Physical examination conclusion merging method and device and computer program product

Abstract

The invention discloses a physical examination conclusion merging method and device and a computer program product, and the method comprises the steps: obtaining a physical examination report, and extracting conclusion words in the physical examination report; building a prompt based on the conclusion word, and inputting the prompt into the adjusted model, so that the model determines a standard conclusion word corresponding to the conclusion word from a word bank based on the prompt; and merging the standard conclusion words according to a specified merging rule by utilizing a merging rule engine. The physical examination conclusions are merged in an intelligent mode, so that the merging efficiency and accuracy are improved, and the technical problem that the merging efficiency and accuracy need to be further improved in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method and device for merging physical examination conclusions, and a computer program product. Background Art

[0002] In the traditional physical examination report generation process, most scenarios require the merging of abnormal conclusions with high disease relevance, which often relies on relevant medical guidelines and manual merging operations by the main examiner, which is not only time-consuming and laborious, but also prone to omissions and errors. Especially when there is a shortage of professional main examiners, the efficiency and accuracy of physical examination report merging are seriously affected. Summary of the invention

[0003] The main purpose of the present invention is to provide a method and device for merging physical examination conclusions, and a computer program product to solve the technical problems existing in the related technologies.

[0004] In order to achieve the above-mentioned purpose, according to the first aspect of the present invention, a method for merging physical examination conclusions is provided, comprising: obtaining a physical examination report and extracting conclusion words in the physical examination report; constructing prompts based on the conclusion words, and inputting the prompts into an adjusted model, so that the model can determine the standard conclusion words corresponding to the conclusion words from the vocabulary based on the prompts; and using a merging rule engine to merge the standard conclusion words according to specified merging rules.

[0005] Optionally, when the model is adjusted: obtain a physical examination report sample to extract abnormal conclusion words from the sample; construct a prompt based on the abnormal conclusion words, and use the prompt as the input of the model; construct an output based on the standard conclusion words mapped to the abnormal conclusion words; and train the model using the input and the output.

[0006] Optionally, using a merge rule engine to merge the standard conclusion words according to specified merge rules includes: merging the standard conclusion words according to multiple sub-merge rules in the merge rule; wherein each sub-merge rule has a different priority, and determining whether the standard conclusion word hits the sub-merge rule during merging; if the standard conclusion word does not hit the current sub-merge rule, matching the next sub-merge rule in order of priority; if the current sub-merge rule is hit, merging is performed according to the instructions of the sub-merge rule.

[0007] Optionally, the sub-merge rules include symptom merging rules, human body system structure information merging rules, and department information merging rules.

[0008] According to a second aspect of the present invention, a physical examination conclusion merging device is provided, comprising: a conclusion word extraction unit, configured to obtain a physical examination report and extract conclusion words in the physical examination report; a prediction unit, configured to construct prompts based on the conclusion words, and input the prompts into an adjusted model, so that the model can determine the standard conclusion words corresponding to the conclusion words from the vocabulary based on the prompts; and a merging unit, configured to use a merging rule engine to merge the standard conclusion words according to specified merging rules.

[0009] Optionally, when the model is adjusted: obtain a physical examination report sample to extract abnormal conclusion words from the sample; construct a prompt based on the abnormal conclusion words, and use the prompt as the input of the model; construct an output based on the standard conclusion words mapped to the abnormal conclusion words; and train the model using the input and the output.

[0010] Optionally, the merging unit is configured to: merge the standard conclusion words according to multiple sub-merge rules in the merging rules; wherein each sub-merge rule has a different priority, and judge whether the standard conclusion word hits the sub-merge rule during the merging; if the standard conclusion word does not hit the current sub-merge rule, match the next sub-merge rule in order of priority; if it hits the current sub-merge rule, merge according to the instructions of the sub-merge rule.

[0011] According to a third aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute a method for merging physical examination conclusions.

[0012] According to a fourth aspect of the present invention, there is provided an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor performs a method for merging physical examination conclusions.

