CN115840800B - Patient information matching method, system, computer and readable storage medium - Google Patents
Patient information matching method, system, computer and readable storage medium Download PDFInfo
- Publication number
- CN115840800B CN115840800B CN202310167353.XA CN202310167353A CN115840800B CN 115840800 B CN115840800 B CN 115840800B CN 202310167353 A CN202310167353 A CN 202310167353A CN 115840800 B CN115840800 B CN 115840800B
- Authority
- CN
- China
- Prior art keywords
- patient information
- target data
- data element
- matching degree
- phrases
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a patient information matching method, a system, a computer and a readable storage medium, wherein the method comprises the following steps: retrieving stock patient information similar to actual patient information and identifying a plurality of data elements contained therein; sequentially carrying out forward maximum step segmentation and reverse maximum step segmentation on a first target data element in actual patient information and a second target data element in stock patient information, and respectively calculating a first matching degree value generated under the forward maximum step segmentation and a second matching degree value generated under the reverse maximum step segmentation of the first target data element and the second target data element; judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not; if yes, the stock patient information is judged to be matched with the actual patient information. By the method, the stock patient information corresponding to the actual patient information received in real time can be accurately matched, and the matching efficiency of the patient information is greatly improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a patient information matching method, system, computer and readable storage medium.
Background
Hospitals are medical institutions taking the rescue and the rest as main targets for developing necessary medical examination, treatment measures, nursing technology, diagnosis receiving service, rehabilitation equipment, rescue transportation and other services for patients according to laws and regulations and industry specifications, and service objects of the medical institutions comprise symptomatic patients and wounded persons and old people who cannot be self-care or are limited in activity and have medical care dependence.
Most of the prior art can apply an information query system, wherein most of the prior information query system is applied with a main index matching strategy of a patient for matching needed patient information in real time.
However, the existing main index matching strategy of the patient mainly uses an equal matching method, namely, each data element of the incoming patient object is compared with the existing patient information one by one, if the comparison result reaches a certain threshold value, the incoming patient object and the existing patient information are considered to belong to the same patient, otherwise, the incoming patient object is considered to be a new patient, so that the existing main index matching strategy of the patient is only suitable for inquiring digital data elements, such as identity card numbers, mobile phone numbers and the like, but the effect is poor when inquiring literal data elements such as names, home addresses, contact addresses, company names and the like, thereby being unfavorable for inquiring the patient information.
Disclosure of Invention
Based on this, the present invention aims to provide a patient information matching method, system, computer and readable storage medium, so as to solve the problem that the patient main index matching strategy in the prior art is only suitable for querying digital data elements, such as identification card numbers, mobile phone numbers, etc., but has poor effect when querying literal data elements such as names, home addresses, contact addresses, company names, etc., thereby being unfavorable for querying patient information.
An embodiment of the present invention provides a patient information matching method, where the method includes:
when receiving actual patient information input by a user, retrieving stock patient information similar to the actual patient information in a preset database, and identifying a plurality of data elements respectively contained in the actual patient information and the stock patient information;
sequentially performing forward maximum step segmentation and reverse maximum step segmentation on a first target data element in the actual patient information and a second target data element in the stock patient information, and respectively calculating a first matching degree value generated by the first target data element and the second target data element under the forward maximum step segmentation and a second matching degree value generated by the second target data element under the reverse maximum step segmentation, wherein the first target data element corresponds to the second target data element;
Judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not;
and if the larger value between the first matching degree value and the second matching degree value is larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information.
The beneficial effects of the invention are as follows: when receiving actual patient information input by a user, retrieving stock patient information similar to the actual patient information from a preset database, and identifying a plurality of data elements respectively contained in the actual patient information and the stock patient information; further, sequentially performing forward maximum step segmentation and reverse maximum step segmentation on a first target data element in actual patient information and a second target data element in stock patient information, and respectively calculating a first matching degree value generated under the forward maximum step segmentation and a second matching degree value generated under the reverse maximum step segmentation of the first target data element and the second target data element; on the basis, judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not; specifically, if yes, it is determined that the current stock patient information matches the actual patient information. Through the mode, the stock patient information corresponding to the real patient information received in real time can be accurately matched through the matching results of the forward and reverse maximum step segmentation, so that the matching efficiency of the patient information is greatly improved, the generation of redundant data is reduced, and the medical experience of a patient is correspondingly improved.
Preferably, the step of sequentially performing forward maximum step segmentation and reverse maximum step segmentation on the first target data element in the actual patient information and the second target data element in the stock patient information includes:
when the forward maximum step segmentation is carried out on a first target data element in the actual patient information and a second target data element in the stock patient information, a first text string contained in the first target data element and a second text string contained in the second target data element are identified, and the first text string and the second text string are respectively scanned and segmented according to a first scanning sequence so as to split the first text string into a plurality of first phrases and split the second text string into a plurality of second phrases.
Preferably, the step of calculating a first matching degree value generated under the forward maximum step segmentation and a second matching degree value generated under the reverse maximum step segmentation of the first target data element and the second target data element respectively includes:
respectively correcting the first phrases and the second phrases through a preset synonym library and a preset address library to respectively generate corresponding first standard phrases and second standard phrases;
Identifying the total number of first characters contained in a plurality of first standard phrases, and detecting the first number of matched characters between the first standard phrases and the second standard phrases;
and calculating the first matching degree value according to the first character total number and the first matching character number.
Preferably, the step of sequentially performing forward maximum step segmentation and reverse maximum step segmentation on the first target data element in the actual patient information and the second target data element in the stock patient information includes:
when the first target data element in the actual patient information and the second target data element in the stock patient information are subjected to the reverse maximum step segmentation, the first text string contained in the first target data element and the second text string contained in the second target data element are identified, and the first text string and the second text string are respectively subjected to scanning segmentation according to a second scanning sequence so as to split the first text string into a plurality of third phrases and the second text string into a plurality of fourth phrases.
