CN115033747A - Abnormal state searching method and device - Google Patents
Abnormal state searching method and device Download PDFInfo
- Publication number
- CN115033747A CN115033747A CN202210727871.8A CN202210727871A CN115033747A CN 115033747 A CN115033747 A CN 115033747A CN 202210727871 A CN202210727871 A CN 202210727871A CN 115033747 A CN115033747 A CN 115033747A
- Authority
- CN
- China
- Prior art keywords
- abnormal state
- candidate
- necessary
- acquiring
- target
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The disclosure provides a retrieval method and a retrieval device for abnormal states, relates to the technical field of data processing, and particularly relates to the technical field of intelligent retrieval. The specific implementation scheme is as follows: acquiring M target features of a target object to be retrieved; acquiring at least one candidate abnormal state to which the ith target feature belongs and generating a candidate abnormal state set i of the ith target feature; acquiring the occurrence times of the same candidate abnormal state in M abnormal state sets; acquiring the number of necessary features included in the candidate abnormal state; and according to the occurrence times and the necessary characteristic quantity, indexing in the candidate abnormal states, and determining at least one target abnormal state of the target object. According to the embodiment of the disclosure, the target characteristics of the patient can be refined in granularity in the scene of a large number of abnormal states, the time complexity of retrieval is reduced, the retrieval speed of millisecond level is realized, the retrieval efficiency of the abnormal states is improved, and the retrieval performance is improved.
Description
Technical Field
The present disclosure relates to the field of data processing technology, and in particular, to the field of intelligent retrieval technology.
Background
In the related art, when searching for an abnormal state, all necessary features included in the abnormal state need to be predefined, each abnormal state is traversed according to the target feature to be searched, and whether the target feature to be searched includes the necessary features included in the abnormal state is judged. Therefore, how to improve the efficiency of searching for abnormal states has become one of important research directions.
Disclosure of Invention
The disclosure provides a retrieval method of abnormal states and a device thereof.
According to an aspect of the present disclosure, there is provided a method for retrieving an abnormal state, including:
acquiring M target features of a target object to be retrieved, wherein M is a positive integer;
acquiring at least one candidate abnormal state to which the ith target feature belongs, wherein the candidate abnormal state is used for generating a candidate abnormal state set i of the ith target feature, and i is a positive integer less than or equal to M;
acquiring the occurrence times of the same candidate abnormal state in M abnormal state sets;
acquiring the number of necessary features included in the candidate abnormal state;
and according to the occurrence times and the necessary characteristic quantity, indexing in the candidate abnormal states, and determining at least one target abnormal state of the target object.
According to the embodiment of the invention, the target characteristics of the patient can be subjected to fine granularity in a scene of a large number of abnormal states, so that the average time complexity is reduced from a square level to a linear level, the millisecond-level retrieval speed is realized, the retrieval efficiency of the abnormal states can be improved, the time waste is avoided, and the retrieval performance is improved.
According to another aspect of the present disclosure, there is provided an abnormal state retrieval apparatus including:
the first acquisition module is used for acquiring M target characteristics of a target object to be retrieved, wherein M is a positive integer;
the second acquisition module is used for acquiring at least one candidate abnormal state to which the ith target feature belongs, wherein the candidate abnormal state is used for generating a candidate abnormal state set i of the ith target feature, and i is a positive integer less than or equal to M;
the third acquisition module is used for acquiring the occurrence frequency of the same candidate abnormal state in the M abnormal state sets;
the fourth acquisition module is used for acquiring the necessary characteristic quantity included by the candidate abnormal state;
and the determining module is used for indexing in the candidate abnormal states according to the occurrence times and the necessary characteristic quantity and determining at least one target abnormal state of the target object.