[0013] According to a fifth aspect of the present invention, there is provided a computer program product, comprising a computer program, wherein the computer program implements a method for merging physical examination conclusions when executed by a processor.

[0014] The present embodiment provides a method and device for merging physical examination conclusions, and a computer program product, wherein the method includes obtaining a physical examination report and extracting conclusion words from the physical examination report; constructing a prompt based on the conclusion word, and inputting the prompt into an adjusted model, so that the model can determine the standard conclusion word corresponding to the conclusion word from the word library based on the prompt; and using a merging rule engine to merge the standard conclusion words according to a specified merging rule. Merging physical examination conclusions in an intelligent manner improves merging efficiency and accuracy, overcoming the technical problem that the efficiency and accuracy of merging in the prior art need to be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] 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.

[0016] Figure 1 is a flow chart of a method for merging physical examination conclusions according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the mapping relationship in the method for merging physical examination conclusions in an embodiment of the present invention; Figure 3 This is a system architecture diagram applicable to the method for merging physical examination conclusions according to an embodiment of the present invention; Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "first", "second", etc. in the specification of the present invention are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] According to an embodiment of the present invention, a method for merging physical examination conclusions is provided, such as Figure 1 As shown, it includes the following steps 101 to 103: Step 101: Obtain a physical examination report and extract conclusion words from the physical examination report.

[0021] In this step, the physical examination report to be merged can be obtained from the terminal, and then the abnormal conclusion words can be extracted based on the department summary in the physical examination report.

[0022] Step 102: construct a prompt based on the conclusion word, and input the prompt into the adjusted model, so that the model can determine the standard conclusion word corresponding to the conclusion word from the vocabulary based on the prompt.

[0023] In this step, the large model can be trained and fine-tuned in advance so that after fine-tuning, the standard conclusion words of the input physical examination report can be predicted. During prediction, the large model can be used to match the standard conclusion words mapped to the extracted abnormal conclusion words in the mapping relationship library.

[0024] Before prediction through a large model, a mapping relationship library between conclusion words and standard conclusion words can be constructed, in which the mapping relationships between different conclusion words and standard conclusion words are stored.

[0025] The standard conclusion words can be stored separately in the annotation vocabulary. When determining the standard conclusion words, the abnormal conclusion words can be extracted from the department summary content in the physical examination report sample based on the large model. The position words and degree words can be removed during the extraction. For example, "upper lobe nodule" can be used to extract the word "pulmonary nodule". The extracted abnormal conclusion words can then be corrected to standard conclusion words through manual correction. The corrected standard conclusion words can be stored in the standard vocabulary. Then, when constructing the mapping relationship, the standard conclusion words can be selected from the standard vocabulary.

[0026] Step 103: Utilize a merging rule engine to merge the standard conclusion words according to a specified merging rule.

[0027] As an optional implementation method of this embodiment, standard conclusion words are merged according to multiple sub-merge rules in different merge rules, wherein the merge rules include symptom merge rules, human system structure information merge rules, and department information merge rules; the symptom merge rules include sub-merge rules configured according to different diseases; the human system structure information merge rules include sub-merge rules defined according to different systems of the human body; the department information merge rules include sub-merge rules defined according to hospital departments; each of the sub-merge rules is associated with multiple standard words; wherein each merge rule has a different priority, and when merging, it is determined whether the standard conclusion word hits the sub-merge rule in the current merge rule; if the standard conclusion word does not hit the sub-merge rule in the current merge rule, then the sub-merge rule of the next merge rule is matched in order of priority; if the current sub-merge rule is hit, then the merge is performed.

[0028] In the above optional implementation, the merging rules may include three categories: monistic merging rules, namely, symptom merging rules, human body system merging rules, and department merging rules. Each rule includes multiple sub-merging rules, and each sub-merging rule is associated with a standard word set, and the standard word set includes multiple standard words. Exemplarily, the monistic merging rules include symptom merging rules: abnormal conclusions with high disease relevance or complications caused by the disease will be merged together. The human body system structure information merging rules include merging rules for the musculoskeletal system, nervous system, endocrine system, circulatory system, respiratory system, digestive system, urinary system, and reproductive system. The department information merging rule is to merge abnormal conclusions of the same hospital department, such as ophthalmology, otolaryngology, etc.