Preferably, the step of calculating a first matching degree value generated under the forward maximum step segmentation and a second matching degree value generated under the reverse maximum step segmentation of the first target data element and the second target data element respectively includes:
Correcting the third phrases and the fourth phrases through the preset synonym library and the preset address library respectively to generate corresponding third standard phrases and fourth standard phrases respectively;
identifying the total number of second characters contained in the third standard phrase, and detecting the number of second matched characters between the third standard phrase and the fourth standard phrase;
and calculating the second matching degree value according to the second character total number and the second matching character number.
Preferably, when the first target data element and the second target data element are each plural, the method further comprises:
calculating first matching degree average values generated by the first target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence, and calculating second matching degree average values generated by the second target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence;
judging whether the first matching degree average value is larger than the second matching degree average value or not;
if the first matching degree average value is larger than the second matching degree average value, judging whether the first matching degree average value is larger than the preset threshold value or not;
And if the first matching degree mean value is judged to be larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information.
Preferably, after the step of determining that the stock patient information matches the actual patient information, the method further comprises:
comparing the stock patient information with the actual patient information, and detecting distinguishing patient information between the stock patient information and the actual patient information;
judging whether the stored patient information stores the differential patient information or not;
and if the difference patient information is judged not to be stored in the stock patient information, correspondingly updating the difference patient information into the stock patient information so as to complete the real-time updating of the stock patient information.
A second aspect of an embodiment of the present invention proposes a patient information matching system, the system comprising:
the receiving module is used for retrieving stock patient information similar to the actual patient information from a preset database when receiving the actual patient information input by a user, and identifying a plurality of data elements respectively contained in the actual patient information and the stock patient information;
The calculation module is used for sequentially carrying out forward maximum step segmentation and reverse maximum step segmentation on a first target data element in the actual patient information and a second target data element in the stock patient information, and respectively calculating a first matching degree value generated by the first target data element and the second target data element under the forward maximum step segmentation and a second matching degree value generated by the second target data element under the reverse maximum step segmentation, wherein the first target data element corresponds to the second target data element;
the judging module is used for judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not;
and the execution module is used for judging that the stock patient information is matched with the actual patient information if judging that the larger value between the first matching degree value and the second matching degree value is larger than the preset threshold value.
In the patient information matching system, the calculation module is specifically configured to:
when the forward maximum step segmentation is carried out on a first target data element in the actual patient information and a second target data element in the stock patient information, a first text string contained in the first target data element and a second text string contained in the second target data element are identified, and the first text string and the second text string are respectively scanned and segmented according to a first scanning sequence so as to split the first text string into a plurality of first phrases and split the second text string into a plurality of second phrases.
In the patient information matching system, the computing module is further specifically configured to:
respectively correcting the first phrases and the second phrases through a preset synonym library and a preset address library to respectively generate corresponding first standard phrases and second standard phrases;
identifying the total number of first characters contained in a plurality of first standard phrases, and detecting the first number of matched characters between the first standard phrases and the second standard phrases;
and calculating the first matching degree value according to the first character total number and the first matching character number.
In the patient information matching system, the computing module is further specifically configured to:
when the first target data element in the actual patient information and the second target data element in the stock patient information are subjected to the reverse maximum step segmentation, the first text string contained in the first target data element and the second text string contained in the second target data element are identified, and the first text string and the second text string are respectively subjected to scanning segmentation according to a second scanning sequence so as to split the first text string into a plurality of third phrases and the second text string into a plurality of fourth phrases.
In the patient information matching system, the computing module is further specifically configured to:
correcting the third phrases and the fourth phrases through the preset synonym library and the preset address library respectively to generate corresponding third standard phrases and fourth standard phrases respectively;
identifying the total number of second characters contained in the third standard phrase, and detecting the number of second matched characters between the third standard phrase and the fourth standard phrase;
and calculating the second matching degree value according to the second character total number and the second matching character number.
In the above patient information matching system, when the first target data element and the second target data element are multiple, the patient information matching system further includes a processing module, where the processing module is specifically configured to:
calculating first matching degree average values generated by the first target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence, and calculating second matching degree average values generated by the second target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence;
Judging whether the first matching degree average value is larger than the second matching degree average value or not;
if the first matching degree average value is larger than the second matching degree average value, judging whether the first matching degree average value is larger than the preset threshold value or not;
and if the first matching degree mean value is judged to be larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information.
In the patient information matching system, the patient information matching system further comprises an updating module, wherein the updating module is specifically configured to:
comparing the stock patient information with the actual patient information, and detecting distinguishing patient information between the stock patient information and the actual patient information;
judging whether the stored patient information stores the differential patient information or not;
and if the difference patient information is judged not to be stored in the stock patient information, correspondingly updating the difference patient information into the stock patient information so as to complete the real-time updating of the stock patient information.
A third aspect of the embodiments of the present invention proposes a computer comprising a memory, a processor and a computer program stored on said memory and executable on said processor, said processor implementing a patient information matching method as described above when executing said computer program.
A fourth aspect of the embodiments of the present invention proposes a readable storage medium having stored thereon a computer program which, when executed by a processor, implements a patient information matching method as described above.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flowchart of a patient information matching method according to a first embodiment of the present invention;
fig. 2 is a block diagram of a patient information matching system according to a sixth embodiment of the present invention.
The invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
The existing main index matching strategy of the patient mainly uses an equal matching method, namely, each data element of the incoming patient object is compared with the existing patient information one by one, if the comparison result reaches a certain threshold value, the incoming patient object and the existing patient information are considered to belong to the same patient, otherwise, the incoming patient object is considered to be a new patient, so that the existing main index matching strategy of the patient is only suitable for inquiring digital data elements, such as identity card numbers, mobile phone numbers and the like, but has poor effect when inquiring literal data elements such as names, home addresses, contact addresses, company names and the like, thereby being unfavorable for inquiring the patient information.
Referring to fig. 1, a patient information matching method provided by a first embodiment of the present invention is shown, where the patient information matching method provided by the present embodiment can accurately match stock patient information corresponding to actual patient information received in real time through the matching results of forward and reverse maximum step word segmentation, so that the matching efficiency of patient information is greatly improved, the generation of redundant data is reduced, and the hospitalizing experience of a patient is correspondingly improved.
Specifically, the patient information matching method provided in the embodiment specifically includes the following steps:
step S10, when receiving actual patient information input by a user, retrieving stock patient information similar to the actual patient information from a preset database, and identifying a plurality of data elements respectively contained in the actual patient information and the stock patient information;
in particular, in the present embodiment, it should be first described that the patient information matching method provided in the present embodiment is specifically applied to a patient information query system of various medical institutions, and is used for simply and quickly matching required patient information in real time.
In addition, in this embodiment, it should be noted that, in the patient information query system of each medical institution, a database is preset for storing the diagnosis information of the patients who have been diagnosed, that is, a large amount of stock patient information is stored in the database, and the stock patient information is the existing patient information.
Therefore, in this step, it should be noted that, when the actual patient information input by the user is received in real time, specifically, the actual patient information may be one or more of "name", "home address", and "phone number" input by the current user, and on the basis of this, this step may further initially retrieve, in the preset database, the stored patient information similar to the actual patient information currently received in real time. It should be noted that, the present patient information may be the information that has been recorded before by the current user, or may be the patient information of other users, so it is necessary to further determine whether the present patient information matches the actual patient information input in real time by the current user.
Further, in this step, a plurality of data elements included in the current actual patient information and the current stock patient information may be identified, and specifically, the plurality of data elements may be data such as "home address", "patient name", and "phone number".
Step S20, sequentially carrying out forward maximum step segmentation and reverse maximum step segmentation on a first target data element in the actual patient information and a second target data element in the stock patient information, and respectively calculating a first matching degree value generated by the first target data element and the second target data element under the forward maximum step segmentation and a second matching degree value generated by the second target data element under the reverse maximum step segmentation, wherein the first target data element corresponds to the second target data element;
further, in this step, it should be noted that, in order to accurately determine whether the current actual patient information matches the current stock patient information, in this step, a first target data element is further selected in the current actual patient information, and a second target data element is selected in the current stock patient information correspondingly, where the first target data element corresponds to the second target data element, that is, both are the same type of data element, for example, both are "home address" data elements or both are "illness description" data elements.
Further, the step sequentially performs forward maximum step segmentation and reverse maximum step segmentation on a first target data element in the current actual patient information and a second target data element in the current stock patient information, and simultaneously calculates a first matching degree value generated by the current first target data element and the current second target data element under the forward maximum step segmentation, and correspondingly, a second matching degree value generated by the current second target data element under the reverse maximum step segmentation, wherein the first matching degree value and the second matching degree value are specific numerical values.
Step S30, judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not;
specifically, this step may further determine whether a larger value between the current first matching degree value and the current second matching degree value is greater than a preset threshold, for example, when the first matching degree value is greater than the second matching degree value, the current first matching degree value is compared with the preset threshold, and when the second matching degree value is greater than the first matching degree value, the current second matching degree value is compared with the preset threshold.
And step S40, if the larger value between the first matching degree value and the second matching degree value is larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information.
Finally, in this embodiment, it should be noted that, if the step determines that the larger value between the current first matching degree value and the current second matching degree value is greater than the preset threshold in real time, it is determined that the current stock patient information is matched with the current actual patient information, and correspondingly, if the step determines that the larger value between the current first matching degree value and the current second matching degree value is less than the preset threshold in real time, it is necessary to repeat the steps S10 to S30 until the larger value between the first matching degree value and the second matching degree value is greater than the preset threshold.
When the method is used, when the actual patient information input by a user is received, stock patient information similar to the actual patient information is searched in a preset database, and a plurality of data elements respectively contained in the actual patient information and the stock patient information are identified; further, sequentially performing forward maximum step segmentation and reverse maximum step segmentation on a first target data element in actual patient information and a second target data element in stock patient information, and respectively calculating a first matching degree value generated under the forward maximum step segmentation and a second matching degree value generated under the reverse maximum step segmentation of the first target data element and the second target data element; on the basis, judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not; specifically, if yes, it is determined that the current stock patient information matches the actual patient information. Through the mode, the stock patient information corresponding to the real patient information received in real time can be accurately matched through the matching results of the forward and reverse maximum step segmentation, so that the matching efficiency of the patient information is greatly improved, the generation of redundant data is reduced, and the medical experience of a patient is correspondingly improved.
It should be noted that the foregoing implementation procedure is only for illustrating the feasibility of the present application, but this does not represent that the patient information matching method of the present application is only one implementation procedure, and may be incorporated into the feasible implementation of the patient information matching method of the present application, as long as it can be implemented.
In summary, the patient information matching method provided by the embodiment of the invention can accurately match the stock patient information corresponding to the real patient information received in real time through the matching results of the forward and reverse maximum step segmentation, thereby greatly improving the matching efficiency of the patient information, reducing the generation of redundant data and correspondingly improving the hospitalizing experience of the patient.