According to another aspect of the present disclosure, there is provided an electronic device comprising at least one processor, and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of retrieving an exception state as embodied in the first aspect of the disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for retrieving an abnormal state of the first aspect of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of retrieving an abnormal state of the first aspect of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flow diagram of a method of retrieval of an abnormal state according to one embodiment of the present disclosure;
FIG. 2 is a flow diagram of a method of retrieval of an abnormal state according to one embodiment of the present disclosure;
FIG. 3 is a flow diagram of a method of retrieval of an abnormal state according to one embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a first index store according to one embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a third index store according to one embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a second index store according to one embodiment of the present disclosure;
FIG. 7 is a flow diagram of a method of retrieving an abnormal state according to one embodiment of the present disclosure;
FIG. 8 is a block diagram of an abnormal state retrieval device according to one embodiment of the present disclosure;
fig. 9 is a block diagram of an electronic device for implementing the retrieval method of an abnormal state of the embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Data processing is the process of extracting valuable information from a large amount of raw data, i.e., converting data into information. The input data in various forms are mainly processed and sorted, and the process comprises the whole process of evolution and derivation of collection, storage, processing, classification, merging, calculation, sorting, conversion, retrieval and propagation of the data. Data management refers to operations such as collection, organization, storage, maintenance, retrieval and transmission of data, is a basic link of data processing business, and is a necessary common part in all data processing processes. In data processing, calculation is generally simple, and processing calculation in data processing services is different according to different services, and needs to be solved by writing an application program according to the needs of the services. Data management is complicated, and since available data is explosively increased and the variety of data is complicated, data management requires not only data use but also effective data management. Therefore, a general, convenient and efficient management software is needed to manage data efficiently. Data processing is associated with data management, and the quality of data management technology has a direct influence on the efficiency of data processing.
The intelligent retrieval is based on the relevance of documents and retrieval words, indexes such as the importance of the documents are comprehensively examined, and retrieval results are ranked to provide higher retrieval efficiency. The relevance and the importance of the intelligent retrieval result are simultaneously considered, the relevance adopts weighted mixed indexes of all fields, the relevance analysis is more accurate, the importance refers to the evaluation of the quality of the documents through document source authority analysis, citation relation analysis and the like, the result ranking is more accurate, the documents most relevant to the user desire can be ranked to the top, and the retrieval efficiency is improved.
The method for searching for an abnormal state and the apparatus thereof according to the present disclosure will be described with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for retrieving an abnormal state according to an embodiment of the present disclosure, as shown in fig. 1, the method including the steps of:
s101, M target features of a target object to be retrieved are obtained, wherein M is a positive integer.
In the embodiment of the present disclosure, an intelligent medical scenario is taken as an example for explanation, a target object is a patient in a diagnosis and treatment process, and target features to be retrieved may be one or several types of data information:
the test item, optionally, the test condition may be a combination of a test specimen and a test item, in some implementations, the test condition may be "serum + albumin", in some implementations, the test condition may be "urine + urinary creatinine", and the like.
The examination items may be, alternatively, examination items including parts of the head and face, neck, chest and abdomen, laboratory examination items such as blood routine, urine routine, kidney function, and liver function, and the like. In some implementations, the examination item may be "Computed Tomography (CT)", in some implementations, the examination item may be "abdominal ultrasound examination", or the like.
The sign name may optionally be a vital sign such as respiration, heart rate, body temperature, blood pressure, in some implementations, the sign name may be "height" or "weight," in some implementations, the sign name may be "diastolic pressure" and "systolic pressure," etc.
The disease name, optionally, can be a disease present in a past history, in some implementations, the disease name can be "lung cancer," and in some implementations, the disease name can be "vascular cancer.
The symptom name, alternatively, may be an abnormal condition that the patient presents as a result of the disease, and in some implementations, the symptom name may be "fever", "headache", "runny nose", and the like.
Surgical name, optionally, in some implementations, the surgical name may be "laparoscopic surgery," "knee replacement surgery," or the like.
The allergy name, alternatively, the allergy name may be the name of an allergen, in some implementations, the allergy name may be "pollen allergy," in some implementations, the allergy name may be "peanut allergy," or the like.
The gender name, alternatively, may be "male" or "female".
The physiological state name, in some implementations, may be "physiological jaundice," or the like.
S102, obtaining at least one candidate abnormal state to which the ith target feature belongs, wherein the candidate abnormal state is used for generating a candidate abnormal state set i of the ith target feature, and i is a positive integer less than or equal to M.
In the context of intelligent medicine, an abnormal condition may be a risk event, such as sudden shock, that occurs during the course of a diagnosis and treatment of a patient.