[0029] Symptom merging rules include but are not limited to hypertension sub-merging rules, diabetes sub-merging rules, blood lipid sub-merging rules, etc., among which hypertension sub-merging rules can include a word set consisting of standard words such as hypertension, bilateral carotid artery sclerosis, and vertebral artery tortuosity; diabetes sub-merging rules can include a word set consisting of standard words such as diabetes, normal high fasting blood sugar, and increased glycosylated hemoglobin; blood lipid sub-merging rules are associated with a word set consisting of standard words such as hypertriglyceridemia, hyperlipidemia, and aortic sclerosis. Human body system merging rules can include respiratory system sub-merging rules, digestive system sub-merging rules, etc., among which respiratory system sub-merging rules include a word set consisting of standard words such as chronic pneumonia, bronchial diseases, and lung nodules; digestive system sub-merging rules include a word set consisting of standard words such as fecal occult blood test positive and chronic non-atrophic gastritis. Department sub-merging rules include a word set consisting of standard words such as ophthalmology and stomatology, among which ophthalmology includes a word set consisting of standard words such as corneal edema and cataract; stomatology includes a word set consisting of standard words such as dental calculus, dental caries, and tooth loss.

[0030] Furthermore, each merge rule sets a priority. The higher the priority, the higher the matching order. The priority relationship is as follows: the monism merge rule has a higher priority than the human body system merge rule, and the human body system merge rule has a higher priority than the department merge rule. The obtained standardized conclusion words are matched and merged according to the priority of the merge rule. The ones with higher priority are merged first. If the standard conclusion word does not hit the current merge rule, it will be postponed to match the next merge rule until the match is successful or all merge rules are matched.

[0031] As an optional implementation of this embodiment, judging whether the standard conclusion word hits the sub-merge rule in the current merge rule during merging includes: judging whether the standard conclusion word hits the standard word associated with the sub-merge rule in the current rule.

[0032] In this optional implementation, since the sub-merge rule is associated with a standard word set, the standard conclusion word is matched with the standard word.

[0033] As an optional implementation method of this embodiment, after determining whether a hit is made, for the same sub-rule in the same rule, multiple standard conclusion words that hit multiple standard words are merged, wherein the conclusion words corresponding to the standard conclusion words are merged during the merging.

[0034] In this optional implementation, for the case where the same sub-rule has standard conclusion words that hit multiple standard words, the conclusion words are merged. The merging method is to merge the conclusion words corresponding to the standard conclusion words when they are hit, such as splicing the conclusion words through connectors.

[0035] For example, if the two standard conclusion words are lung nodules and emphysema, and the two standard conclusion words can simultaneously hit the standard words of the respiratory system sub-merge rule (a sub-merge rule in the human body system merge rule), then the corresponding conclusion words of the small nodule les in the left lower lobe of the lung, considering the Lu-RADS2 category and the paraseptal emphysema of the left upper lung, are spliced ​​as the final merged result.

[0036] As an optional implementation method of this embodiment, for the same sub-rule in the same rule, if the number of standard conclusion words that hit the standard word is one, the conclusion word corresponding to the standard conclusion word is directly used as the result.

[0037] In this optional implementation, for the same sub-rule, if the number of hits is one instead of multiple, then the conclusion word corresponding to the standard conclusion word can be directly determined as the final result without involving the merging under the sub-rule.

[0038] As an optional implementation method of this embodiment, when the model is adjusted: obtain a physical examination report sample to extract abnormal conclusion words from the sample; construct a prompt based on the abnormal conclusion words, and use the prompt as the input of the model; construct an output based on the standard conclusion words mapped to the abnormal conclusion words; and train the model using the input and the output.