The second embodiment of the present invention also provides a patient information matching method, which is different from the patient information matching method provided in the first embodiment in that:
specifically, in this embodiment, it should be noted that the step of sequentially performing the forward maximum step segmentation and the reverse maximum step segmentation on the first target data element in the actual patient information and the second target data element in the stock patient information includes:
When the forward maximum step segmentation is carried out on a first target data element in the actual patient information and a second target data element in the stock patient information, a first text string contained in the first target data element and a second text string contained in the second target data element are identified, and the first text string and the second text string are respectively scanned and segmented according to a first scanning sequence so as to split the first text string into a plurality of first phrases and split the second text string into a plurality of second phrases.
Specifically, in this embodiment, it should be noted that, when the foregoing forward maximum step word segmentation needs to be performed on the first target data element in the current actual patient information and the second target data element in the current stock patient information, this embodiment first identifies the first text string included in the current first target data element, and correspondingly identifies the second text string included in the current second target data element, and scans and segments the current first text string and the second text string according to the left-to-right order, so as to correspondingly split the current first text string into a plurality of first phrases, and split the current second text string into a plurality of second phrases.
Further, in this embodiment, for convenience of understanding, it should be noted that, for example, this embodiment takes a "home address" data element as an example to explain, specifically, for example, a first text string in a first target data element included in actual patient information obtained in this embodiment is "new Wu Ouling lake great road No. 200F zone No. 5 building" in Jiangsu province, correspondingly, a second text string in a second target data element included in stock patient information obtained in this embodiment is "new area rhombus great road No. 200 innovation garden No. 5 building" and, on this basis, scanning word segmentation is sequentially performed on the current first text string and the second text string from left to right, so that a forward maximum step word segmentation result obtained for the first text string is "Jiangsu province/no tin city/new Wu Ou/rhombus great road/No. 200/No. F/region/No. 5 building", and a corresponding forward maximum step word segmentation result obtained for the second text string is "No. tin/new area/rhombus/200/v/No. 200/innovation/v/5 building".
In this embodiment, it should be noted that the step of calculating the first matching degree value generated by the first target data element and the second target data element under the maximum forward step segmentation includes:
Respectively correcting the first phrases and the second phrases through a preset synonym library and a preset address library to respectively generate corresponding first standard phrases and second standard phrases;
identifying the total number of first characters contained in a plurality of first standard phrases, and detecting the first number of matched characters between the first standard phrases and the second standard phrases;
and calculating the first matching degree value according to the first character total number and the first matching character number.
Further, in this embodiment, it should be noted that, after the first phrase and the second phrase are sequentially obtained through the above steps, in order to further improve the accuracy of matching, in this embodiment, the current plurality of first phrases and the current plurality of second phrases are further modified respectively through a preset synonym library and a preset address library. Taking the address data element as an example, the original address information may lose administrative level, road, residential area and other information, so after the phrase is corrected by combining the synonym library and the address library, the lost administrative level, road, residential area and other information can be supplemented, thereby improving the matching rate of the data element and further achieving the purpose of prompting the matching rate of the patient information.
Specifically, in this embodiment, the current word groups in the first word group and the second word group are further subjected to leak detection and deficiency repair through the synonym word library and the address library, for example, when the obtained positive maximum step word segmentation result of the second text string is "no tin/new area/great water-chestnut lake channel/200/No. innovation garden/F/area/5/building", the embodiment corrects the positive maximum step word segmentation result of the current second text string into "Jiangsu province/no tin city/new area/great water-chestnut lake channel/200/No. innovation garden/F/area/5/building" through the synonym word library and the address library, so that the corresponding first standard word group and the second standard word group can be generated, thereby improving the subsequent calculation accuracy.
Furthermore, the embodiment further identifies the total number of the first characters included in the current first standard phrase, and at the same time, the embodiment further correspondingly detects the first matching character number between the current first standard phrase and the current second standard phrase, and finally, the required first matching degree value can be calculated only according to the obtained total number of the first characters and the first matching character number.
Specifically, in this embodiment, for convenience of understanding, it should be noted that, for example, the modified first standard phrase is "Jiangsu province/Wuxi city/New Wu Ou/Linghu Dadao/200/No. F/district/No. 5/building", and the corresponding modified second standard phrase is "Jiangsu province/Wuxi city/New district/Linghu Dadao/200/No. 1/Innovative garden/F/district/No. 5/building", where it should be noted that, it is generally considered that the single word of the word has limited effect and may affect the matching effect, so that the embodiment only counts the word of more than one word. Therefore, the total number of the first characters calculated in this embodiment is 22, and correspondingly, the number of the first matching characters calculated in this embodiment between the first standard phrase and the second standard phrase is 17, and the specific numerical value of the first matching degree value calculated in this embodiment is 77.3%.
It should be noted that, for the sake of brevity, the method according to the second embodiment of the present invention, which implements the same principle and some of the technical effects as the first embodiment, is not mentioned here, and reference is made to the corresponding content provided by the first embodiment.
In summary, the patient information matching method provided by the embodiment of the invention can accurately match the stock patient information corresponding to the real patient information received in real time through the matching results of the forward and reverse maximum step segmentation, thereby greatly improving the matching efficiency of the patient information, reducing the generation of redundant data and correspondingly improving the hospitalizing experience of the patient.