Taking an example that the abnormal state a includes the necessary feature m and the necessary feature n, the abnormal state B includes the necessary feature n and the necessary feature r, and the abnormal state C includes the necessary feature m and the necessary feature r, if the ith target feature is n, the candidate abnormal state to which the ith target feature belongs is the abnormal state a and the abnormal state B. The candidate abnormal state set i of the ith target feature is { abnormal state A, abnormal state B }.
Alternatively, to facilitate data reading and improve the retrieval efficiency of the abnormal state, the abnormal state may be indicated by an abnormal state identifier (Event ID), that is, the abnormal state set i contains only Event IDs of candidate abnormal states to which the ith target feature belongs.
S103, acquiring the occurrence frequency of the same candidate abnormal state in the M abnormal state sets.
In the embodiment of the present disclosure, the number of occurrences of the same candidate abnormal state in the M abnormal state sets is also the number of target features included in the candidate abnormal state. Optionally, the M abnormal state sets may be merged, so as to identify the occurrence number of the same candidate abnormal state.
And S104, acquiring the necessary characteristic quantity included in the candidate abnormal state.
In the embodiment of the present disclosure, the abnormal state Q is described as an example including the necessary feature m, the necessary feature n, the necessary feature r, and the necessary feature f, and if the candidate abnormal state is the abnormal state Q, the number of necessary features included in the candidate abnormal state is 4.
And S105, indexing in the candidate abnormal states according to the occurrence times and the necessary characteristic quantity, and determining at least one target abnormal state of the target object.
The number of occurrences of the same candidate abnormal state in the M abnormal state sets is the number of target features included in the candidate abnormal state, and for any candidate abnormal state, the target feature includes all necessary features of the candidate abnormal state, and the candidate abnormal state is triggered to be the target abnormal state of the target object, so that the number of the target features included in the candidate abnormal state should be greater than or equal to the number of necessary features of the candidate abnormal state.
In the embodiment of the present disclosure, the candidate abnormal state may be indexed in the candidate abnormal state based on the number of occurrences and the number of necessary features, and the candidate abnormal state whose number of occurrences is greater than or equal to the number of necessary features may be determined as the target abnormal state.
In some scenarios, when retrieving a target abnormal state, it is necessary to index from millions of abnormal states and perform traversal operation according to target characteristics, and the time complexity of this method is in the millions. In the embodiment of the disclosure, the N target abnormal states which can be satisfied by de-matching the M target features of the patient are obtained, so that each necessary feature in each target abnormal state can be constrained, the overall time complexity is O (MN), and the time complexity of retrieval is greatly reduced.
In the embodiment of the disclosure, M target features of a target object to be retrieved are obtained, at least one candidate abnormal state to which an ith target feature belongs is obtained, wherein the candidate abnormal state is used for generating a candidate abnormal state set i of the ith target feature, and the occurrence frequency of the same candidate abnormal state in the M abnormal state sets and the number of necessary features included in the candidate abnormal state are obtained; and according to the occurrence times and the necessary characteristic quantity, indexing in the candidate abnormal states, and determining at least one target abnormal state of the target object. According to the embodiment of the disclosure, the target characteristics of the patient can be subjected to fine granularity in the scene of a large number of abnormal states, so that the average time complexity is reduced from a square level to a linear level, the millisecond-level retrieval speed is realized, the retrieval efficiency of the abnormal states can be improved, the time waste is avoided, and the retrieval performance is improved.
It should be noted that the abnormal state retrieval method according to the embodiment of the present disclosure is not only applicable to an intelligent medical scenario, but also applicable to other precondition scenarios in the retrieval process, such as a natural disaster detection scenario and an intelligent cockpit scenario. Alternatively, in the intelligent cabin scene, the target object is a vehicle in the driving process, the target feature to be retrieved may be different types of driving data, such as acceleration, wheel speed, airbag data, vehicle posture data, smoke data, wading data, and the like, and the abnormal state may be a vehicle fire or a vehicle wading. Optionally, in a natural disaster detection scenario, the target object is an area to be detected, the target feature to be retrieved may be different types of detection data, such as wind speed, water flow speed, smoke data, humidity, and the like, and the abnormal state may be a rainstorm, a torrential flood, a typhoon, and the like.
