information of the target medical record text, the M associated medical record texts, and the M keyword sequences into the spliced medical record text, which can provide additional text position, text type, and other information for feature extraction, thereby improving the translation accuracy of the target medical record text.

[0073] In step S203, feature extraction is performed on the spliced medical record text to obtain text features of the spliced medical record text, and a translation direction judgment is performed on the text features to determine the target translation direction of the target medical record text.

[0074] The feature extraction is performed on the spliced medical record text to obtain text features of the spliced medical record text, and the text features simultaneously represent semantic information, correlation information between each other, translation information between the original text and the corresponding translation, and other effective information of the target medical record text, the M associated medical record texts, and the M keyword sequences, which can be used as a basis for translation of the target medical record text.

[0075] Then, the translation direction of the text feature is judged to determine the target translation direction of the target medical record text. For example, when the target medical record text is Chinese, the determined target translation direction can be "Chinese to English". By explicitly determining the target translation direction, the target medical record text can be translated specifically, which can ensure the rationality of the translation and improve the accuracy of the translation result.

[0076] In an embodiment, the trained encoder is used to extract features of the spliced medical record text to obtain text features of the spliced medical record text, so as to improve the extraction accuracy of the text features.

[0077] Optionally, the judgment of the translation direction of the text feature to determine the target translation direction of the target medical record text includes:

[0078] The trained multi-layer perception model is used to judge the translation direction of the text feature to obtain a probability value corresponding to the text feature.

[0079] A preset mapping table between the translation direction and the probability value is obtained, and the target translation direction of the target medical record text is determined according to the probability value and the mapping table.

[0080] The multi-layer perception model is a neural network composed of fully connected layers with at least one hidden layer, which can be used for category judgment of input content. The categories of the translation direction and the preset mapping table between the translation direction and the probability value can be set according to actual conditions. For example, the translation direction corresponding to the probability value in [0, 0.5] can be set as "Chinese to English", and the translation direction corresponding to the probability value in (0.5, 1] can be set as "English to Chinese".

[0081] In this embodiment, the trained multi-layer perception model is used to judge the translation direction of the text feature to obtain a probability value corresponding to the text feature, and further according to the probability value and the mapping table, the translation direction corresponding to the probability value in the mapping table is determined as the target translation direction of the target medical record text.

[0082] In this embodiment, the trained multi-layer perception model is used to judge the translation direction of the text feature to obtain a probability value corresponding to the text feature, and further according to the probability value and the mapping table, the translation direction corresponding to the probability value in the mapping table is determined as the target translation direction of the target medical record text.

[0083] The above steps of extracting features of the spliced medical record text to obtain text features of the spliced medical record text, judging the translation direction of the text feature to determine the target translation direction of the target medical record text, extracting the text features of the spliced medical record text and explicitly determining the target translation direction to specifically translate the target medical record text can ensure the rationality of the translation and improve the accuracy of the translation result.

[0084] In step S204, the preset vocabulary and the preset linear transformation matrix corresponding to the target translation direction are obtained, the text features are decoded to obtain the translation features of the target medical record text, the linear transformation is performed on the translation features according to the preset linear transformation matrix, and the target medical record translation text of the target medical record text is obtained. All the texts in the target medical record translation text are included in the preset vocabulary.

[0085] The preset vocabulary and the preset linear transformation matrix are set according to the corresponding translation direction. For example, when the translation direction is “Chinese to English”, the corresponding preset vocabulary is composed of English texts, the corresponding preset linear transformation matrix is used to perform linear transformation on the input features to obtain the corresponding English translation text, and all the texts in the English translation text are included in the corresponding preset vocabulary. When the translation direction is “English to Chinese”, the corresponding preset vocabulary is composed of Chinese texts, the corresponding preset linear transformation matrix is used to perform linear transformation on the input features to obtain the corresponding Chinese translation text, and all the texts in the Chinese translation text are included in the corresponding preset vocabulary.

[0086] Therefore, the preset vocabulary and the preset linear transformation matrix corresponding to the target translation direction are obtained to translate the target medical record text specifically, which can ensure the rationality of the translation and improve the accuracy of the translation result. Specifically, the text features are decoded to obtain the translation features of the target medical record text. Then, the linear transformation is performed on the translation features according to the preset linear transformation matrix to obtain the target medical record translation text of the target medical record text. Correspondingly, all the texts in the target medical record translation text are included in the preset vocabulary.