The third embodiment of the present invention also provides a patient information matching method, which is different from the patient information matching method provided in the first embodiment in that:
specifically, in this embodiment, it should be noted that the step of sequentially performing the forward maximum step segmentation and the reverse maximum step segmentation on the first target data element in the actual patient information and the second target data element in the stock patient information includes:
when the first target data element in the actual patient information and the second target data element in the stock patient information are subjected to the reverse maximum step segmentation, the first text string contained in the first target data element and the second text string contained in the second target data element are identified, and the first text string and the second text string are respectively subjected to scanning segmentation according to a second scanning sequence so as to split the first text string into a plurality of third phrases and the second text string into a plurality of fourth phrases.
Similarly, in this embodiment, it should be noted that, when the first target data element in the actual patient information and the second target data element in the stock patient information need to be segmented in the opposite maximum step, the present embodiment also identifies the first text string included in the current first target data element and the second text string included in the second target data element, and on this basis, scans and segments the first text string and the second text string in a right-to-left manner so as to correspondingly split the current first text string into a plurality of third phrases and split the current second text string into a plurality of fourth phrases.
Specifically, for example, the third phrase obtained in this embodiment is "Jiangsu province/Wuxi city/Xin Wu Ou/Linghu Dadao/No. 200/F area/No. 5 building", and the corresponding fourth phrase obtained is "Wuxi/Xin district/Linghu Dadao/No. 200/Innovative garden/F area/No. 5 building", so as to perform subsequent calculation.
In this embodiment, it should be noted that, the step of calculating the first matching degree value generated by the first target data element and the second target data element under the forward maximum step segmentation and the second matching degree value generated by the reverse maximum step segmentation includes:
Correcting the third phrases and the fourth phrases through the preset synonym library and the preset address library respectively to generate corresponding third standard phrases and fourth standard phrases respectively;
identifying the total number of second characters contained in the third standard phrase, and detecting the number of second matched characters between the third standard phrase and the fourth standard phrase;
and calculating the second matching degree value according to the second character total number and the second matching character number.
Further, in this embodiment, it should be noted that, similarly, in this embodiment, the current third phrase and the fourth phrase are modified by the synonym library and the address library to generate a corresponding third standard phrase and fourth standard phrase. Specifically, for example, the third standard phrase obtained in this embodiment is "Jiangsu province/Wuxi city/Xin Wu Ou/Ling lake Dadao/No. 200/F area/No. 5 building", and the corresponding fourth standard phrase obtained is "Jiangsu province/Wuxi city/Xin district/Ling lake Dadao/No. 200/Innovative garden/F area/No. 5 building".
Based on this, the embodiment further recognizes that the total number of the second characters included in the current third standard phrase is 22, and correspondingly, the embodiment detects that the number of the second matching characters between the current third standard phrase and the current fourth standard phrase is 21, and then the second matching degree value calculated according to the total number of the current second characters and the number of the second matching characters is 95.5%.
It should be noted that, for the sake of brevity, the principles and some technical effects of the method according to the third embodiment of the present invention are the same as those of the first embodiment, and reference should be made to the corresponding matters provided in the first embodiment for the description of the present invention.
In summary, the patient information matching method provided by the embodiment of the invention can accurately match the stock patient information corresponding to the real patient information received in real time through the matching results of the forward and reverse maximum step segmentation, thereby greatly improving the matching efficiency of the patient information, reducing the generation of redundant data and correspondingly improving the hospitalizing experience of the patient.
The fourth embodiment of the present invention also provides a patient information matching method, which is different from the patient information matching method provided in the first embodiment in that:
specifically, in this embodiment, it should be noted that, when the first target data element and the second target data element are multiple, the method further includes:
calculating first matching degree average values generated by the first target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence, and calculating second matching degree average values generated by the second target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence;
Judging whether the first matching degree average value is larger than the second matching degree average value or not;
if the first matching degree average value is larger than the second matching degree average value, judging whether the first matching degree average value is larger than the preset threshold value or not;
and if the first matching degree mean value is judged to be larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information.
Specifically, in this embodiment, it should be noted that, when a plurality of first target data elements and a plurality of second target data elements need to be compared at the same time, the embodiment sequentially calculates, in the above manner, a first matching degree value average value generated by a current plurality of first target data elements under the above-mentioned forward maximum step segmentation and the above-mentioned reverse maximum step segmentation, and simultaneously correspondingly calculates a second matching degree average value generated by a current plurality of second target data elements under the above-mentioned forward maximum step segmentation and the reverse maximum step segmentation, and further determines whether the current first matching degree average value is greater than the current second matching degree average value based on this basis, and specifically, if it is determined that the current first matching degree average value is greater than the current second matching degree average value, determines whether the current first matching degree average value is greater than the preset threshold; further, if the current first matching degree mean value is judged to be larger than the preset threshold value, the stock patient information is judged to be matched with the actual patient information.
It should be noted that, for the sake of brevity, the method according to the fourth embodiment of the present invention, which implements the same principle and some of the technical effects as those of the first embodiment, may refer to the corresponding content provided by the first embodiment.
In summary, the patient information matching method provided by the embodiment of the invention can accurately match the stock patient information corresponding to the real patient information received in real time through the matching results of the forward and reverse maximum step segmentation, thereby greatly improving the matching efficiency of the patient information, reducing the generation of redundant data and correspondingly improving the hospitalizing experience of the patient.
The fifth embodiment of the present invention also provides a patient information matching method, which is different from the patient information matching method provided in the first embodiment in that:
specifically, in this embodiment, it should be noted that, after the step of determining that the stock patient information matches the actual patient information, the method further includes:
comparing the stock patient information with the actual patient information, and detecting distinguishing patient information between the stock patient information and the actual patient information;
Judging whether the stored patient information stores the differential patient information or not;
and if the difference patient information is judged not to be stored in the stock patient information, correspondingly updating the difference patient information into the stock patient information so as to complete the real-time updating of the stock patient information.