Fig. 2 is a flowchart of a method for retrieving an abnormal state according to an embodiment of the present disclosure, as shown in fig. 2, the method includes the steps of:
s201, M target features of a target object to be retrieved are obtained, wherein M is a positive integer.
S202, at least one candidate abnormal state to which the ith target feature belongs is obtained, wherein the candidate abnormal state is used for generating a candidate abnormal state set i of the ith target feature, and i is a positive integer less than or equal to M.
S203, acquiring the occurrence frequency of the same candidate abnormal state in the M abnormal state sets.
S204, acquiring the necessary characteristic quantity included in the candidate abnormal state.
The descriptions of step S201 to step S204 can refer to the relevant contents of the above embodiments, and are not described herein again.
S205, traversing the M abnormal state sets, and comparing the occurrence frequency of the currently traversed candidate abnormal state with the necessary feature quantity.
In the embodiment of the disclosure, after the candidate abnormal states in the M abnormal state sets are merged, the candidate abnormal states in the M abnormal state sets are traversed, and for the currently traversed candidate abnormal state, a difference value between the occurrence frequency of the candidate abnormal state and the necessary feature quantity is obtained.
S206, in response to the occurrence frequency being greater than or equal to the necessary feature quantity, determining the currently traversed candidate abnormal state as a target abnormal state until the M abnormal state sets are traversed.
If the difference between the occurrence frequency of the candidate abnormal state and the necessary feature quantity is greater than or equal to 0, it is indicated that the quantity of the target features contained in the candidate abnormal state is greater than or equal to the necessary feature quantity of the candidate abnormal state, the currently traversed candidate abnormal state is determined as the target abnormal state until the M abnormal state sets are traversed, and at least one target abnormal state of the target object is obtained.
Optionally, in this embodiment of the present disclosure, after obtaining at least one target abnormal state of the target object, the method further includes generating a target abnormal state set of the target object according to all the target abnormal states.
In the embodiment of the disclosure, the M abnormal state sets are traversed, the occurrence number of the currently traversed candidate abnormal state is compared with the necessary feature number, and in response to the occurrence number being greater than or equal to the necessary feature number, the currently traversed candidate abnormal state is determined to be the target abnormal state until the M abnormal state sets are traversed. According to the embodiment of the invention, the target characteristics of the patient can be refined in granularity in the scene of massive abnormal states, the time complexity of retrieval is reduced, the retrieval efficiency of the abnormal states is improved, the waste of time is avoided, the retrieval performance is improved, and the use experience of a user can be improved.
Fig. 3 is a flowchart of a method for retrieving an abnormal state according to an embodiment of the present disclosure, as shown in fig. 3, the method including the steps of:
s301, M target features of the target object to be retrieved are obtained, wherein M is a positive integer.
S302, searching the ith target feature in a preset first index library, and acquiring a candidate abnormal state comprising the ith target feature from the first index library, wherein i is a positive integer less than or equal to M, and the first index library comprises a first mapping relation between the abnormal state and necessary features of the abnormal state.
In the embodiment of the disclosure, historical abnormal states and characteristics associated with the historical abnormal states are acquired. And counting the characteristics associated with the historical abnormal state, acquiring necessary characteristics corresponding to the historical abnormal state to generate a first mapping relation, and constructing a first index library based on the first mapping relation.
FIG. 4 is a schematic diagram of a first index bank according to an embodiment of the disclosure, as shown in FIG. 4, an abnormal state A includes an essential feature m and an essential feature n, an abnormal state B includes an essential feature n and an essential feature r, and an abnormal state C includes an essential feature n and an essential feature rFor example, the feature r has a first mapping relationship between the necessary feature m and the abnormal state a, the necessary feature n has a first mapping relationship between the necessary feature m and the abnormal state a, the abnormal state B, and the abnormal state C, and the necessary feature r has a first mapping relationship between the necessary feature m and the abnormal state B, and the abnormal state C. Wherein EventID 1 Identification of abnormal State A, EventID 2 Identification of abnormal State B, EventID 3 Is an identification of abnormal state C.
S303, generating a candidate abnormal state set i based on the candidate abnormal state of the ith target feature.
And generating a candidate abnormal state set i according to the candidate abnormal states with the first mapping relation with the ith target feature.