[0087] Optionally, the target medical record text includes N text characters, and N is a positive integer.

[0088] The text features are decoded to obtain the translation features of the target medical record text, including:

[0089] The trained decoder is used to decode the text features and the preset features to obtain the first translation sub-feature corresponding to the first text character in the target medical record text. The preset features are zero feature sequences.

[0090] The trained decoder is used to decode the text features and the first n-1 translation sub-features to obtain the n-th translation sub-feature corresponding to the n-th text character in the target medical record text, n=2, 3, …, N.

[0091] The translation features of the target medical record text are obtained according to the N translation sub-features corresponding to the N text characters in the target medical record text.

[0092] Wherein, the target medical record text includes N text characters, the trained decoder in the embodiment is used to decode the N text characters respectively, and the decoding feature of the previous text character is used to decode the next text character, so as to improve the accuracy of the decoded translation feature.

[0093] Since the first text character does not have a corresponding previous text character, in order to ensure the decoding accuracy of the decoder for the target medical record text, the embodiment obtains a zero feature sequence as a preset feature to replace the decoding feature of the previous text character of the first text character, finally obtains N translation sub-features corresponding to the N text characters in the target medical record text, and splices the N translation sub-features to obtain the translation feature of the target medical record text.

[0094] In the embodiment, the trained decoder is used to decode the N text characters respectively, and the decoding feature of the previous text character is used to decode the next text character, and meanwhile, considering that the first text character does not have a corresponding previous text character, a zero feature sequence is obtained as a preset feature to replace the decoding feature of the previous text character of the first text character, so as to improve the accuracy of the decoded translation feature.

[0095] The above steps of obtaining the preset vocabulary and the preset linear transformation matrix corresponding to the target translation direction, decoding the text feature to obtain the translation feature of the target medical record text, and linearly transforming the translation feature according to the preset linear transformation matrix to obtain the target medical record translation of the target medical record text, all the texts in the target medical record translation are contained in the preset vocabulary, obtaining the preset vocabulary and the preset linear transformation matrix corresponding to the target translation direction to translate the target medical record text specifically, ensure the rationality of the translation, and improve the accuracy of the translation result.

[0096] The embodiment of the present invention obtains a target medical record text and M associated medical record texts corresponding to the target medical record text, extracts a number of keywords from the associated medical record texts, splices the keywords into a keyword sequence corresponding to the associated medical record text according to the order of the keywords in the associated medical record texts, splices the target medical record text, the M associated medical record texts and the M keyword sequence to obtain a spliced ​​medical record text, extracts features from the spliced ​​medical record text, obtains text features of the spliced ​​medical record text, judges the translation direction of the text features, determines the target translation direction of the target medical record text, and obtains the translation direction corresponding to the target translation direction. A preset vocabulary and a preset linear transformation matrix are used to decode the text features and obtain the translation features of the target medical record text. The translation features are linearly transformed according to the preset linear transformation matrix to obtain the target medical record translation of the target medical record text. By associating the medical record text and the keyword sequence, the information representation ability of the target medical record text is enhanced. By determining the target translation direction, the corresponding preset vocabulary and preset linear transformation matrix are obtained, and the text features of the target medical record text are decoded and linearly transformed in a targeted manner, which improves the accuracy of the translation results and improves the efficiency of digital services, intelligent interactions and other businesses in the medical process.

[0097] Corresponding to the medical record text translation method of the above embodiment, Figure 3 A structural block diagram of an artificial intelligence-based medical record text translation device provided in the second embodiment of the present invention is given. For ease of explanation, only the parts related to the embodiment of the present invention are shown.

[0098] See also Figure 3 , the medical record text translation device includes:

[0099] The keyword concatenation module 31 is configured to obtain a target medical record text to be translated and M associated medical record texts corresponding to the target medical record text, extract a number of keywords from any associated medical record text, and concatenate the keywords into a keyword sequence corresponding to the associated medical record text according to the order of the keywords in the associated medical record text, where M is a positive integer.

[0100] The text splicing module 32 is used to traverse all the related medical record texts, obtain the keyword sequence corresponding to each related medical record text, obtain M keyword sequences, and splice the target medical record text, the M related medical record texts and the M keyword sequences to obtain a spliced ​​medical record text;

[0101] The feature extraction module 33 is used to extract features from the spliced ​​medical record text, obtain text features of the spliced ​​medical record text, judge the translation direction based on the text features, and determine the target translation direction of the target medical record text;

[0102] The text translation module 34 is configured to acquire a preset word table and a preset linear transformation matrix corresponding to a target translation direction, decode the text features to obtain translation features of the target medical record text, and perform linear transformation on the translation features according to the preset linear transformation matrix to obtain a target medical record translation text of the target medical record text, wherein all the text in the target medical record translation text is included in the preset word table.