Specifically, in this embodiment, it should be noted that, in order to be able to update the stock patient information in the database in real time, this embodiment compares the actual patient information received in real time with the stock patient information already stored, and at the same time, correspondingly detects the differential patient information between the current stock patient information and the current actual patient information, and further determines whether the current stock patient information stores the current differential patient information, and specifically, if it is determined in real time that the current stock patient information does not store the current differential patient information, it is necessary to correspondingly update the current differential patient information to the current stock patient information, so as to complete the real-time update of the current stock patient information.
Correspondingly, if the current stock patient information is judged to be stored with the current distinguishing patient information in real time, the current stock patient information does not need to be updated.
It should be noted that, for the sake of brevity, the method according to the fifth embodiment of the present invention, which implements the same principle and some of the technical effects as those of the first embodiment, may refer to the corresponding content provided by the first embodiment.
In summary, the patient information matching method provided by the embodiment of the invention can accurately match the stock patient information corresponding to the real patient information received in real time through the matching results of the forward and reverse maximum step segmentation, thereby greatly improving the matching efficiency of the patient information, reducing the generation of redundant data and correspondingly improving the hospitalizing experience of the patient.
Referring to fig. 2, a patient information matching system according to a sixth embodiment of the present invention is shown, the system includes:
a receiving module 12, configured to, when receiving actual patient information input by a user, retrieve stock patient information similar to the actual patient information in a preset database, and identify a plurality of data elements respectively included in the actual patient information and the stock patient information;
the calculation module 22 is configured to sequentially perform a forward maximum step segmentation and a reverse maximum step segmentation on a first target data element in the actual patient information and a second target data element in the stock patient information, and calculate a first matching degree value generated by the first target data element and the second target data element under the forward maximum step segmentation and a second matching degree value generated by the second target data element under the reverse maximum step segmentation, where the first target data element corresponds to the second target data element;
A judging module 32, configured to judge whether a larger value between the first matching degree value and the second matching degree value is greater than a preset threshold;
and an execution module 42, configured to determine that the stock patient information matches the actual patient information if it is determined that the larger value between the first matching degree value and the second matching degree value is greater than the preset threshold.
In the patient information matching system, the computing module 22 is specifically configured to:
when the forward maximum step segmentation is carried out on a first target data element in the actual patient information and a second target data element in the stock patient information, a first text string contained in the first target data element and a second text string contained in the second target data element are identified, and the first text string and the second text string are respectively scanned and segmented according to a first scanning sequence so as to split the first text string into a plurality of first phrases and split the second text string into a plurality of second phrases.
In the patient information matching system, the calculating module 22 is further specifically configured to:
respectively correcting the first phrases and the second phrases through a preset synonym library and a preset address library to respectively generate corresponding first standard phrases and second standard phrases;
Identifying the total number of first characters contained in a plurality of first standard phrases, and detecting the first number of matched characters between the first standard phrases and the second standard phrases;
and calculating the first matching degree value according to the first character total number and the first matching character number.
In the patient information matching system, the calculating module 22 is further specifically configured to:
when the first target data element in the actual patient information and the second target data element in the stock patient information are subjected to the reverse maximum step segmentation, the first text string contained in the first target data element and the second text string contained in the second target data element are identified, and the first text string and the second text string are respectively subjected to scanning segmentation according to a second scanning sequence so as to split the first text string into a plurality of third phrases and the second text string into a plurality of fourth phrases.
In the patient information matching system, the calculating module 22 is further specifically configured to:
correcting the third phrases and the fourth phrases through the preset synonym library and the preset address library respectively to generate corresponding third standard phrases and fourth standard phrases respectively;
Identifying the total number of second characters contained in the third standard phrase, and detecting the number of second matched characters between the third standard phrase and the fourth standard phrase;
and calculating the second matching degree value according to the second character total number and the second matching character number.
In the above patient information matching system, when the first target data element and the second target data element are multiple, the patient information matching system further includes a processing module 52, where the processing module 52 is specifically configured to:
calculating first matching degree average values generated by the first target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence, and calculating second matching degree average values generated by the second target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence;
judging whether the first matching degree average value is larger than the second matching degree average value or not;
if the first matching degree average value is larger than the second matching degree average value, judging whether the first matching degree average value is larger than the preset threshold value or not;
and if the first matching degree mean value is judged to be larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information.
In the above patient information matching system, the patient information matching system further includes an update module 62, where the update module 62 is specifically configured to:
comparing the stock patient information with the actual patient information, and detecting distinguishing patient information between the stock patient information and the actual patient information;
judging whether the stored patient information stores the differential patient information or not;
and if the difference patient information is judged not to be stored in the stock patient information, correspondingly updating the difference patient information into the stock patient information so as to complete the real-time updating of the stock patient information.
A seventh embodiment of the present invention provides a computer including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the patient information matching method provided in the above embodiment when executing the computer program.
An eighth embodiment of the present invention provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the patient information matching method provided by the above embodiments.