[0039] In this optional implementation, each piece of training data consists of an input and an output. The input is generated by a prompt template and a set of conclusion words, and the output is generated by an output template and the standard conclusion words corresponding to the set of conclusion words. When constructing training data, since it is necessary to determine the input and output, the mapping relationship between the conclusion words and the standard conclusion words in the mapping relationship library can be used as a reference to implement the construction of training data. Figure 2 Schematic diagram of the indicated conclusion words and standard conclusion words.

[0040] For example, take a set of conclusion words: multiple lung nodules, consider LU-RADS2-3S category; multiple gallbladder stones; according to the mapping relationship, the corresponding standardized conclusion words are: lung nodules; gallbladder stones. The input data can be: You are an excellent chief inspector, and now you find conclusion words separated by | in the general inspection report. You need to refine the description of abnormal items into standard conclusion words that conform to medical knowledge habits. Standard conclusion words should have no position information, no quantifiers, and no modifiers. Conclusion words: multiple lung nodules LU-RADS2-3S category; multiple gallbladder stones. What are the standard conclusion words for these conclusion words? The result is returned in jsonArray format data, with the JSON object key as the conclusion word and the value as the standard conclusion word. The corresponding output data is as follows: [{"multiple lung nodules LU-RADS2-3S category":"lung nodules"},{"multiple gallbladder stones":"gallbladder stones"}].

[0041] After training and adjustment, the big model can be deployed on the server side and provide services to the outside world in the form of API. By calling the big model API, the conclusion words in the physical examination results in the physical examination report are standardized to obtain standardized conclusion words. The mapping relationship between the conclusion words and the standard conclusion words is stored in the database, which plays a role in caching and facilitating manual proofreading in the later stage.

[0042] refer to Figure 3 The system architecture applicable to the method of this embodiment is illustrated, including a large model fine-tuning module, a large model service module, a conclusion intelligent merging module, and a merging rule engine module. When the conclusion is intelligently merged, the LLM service can be called to extract multiple conclusion words in the physical examination report, and then the LLM service can be called to determine multiple standard conclusion words corresponding to the multiple conclusion words; in the merging rule engine, the multiple standard conclusion words are merged according to the merging rules and the final merged conclusion is output.

[0043] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] According to an embodiment of the present invention, a physical examination conclusion merging device is also provided, including: a conclusion word extraction unit, configured to obtain a physical examination report and extract conclusion words in the physical examination report; a prediction unit, configured to construct prompts based on the conclusion words, and input the prompts into an adjusted model, so that the model can determine the standard conclusion words corresponding to the conclusion words from the vocabulary based on the prompts; a merging unit, configured to use a merging rule engine to merge the standard conclusion words according to specified merging rules.

[0045] As an optional implementation method of this embodiment, when the model is adjusted: obtain a physical examination report sample to extract abnormal conclusion words from the sample; construct a prompt based on the abnormal conclusion words, and use the prompt as the input of the model; construct an output based on the standard conclusion words mapped to the abnormal conclusion words; and train the model using the input and the output.

[0046] As an optional implementation method of this embodiment, the merging unit is configured to: merge standard conclusion words according to multiple sub-merge rules in different merging rules, wherein the merging rules include symptom merging rules, human system structure information merging rules, and department information merging rules; the symptom merging rules include sub-merge rules configured according to different diseases; the human system structure information merging rules include sub-merge rules defined according to different systems of the human body; the department information merging rules include sub-merge rules defined according to hospital departments; each of the sub-merge rules is associated with multiple standard words; wherein each merging rule has a different priority, and when merging, it is judged whether the standard conclusion word hits the sub-merge rule in the current merging rule; if the standard conclusion word does not hit the sub-merge rule in the current merging rule, then the sub-merge rule of the next merging rule is matched in order of priority; if the current sub-merge rule is hit, then the merge is performed.

[0047] As an optional implementation of this embodiment, judging whether the standard conclusion word hits the sub-merge rule in the current merge rule during merging includes: judging whether the standard conclusion word hits the standard associated with the sub-merge rule in the current rule.