[0103] Optionally, the keywords include a predicate, a predicate doer and a predicate receiver, and the keyword splicing module 31 includes:

[0104] The keyword splicing sub-module is configured to extract all the predicates, the predicate doers and the predicate receivers in the associated medical record text, and splice all the predicates, the predicate doers and the predicate receivers into a keyword sequence of the associated medical record text according to the order of the predicates, the predicate doers and the predicate receivers in the associated medical record text.

[0105] Optionally, the associated medical record text includes an original medical record text and a medical record translation text corresponding to the original medical record text, and the keyword splicing sub-module includes:

[0106] The first keyword splicing unit is configured to extract all the first predicates, the first predicate doers and the first predicate receivers in the original medical record text, and splice all the first predicates, the first predicate doers and the first predicate receivers into a first keyword sequence of the original medical record text according to the order of the first predicates, the first predicate doers and the first predicate receivers in the original medical record text.

[0107] The second keyword splicing unit is configured to extract all the second predicates, the second predicate doers and the second predicate receivers in the medical record translation text, and splice all the second predicates, the second predicate doers and the second predicate receivers into a second keyword sequence of the medical record translation text according to the order of the second predicates, the second predicate doers and the second predicate receivers in the medical record translation text.

[0108] The third keyword splicing unit is configured to determine the first keyword sequence and the second keyword sequence as the keyword sequence of the associated medical record text.

[0109] Optionally, the text splicing module 32 includes:

[0110] The first text splicing sub-module is configured to acquire a preset starting delimiter and a sequence end symbol, splice, for any associated medical record text and a keyword sequence corresponding to the associated medical record text, the starting delimiter, the keyword sequence and the associated medical record text in a first preset order to obtain a first spliced medical record text corresponding to the associated medical record text.

[0111] The first traversing submodule is configured to traverse M associated medical record texts and M keyword sequences corresponding to the M associated medical record texts to obtain M first spliced medical record texts.

[0112] The second text splicing submodule is configured to splice the start delimiter, the target medical record text and the sequence end symbol in a second preset order to obtain a corresponding second spliced medical record text.

[0113] The third text splicing submodule is configured to splice the M first spliced medical record texts and the second spliced medical record text in a third preset order to obtain a spliced medical record text.

[0114] Optionally, the first preset order includes a fourth preset order and a fifth preset order, and the keyword sequence includes a first keyword sequence and a second keyword sequence, and the first text splicing submodule includes:

[0115] The first text splicing unit is configured to splice the start delimiter, the first keyword sequence and the associated medical record text in the fourth preset order to obtain a corresponding first spliced medical record subtext.

[0116] The second text splicing unit is configured to splice the start delimiter, the second keyword sequence and the medical record translation in the fifth preset order to obtain a corresponding second spliced medical record subtext.

[0117] The third text splicing unit is configured to splice the first spliced medical record subtext and the second spliced medical record subtext to obtain the first spliced medical record text corresponding to the associated medical record text.

[0118] Optionally, the feature extraction module 33 includes:

[0119] The probability value determination submodule is configured to use the trained multilayer perception model to determine the translation direction of the text feature to obtain a probability value corresponding to the text feature.

[0120] The target translation direction determination submodule is configured to obtain a preset mapping table between the translation direction and the probability value, and determine the target translation direction of the target medical record text according to the probability value and the mapping table.

[0121] Optionally, the target medical record text includes N text characters, and N is a positive integer, and the text translation module 34 includes:

[0122] The first feature decoding submodule is configured to use the trained decoder to decode the text feature and a preset feature to obtain a first translation sub-feature corresponding to a first text character in the target medical record text, and the preset feature is a zero feature sequence.

[0123] a second feature decoding submodule configured to decode the text features and the first n-1 translation sub-features using the trained decoder to obtain an n-th translation sub-feature corresponding to an n-th text character in the target medical record text, n = 2, 3,..., N;

[0124] a translation feature determination submodule configured to obtain a translation feature of the target medical record text according to the N translation sub-features corresponding to the N text characters in the target medical record text.