In summary, the patient information matching method, system, computer and readable storage medium provided by the embodiments of the present invention can accurately match stock patient information corresponding to real patient information received in real time through the matching results of forward and reverse maximum step word segmentation, thereby greatly improving the matching efficiency of patient information, reducing the generation of redundant data, and correspondingly improving the hospitalizing experience of patients.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (6)
1. A method of matching patient information, the method comprising:
When receiving actual patient information input by a user, retrieving stock patient information similar to the actual patient information in a preset database, and identifying a plurality of data elements respectively contained in the actual patient information and the stock patient information;
sequentially performing forward maximum step segmentation and reverse maximum step segmentation on a first target data element in the actual patient information and a second target data element in the stock patient information, and respectively calculating a first matching degree value generated by the first target data element and the second target data element under the forward maximum step segmentation and a second matching degree value generated by the second target data element under the reverse maximum step segmentation, wherein the first target data element corresponds to the second target data element;
judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not;
if the larger value between the first matching degree value and the second matching degree value is larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information;
the step of sequentially performing forward maximum step segmentation and reverse maximum step segmentation on the first target data element in the actual patient information and the second target data element in the stock patient information comprises the following steps:
When the forward maximum step segmentation is carried out on a first target data element in the actual patient information and a second target data element in the stock patient information, a first text string contained in the first target data element and a second text string contained in the second target data element are identified, and the first text string and the second text string are respectively scanned and segmented according to a first scanning sequence so as to split the first text string into a plurality of first phrases and split the second text string into a plurality of second phrases;
the step of calculating the first matching degree value generated by the first target data element and the second target data element under the maximum forward step segmentation and the second matching degree value generated by the maximum reverse step segmentation respectively comprises the following steps:
respectively correcting the first phrases and the second phrases through a preset synonym library and a preset address library to respectively generate corresponding first standard phrases and second standard phrases;
identifying the total number of first characters contained in a plurality of first standard phrases, and detecting the first number of matched characters between the first standard phrases and the second standard phrases, wherein only word segmentation of more than one word is counted;
Calculating the first matching degree value according to the first character total number and the first matching character number;
the step of sequentially performing forward maximum step segmentation and reverse maximum step segmentation on the first target data element in the actual patient information and the second target data element in the stock patient information comprises the following steps:
when the first target data element in the actual patient information and the second target data element in the stock patient information are subjected to the reverse maximum step segmentation, identifying the first text string contained in the first target data element and the second text string contained in the second target data element, and respectively carrying out scanning segmentation on the first text string and the second text string according to a second scanning sequence so as to split the first text string into a plurality of third phrases and split the second text string into a plurality of fourth phrases;
the step of calculating the first matching degree value generated by the first target data element and the second target data element under the maximum forward step segmentation and the second matching degree value generated by the maximum reverse step segmentation respectively comprises the following steps:
Correcting the third phrases and the fourth phrases through the preset synonym library and the preset address library respectively to generate corresponding third standard phrases and fourth standard phrases respectively;
identifying the total number of second characters contained in the third standard phrase, and detecting the number of second matched characters between the third standard phrase and the fourth standard phrase, wherein only word segmentation of more than one word is counted;
and calculating the second matching degree value according to the second character total number and the second matching character number.
2. The patient information matching method according to claim 1, wherein: when the first target data element and the second target data element are each plural, the method further comprises:
calculating first matching degree average values generated by the first target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence, and calculating second matching degree average values generated by the second target data elements under the forward maximum step segmentation and the reverse maximum step segmentation in sequence;
judging whether the first matching degree average value is larger than the second matching degree average value or not;
If the first matching degree average value is larger than the second matching degree average value, judging whether the first matching degree average value is larger than the preset threshold value or not;
and if the first matching degree mean value is judged to be larger than the preset threshold value, judging that the stock patient information is matched with the actual patient information.
3. The patient information matching method according to claim 1, wherein: after the step of determining that the stock patient information matches the actual patient information, the method further comprises:
comparing the stock patient information with the actual patient information, and detecting distinguishing patient information between the stock patient information and the actual patient information;
judging whether the stored patient information stores the differential patient information or not;
and if the difference patient information is judged not to be stored in the stock patient information, correspondingly updating the difference patient information into the stock patient information so as to complete the real-time updating of the stock patient information.
4. A patient information matching system, the system comprising:
the receiving module is used for retrieving stock patient information similar to the actual patient information from a preset database when receiving the actual patient information input by a user, and identifying a plurality of data elements respectively contained in the actual patient information and the stock patient information;
The calculation module is used for sequentially carrying out forward maximum step segmentation and reverse maximum step segmentation on a first target data element in the actual patient information and a second target data element in the stock patient information, and respectively calculating a first matching degree value generated by the first target data element and the second target data element under the forward maximum step segmentation and a second matching degree value generated by the second target data element under the reverse maximum step segmentation, wherein the first target data element corresponds to the second target data element;
the judging module is used for judging whether a larger value between the first matching degree value and the second matching degree value is larger than a preset threshold value or not;
the execution module is used for judging that the stock patient information is matched with the actual patient information if judging that the larger value between the first matching degree value and the second matching degree value is larger than the preset threshold value;
in the patient information matching system, the calculation module is specifically configured to:
when the forward maximum step segmentation is carried out on a first target data element in the actual patient information and a second target data element in the stock patient information, a first text string contained in the first target data element and a second text string contained in the second target data element are identified, and the first text string and the second text string are respectively scanned and segmented according to a first scanning sequence so as to split the first text string into a plurality of first phrases and split the second text string into a plurality of second phrases;
In the patient information matching system, the computing module is further specifically configured to:
respectively correcting the first phrases and the second phrases through a preset synonym library and a preset address library to respectively generate corresponding first standard phrases and second standard phrases;
identifying the total number of first characters contained in a plurality of first standard phrases, and detecting the first number of matched characters between the first standard phrases and the second standard phrases;
and calculating the first matching degree value according to the first character total number and the first matching character number.
In the patient information matching system, the computing module is further specifically configured to:
when the first target data element in the actual patient information and the second target data element in the stock patient information are subjected to the reverse maximum step segmentation, the first text string contained in the first target data element and the second text string contained in the second target data element are identified, and the first text string and the second text string are respectively subjected to scanning segmentation according to a second scanning sequence so as to split the first text string into a plurality of third phrases and the second text string into a plurality of fourth phrases.