[0048] As an optional implementation method of this embodiment, after determining whether a hit is made, for the same sub-rule in the same rule, multiple standard conclusion words that hit multiple standard words are merged, wherein the conclusion words corresponding to the standard conclusion words are merged during the merging.

[0049] As an optional implementation method of this embodiment, for the same sub-rule in the same rule, if the number of standard conclusion words that hit the standard word is one, the conclusion word corresponding to the standard conclusion word is directly used as the result.

[0050] According to an embodiment of the present invention, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the object method described in any of the above embodiments when executing.

[0051] According to an embodiment of the present invention, the present invention further provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the object matching method described in any of the above embodiments when executed.

[0052] According to an embodiment of the present invention, the present invention further provides a computer program product, which can implement the method described in any of the above embodiments when executed by a processor.

[0053] Figure 4A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0054] like Figure 4 As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0055] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0056] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method described above may be performed.

[0057] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0058] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0059] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims

1. A method for merging physical examination conclusions, characterized in that: include: Obtaining a physical examination report and extracting conclusion words from the physical examination report; constructing a prompt based on the conclusion word, and inputting the prompt into the adjusted model, so that the model can determine a standard conclusion word corresponding to the conclusion word from a word library based on the prompt; The standard conclusion words are merged according to the specified merging rules using a merging rule engine.

2. The method for merging physical examination conclusions according to claim 1, characterized in that: When the model is adjusted: obtaining a sample of a physical examination report to extract abnormal conclusion words from the sample; constructing a prompt based on the abnormal conclusion word, and using the prompt as an input to the model; Constructing an output based on the standard conclusion words mapped to the abnormal conclusion words; The model is trained using the input and the output.

3. The method for merging physical examination conclusions according to claim 1, characterized in that: Using the merging rule engine to merge the standard conclusion words according to the specified merging rules includes: The standard conclusion words are merged according to multiple sub-merge rules in different merge rules, wherein the merge rules include a symptom merge rule, a human system structure information merge rule, and a department information merge rule; the symptom merge rule includes sub-merge rules configured according to different diseases; the human system structure information merge rule includes sub-merge rules defined according to different human systems; the department information merge rule includes sub-merge rules defined according to hospital departments; each of the sub-merge rules is associated with multiple standard words; Among them, each merging rule has a different priority. When merging, it is judged whether the standard conclusion word hits the sub-merging rule in the current merging rule; if the standard conclusion word does not hit the sub-merging rule in the current merging rule, the sub-merging rule of the next merging rule is matched in order of priority; if it hits the current sub-merging rule, the merge is performed.

4. The method for merging physical examination conclusions according to claim 3, characterized in that: When merging, judging whether the standard conclusion word hits the sub-merge rule in the current merge rule includes: judging whether the standard conclusion word hits the standard word associated with the sub-merge rule in the current rule.

5. The method for merging physical examination conclusions according to claim 4, characterized in that: The method further comprises: After determining whether a hit is found, for the same sub-rule in the same rule, multiple standard conclusion words that hit multiple standard words are merged, wherein the conclusion words corresponding to the standard conclusion words are merged during the merging.

6. The method for merging physical examination conclusions according to claim 4, characterized in that: For the same sub-rule in the same rule, if the number of standard conclusion words that hit the standard word is one, the conclusion word corresponding to the standard conclusion word is directly taken as the result.

7. A physical examination conclusion merging device, characterized in that: include: A conclusion word extraction unit is configured to obtain a physical examination report and extract conclusion words in the physical examination report; a prediction unit configured to construct a prompt based on the conclusion word, and input the prompt into the adjusted model, so that the model can determine a standard conclusion word corresponding to the conclusion word from a word library based on the prompt; The merging unit is configured to use a merging rule engine to merge the standard conclusion words according to a specified merging rule.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the physical examination conclusion merging method described in any one of claims 1-6.

9. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the physical examination conclusion merging method described in any one of claims 1-6.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the method for merging physical examination conclusions according to any one of claims 1 to 6.

Images