S304, acquiring the occurrence frequency of the same candidate abnormal state in the M abnormal state sets.
The description of step S304 may refer to the relevant contents of the above embodiments, and is not described herein again.
It should be noted that, after the M abnormal state sets are merged and the occurrence frequency of the same candidate abnormal state is identified, a third index library may be constructed according to a third mapping relationship between the candidate abnormal state and the occurrence frequency of the candidate abnormal state.
Fig. 5 is a schematic diagram of a third index library according to an embodiment of the present disclosure, and as shown in fig. 5, it is described by taking an example that a candidate abnormal state a includes a target feature m, a candidate abnormal state B includes a target feature n and a target feature r, and a candidate abnormal state C includes a target feature m, a target feature n and a target feature r, where the number of occurrences of the abnormal state a is 1, the number of occurrences of the abnormal state B is 2, and the number of occurrences of the abnormal state C is 3.
And S305, searching the candidate abnormal state in a preset second index base, and acquiring the necessary feature quantity included in the candidate abnormal state from the second index base, wherein the second index base includes a second mapping relation between the candidate abnormal state and the necessary feature quantity of the candidate abnormal state.
Acquiring the necessary characteristic quantity included in the historical abnormal state. And constructing a second index library based on a second mapping relation between the historical abnormal state and the necessary feature quantity.
Fig. 6 is a schematic diagram of a second index library according to an embodiment of the present disclosure, as shown in fig. 6, an abnormal state a is described by taking an example that includes necessary features m and n, an abnormal state B includes necessary features n and r, and an abnormal state C includes necessary features n and r, the number of necessary features of the abnormal state a is 2, the number of necessary features of the abnormal state B is 2, and the number of necessary features of the abnormal state C is 2.
S306, according to the occurrence times and the necessary feature quantity, indexing is carried out in the candidate abnormal state, and at least one target abnormal state of the target object is determined.
The description of step S306 can refer to the relevant contents of the above embodiments, and is not described herein again.
It should be noted that, in the embodiment of the present disclosure, any candidate abnormal state in the third index library may be indexed, the occurrence number of the candidate abnormal state and the necessary feature quantity of the candidate abnormal state in the second index library are obtained, and then at least one target abnormal state of the target object is determined according to the occurrence number and the necessary feature quantity.
In the embodiment of the disclosure, an ith target feature is searched in a preset first index library, a candidate abnormal state including the ith target feature is obtained from the first index library, a candidate abnormal state set i is generated based on the candidate abnormal state of the ith target feature, and the occurrence frequency of the same candidate abnormal state in M abnormal state sets is obtained. And searching the candidate abnormal state in a preset second index library, and acquiring the necessary characteristic quantity included in the candidate abnormal state from the second index library. According to the embodiment of the disclosure, the target characteristics of the patient can be subjected to fine granularity in the scene of a large number of abnormal states, so that the average time complexity is reduced from a square level to a linear level, the time complexity of retrieval is reduced, the retrieval speed of a millisecond level is realized, the retrieval efficiency of the abnormal states can be improved, the waste of time is avoided, the retrieval performance is improved, and the use experience of the user is improved.
Fig. 7 is a flowchart illustrating a method for retrieving an abnormal state according to an embodiment of the present disclosure, where as shown in fig. 7, the method includes obtaining a first index library and a second index library constructed offline, where the first index library includes a first mapping relationship between the abnormal state and necessary features of the abnormal state, and the second index library includes a second mapping relationship between the abnormal state and necessary feature quantities of the abnormal state. The method comprises the steps of obtaining M target features to be retrieved of a target object, searching the ith target feature in a preset first index base, obtaining a candidate abnormal state set comprising the ith target feature from the first index base, further obtaining the occurrence frequency of the same candidate abnormal state in the M abnormal state sets, and constructing a third index base according to a third mapping relation between the candidate abnormal state and the occurrence frequency of the candidate abnormal state. And indexing any candidate abnormal state in the third index library, acquiring the occurrence frequency of the candidate abnormal state and the necessary characteristic quantity of the candidate abnormal state in the second index library, and determining at least one target abnormal state of the target object according to the occurrence frequency and the necessary characteristic quantity to generate a target abnormal state set.