[0125] It should be noted that the information interaction between the above modules, the execution process and the like, since the same concept as the method embodiments of the present application, the specific functions and the technical effects brought about, specific can be seen from the method embodiments, this will not be repeated here.

[0126] Figure 4 A structural schematic diagram of a computer device for the third embodiment of the present application is shown in FIG. 3. Figure 4 As shown in the figure, the computer device of this embodiment comprises at least one processor (only one is shown in the figure), a memory, and a computer program stored in the memory and executable on the at least one processor, and the processor executes the computer program to implement the steps in any of the medical record text translation method embodiments. Figure 4

[0127] The computer device can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the computer device is only an example of the computer device and does not constitute a limitation on the computer device, and the computer device can include more or fewer components than the figure, or combine certain components, or different components, for example, it can also include a network interface, a display screen, and an input device, etc. Figure 4

[0128] The processor can be a CPU, and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), ready programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0129] ​​The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory can be a memory of the computer device, and the internal memory provides an environment for running of the operating system and the computer-readable instructions in the readable storage medium. The readable storage medium can be a hard disk of the computer device, and in other embodiments, can also be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory can include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a BootLoader, data, and other programs, such as program codes of computer programs, etc. The memory can also be used to temporarily store data that has been output or will be output.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the unit and module in the above device can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. If the integrated unit is realized in the form of software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present application realizes all or part of the processes in the above-mentioned embodiment methods, which can be completed by a computer program instructing related hardware. The computer program can be stored in a computer readable storage medium, and when the processor executes the computer program, the steps of the above-mentioned method embodiment can be realized. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium at least includes any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (Read-Only Memory, ROM), random access memory, electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, computer readable medium cannot be electrical carrier signal and telecommunication signal.

[0131] The present application realizes all or part of the processes in the above-mentioned embodiment methods, which can also be completed by a computer program product. When the computer program product runs on the computer device, it makes the computer device execute the steps that can realize the above-mentioned method embodiments.

[0132] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0133] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0134] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / computer device and method can be implemented in other manners. For example, the described apparatus / computer device embodiments are merely schematic. For example, the division of the modules or units can be different, and each can include a plurality of sub-units. Some or all of the modules or units can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e. may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0136] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A medical record text translation method based on artificial intelligence, characterized in that: The medical record text translation method comprises: Obtain a target medical record text to be translated and M associated medical record texts corresponding to the target medical record text, extract a number of keywords from any associated medical record text, and concatenate the keywords into a keyword sequence corresponding to the associated medical record text according to the order of the keywords in the associated medical record text, where M is a positive integer; Traversing all associated medical record texts, respectively obtaining a keyword sequence corresponding to each associated medical record text, obtaining M keyword sequences, and splicing the target medical record text, the M associated medical record texts, and the M keyword sequences to obtain a spliced ​​medical record text; Performing feature extraction on the spliced ​​medical record text to obtain text features of the spliced ​​medical record text, determining the translation direction of the text features, and determining the target translation direction of the target medical record text; Obtain a preset vocabulary and a preset linear transformation matrix corresponding to the target translation direction, decode the text features to obtain the translation features of the target medical record text, perform linear transformation on the translation features according to the preset linear transformation matrix, and obtain the target medical record translation of the target medical record text, wherein all texts in the target medical record translation are included in the preset vocabulary.

2. The medical record text translation method according to claim 1, characterized in that: The keywords include predicate, predicate sender and predicate receiver; The step of extracting a plurality of keywords from the associated medical record text and splicing the keywords into a keyword sequence corresponding to the associated medical record text according to the order of the keywords in the associated medical record text includes: Extract all predicates, predicate issuers and predicate recipients in the associated medical record text, and splice all predicates, predicate issuers and predicate recipients into a keyword sequence of the associated medical record text according to the order of all predicates, predicate issuers and predicate recipients in the associated medical record text.

3. The medical record text translation method according to claim 2, characterized in that: The associated medical record text includes the original medical record text and the medical record translation corresponding to the original medical record text; The step of extracting all predicates, predicate issuers, and predicate recipients from the associated medical record text and splicing all predicates, predicate issuers, and predicate recipients into a keyword sequence for the associated medical record text according to the order of the predicates, predicate issuers, and predicate recipients in the associated medical record text includes: Extracting all first predicates, first predicate issuers, and first predicate recipients from the original medical record text, and concatenating all first predicates, first predicate issuers, and first predicate recipients into a first keyword sequence of the original medical record text according to their order in the original medical record text; Extracting all second predicates, second predicate issuers, and second predicate recipients from the medical record translation, and concatenating all second predicates, second predicate issuers, and second predicate recipients into a second keyword sequence for the medical record translation based on their order in the medical record translation; The first keyword sequence and the second keyword sequence are determined as the keyword sequence of the associated medical record text.