In the patient information matching system, the computing module is further specifically configured to:
correcting the third phrases and the fourth phrases through the preset synonym library and the preset address library respectively to generate corresponding third standard phrases and fourth standard phrases respectively;
identifying the total number of second characters contained in the third standard phrase, and detecting the number of second matched characters between the third standard phrase and the fourth standard phrase;
and calculating the second matching degree value according to the second character total number and the second matching character number.
5. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the patient information matching method of any one of claims 1 to 3 when the computer program is executed.
6. A readable storage medium having stored thereon a computer program, which when executed by a processor implements the patient information matching method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310167353.XA CN115840800B (en) | 2023-02-27 | 2023-02-27 | Patient information matching method, system, computer and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310167353.XA CN115840800B (en) | 2023-02-27 | 2023-02-27 | Patient information matching method, system, computer and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115840800A CN115840800A (en) | 2023-03-24 |
| CN115840800B true CN115840800B (en) | 2023-05-12 |
Family
ID=85580208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310167353.XA Active CN115840800B (en) | 2023-02-27 | 2023-02-27 | Patient information matching method, system, computer and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115840800B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116825265A (en) * | 2023-08-29 | 2023-09-29 | 先临三维科技股份有限公司 | Treatment record processing method and device, electronic equipment and storage medium |
| CN117912624A (en) * | 2024-03-15 | 2024-04-19 | 江西曼荼罗软件有限公司 | Electronic medical record sharing method and system |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727535A (en) * | 2008-10-30 | 2010-06-09 | 北大方正集团有限公司 | Cross indexing method for patients crossing system and system thereof |
| CN105608113B (en) * | 2015-12-10 | 2018-09-11 | 北京奇虎科技有限公司 | Judge the method and device of POI data in text |
| CN105893353B (en) * | 2016-04-20 | 2018-10-26 | 广东万丈金数信息技术股份有限公司 | Word segmentation method and word segmentation system |
| CN108664494A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method, apparatus, electronic equipment and the storage medium of Data Matching |
| CN108628811B (en) * | 2018-04-10 | 2022-04-12 | 北京京东尚科信息技术有限公司 | Address text matching method and device |
| CN109344263B (en) * | 2018-08-01 | 2022-07-19 | 昆明理工大学 | Address matching method |
| CN111160014B (en) * | 2019-12-03 | 2023-05-16 | 北京博瑞彤芸科技股份有限公司 | Intelligent word segmentation method |
| CN112612863B (en) * | 2020-12-23 | 2023-03-31 | 武汉大学 | Address matching method and system based on Chinese word segmentation device |
| CN113065057B (en) * | 2021-04-14 | 2022-12-02 | 上海浦东发展银行股份有限公司 | Data information authenticity verification method, device, equipment and storage medium |
| CN115238062A (en) * | 2022-07-21 | 2022-10-25 | 上海国际知识产权运营管理有限公司 | Technical property right matching method and system |
-
2023
- 2023-02-27 CN CN202310167353.XA patent/CN115840800B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115840800A (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115840800B (en) | Patient information matching method, system, computer and readable storage medium | |
| WO2019085064A1 (en) | Medical claim denial determination method, device, terminal apparatus, and storage medium | |
| CN111145510B (en) | Alarm receiving processing method, device and equipment | |
| JP2012511762A (en) | Automated assertion reuse for improved record linkage in distributed and autonomous medical environments with heterogeneous trust models | |
| US11182481B1 (en) | Evaluation of files for cyber threats using a machine learning model | |
| CN114398983A (en) | Classification prediction method, classification prediction device, classification prediction equipment, storage medium and computer program product | |
| US20210326615A1 (en) | System and method for automatically detecting and repairing biometric crosslinks | |
| CN110837635A (en) | Method, device, equipment and storage medium for equipment verification | |
| CN113705164A (en) | Text processing method and device, computer equipment and readable storage medium | |
| CN116992880A (en) | Building name identification method, device, electronic equipment and storage medium | |
| CN112686732B (en) | Abnormal address data identification method, device, equipment and medium | |
| CN115458100A (en) | Knowledge graph-based follow-up method and device, electronic equipment and storage medium | |
| CN114329454A (en) | Threat analysis method and system based on application software big data | |
| CN115730049A (en) | Customer service question and answer method, device, equipment and medium based on short for identification | |
| CN114266777A (en) | Segmentation model training method, segmentation device, electronic device, and medium | |
| CN110909538A (en) | Question and answer content identification method and device, terminal equipment and medium | |
| CN113672703A (en) | User information updating method, device, equipment and storage medium | |
| CN115345323A (en) | Vehicle fault detection method, device, equipment and storage medium | |
| CN112786041A (en) | Voice processing method and related equipment | |
| CN113283434B (en) | Image semantic segmentation method and system based on segmentation network optimization | |
| CN115099922B (en) | Financial data query method, system, readable storage medium and computer equipment | |
| CN117493528A (en) | Insurance customer service corpus generation method, electronic equipment and storage medium | |
| CN117216132B (en) | Mathematical test question similarity judging method, system and application | |
| CN111027667B (en) | Method and device for identifying intention category | |
| CN111881679B (en) | Text standardization processing method and device, electronic equipment and computer medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xue Hao Inventor after: He Changhai Inventor after: Zeng Zhongan Inventor after: Fan Haidong Inventor after: Ye Kai Inventor after: Ding Chuan Inventor after: Lu Bingqing Inventor before: Xue Hao Inventor before: Ji Zhengrong Inventor before: He Changhai Inventor before: Zeng Zhongan Inventor before: Fan Haidong Inventor before: Ye Kai Inventor before: Ding Chuan Inventor before: Lu Bingqing |