4. The medical record text translation method according to claim 3, characterized in that: The step of splicing the target medical record text, the M associated medical record texts, and the M keyword sequences to obtain a spliced ​​medical record text includes: Obtaining a preset start delimiter and a sequence end character, and for any associated medical record text and a keyword sequence corresponding to the associated medical record text, concatenating the start delimiter, the keyword sequence, and the associated medical record text in a first preset order to obtain a first concatenated medical record text corresponding to the associated medical record text; Traverse the M associated medical record texts and the M keyword sequences corresponding to the M associated medical record texts to obtain M first concatenated medical record texts; splicing the start delimiter, the target medical record text, and the sequence terminator in a second preset order to obtain a corresponding second spliced ​​medical record text; The M first spliced ​​medical record texts and the second spliced ​​medical record text are spliced ​​in a third preset order to obtain a spliced ​​medical record text.

5. The medical record text translation method according to claim 4, characterized in that: The first preset order includes a fourth preset order and a fifth preset order, and the keyword sequence includes the first keyword sequence and the second keyword sequence; The step of splicing the start delimiter, the keyword sequence, and the associated medical record text in a first preset order to obtain a first spliced ​​medical record text corresponding to the associated medical record text includes: splicing the start delimiter, the first keyword sequence, and the associated medical record text in a fourth preset order to obtain a corresponding first spliced ​​medical record subtext; splicing the start delimiter, the second keyword sequence, and the medical record translation in a fifth preset order to obtain a corresponding second spliced ​​medical record subtext; The first spliced ​​medical record subtext and the second spliced ​​medical record subtext are spliced ​​to obtain a first spliced ​​medical record text corresponding to the associated medical record text.

6. The medical record text translation method according to claim 1, characterized in that: The determining of the translation direction of the text features to determine the target translation direction of the target medical record text includes: Using a trained multi-layer perceptron model to determine the translation direction of the text features, and obtaining a probability value corresponding to the text features; A preset mapping table between translation directions and probability values ​​is obtained, and a target translation direction of the target medical record text is determined according to the probability values ​​and the mapping table.

7. The medical record text translation method according to claim 1, characterized in that: The target medical record text includes N text characters, where N is a positive integer; Decoding the text features to obtain translation features of the target medical record text includes: Decoding the text feature and the preset feature using a trained decoder to obtain a first translation sub-feature corresponding to the first text character in the target medical record text, wherein the preset feature is a zero feature sequence; Decoding the text feature and the first n-1 translation sub-features using the trained decoder to obtain the n-th translation sub-feature corresponding to the n-th text character in the target medical record text, where n=2, 3, ..., N; The translation features of the target medical record text are obtained according to the N translation sub-features corresponding to the N text characters in the target medical record text.

8. A medical record text translation device based on artificial intelligence, characterized in that: The medical record text translation device comprises: A keyword concatenation module is configured to obtain a target medical record text to be translated and M associated medical record texts corresponding to the target medical record text, extract a number of keywords from any associated medical record text, and concatenate the keywords into a keyword sequence corresponding to the associated medical record text based on the order of the keywords in the associated medical record text, where M is a positive integer; A text splicing module is used to traverse all related medical record texts, obtain the keyword sequence corresponding to each related medical record text, obtain M keyword sequences, and splice the target medical record text, the M related medical record texts, and the M keyword sequences to obtain a spliced ​​medical record text; A feature extraction module is used to extract features from the spliced ​​medical record text to obtain text features of the spliced ​​medical record text, determine the translation direction of the text features, and determine the target translation direction of the target medical record text; A text translation module is used to obtain a preset vocabulary and a preset linear transformation matrix corresponding to the target translation direction, decode the text features to obtain the translation features of the target medical record text, perform linear transformation on the translation features according to the preset linear transformation matrix, and obtain the target medical record translation of the target medical record text. All texts in the target medical record translation are included in the preset vocabulary.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the medical record text translation method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the medical record text translation method according to any one of claims 1 to 7 is implemented.

Images