According to the embodiment of the disclosure, the target characteristics of the patient can be subjected to fine granularity in the scene of a large number of abnormal states, so that the average time complexity is reduced from a square level to a linear level, the time complexity of retrieval is reduced, the retrieval speed of a millisecond level is realized, the retrieval efficiency of the abnormal states can be improved, the waste of time is avoided, the retrieval performance is improved, and the use experience of the user is improved.
Fig. 8 is a block diagram of an abnormal state search apparatus according to an embodiment of the present disclosure, and as shown in fig. 8, the abnormal state search apparatus 800 includes:
a first obtaining module 810, configured to obtain M target features of a target object to be retrieved, where M is a positive integer;
a second obtaining module 820, configured to obtain at least one candidate abnormal state to which an ith target feature belongs, where the candidate abnormal state is used to generate a candidate abnormal state set i of the ith target feature, and i is a positive integer less than or equal to M;
a third obtaining module 830, configured to obtain the occurrence frequency of the same candidate abnormal state in the M abnormal state sets;
a fourth obtaining module 840, configured to obtain the number of necessary features included in the candidate abnormal state;
and the determining module 850 is configured to perform indexing in the candidate abnormal states according to the occurrence number and the necessary feature quantity, and determine at least one target abnormal state of the target object.
In some implementations, the determining module 850 is further configured to:
traversing M abnormal state sets, and comparing the occurrence times of the currently traversed candidate abnormal states with the necessary feature quantity;
and determining the candidate abnormal state traversed currently as a target abnormal state in response to the occurrence frequency being greater than or equal to the necessary feature quantity until the M abnormal state sets are traversed.
In some implementations, the second obtaining module 820 is further configured to:
searching the ith target feature in a preset first index base, and acquiring a candidate abnormal state comprising the ith target feature from the first index base, wherein the first index base comprises a first mapping relation between the abnormal state and necessary features of the abnormal state.
In some implementations, the fourth obtaining module 840 is further configured to:
and searching the candidate abnormal state in a preset second index library, and acquiring the necessary feature quantity included in the candidate abnormal state from the second index library, wherein the second index library comprises a second mapping relation between the candidate abnormal state and the necessary feature quantity of the candidate abnormal state.
In some implementations, the second obtaining module 820 is further configured to:
acquiring historical abnormal states and historical abnormal state associated characteristics;
counting the characteristics associated with the historical abnormal state, and acquiring necessary characteristics corresponding to the historical abnormal state to generate a first mapping relation;
and constructing a first index library based on the first mapping relation.
In some implementations, the fourth obtaining module 840 is further configured to:
acquiring the necessary characteristic quantity included in historical abnormal states;
and constructing a second index library based on a second mapping relation between the historical abnormal state and the necessary feature quantity.
According to the embodiment of the invention, the target characteristics of the patient can be subjected to fine granularity in a scene of a large number of abnormal states, so that the average time complexity is reduced from a square level to a linear level, the millisecond-level retrieval speed is realized, the retrieval efficiency of the abnormal states can be improved, the time waste is avoided, and the retrieval performance is improved.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 9 illustrates a schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate 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. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 9, the apparatus 900 includes a computing unit 901, which can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)902 or a computer program loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The calculation unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
A number of components in the device 900 are connected to the I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, and the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, optical disk, or the like; and a communication unit 909 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 901 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, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 901 performs the respective methods and processes described above, such as retrieval of an abnormal state. For example, in some embodiments, the retrieval of the abnormal state may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 900 via ROM 902 and/or communications unit 909. When the computer program is loaded into RAM 903 and executed by computing unit 901, one or more steps of the above-described retrieval of an abnormal state may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the retrieval of the abnormal state in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, causes the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The 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, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (15)
1. A retrieval method of an abnormal state comprises the following steps:
acquiring M target features of a target object to be retrieved, wherein M is a positive integer;
acquiring at least one candidate abnormal state to which an ith target feature belongs, wherein the candidate abnormal state is used for generating a candidate abnormal state set i of the ith target feature, and the i is a positive integer less than or equal to M;
acquiring the occurrence times of the same candidate abnormal state in M abnormal state sets;
acquiring the number of necessary features included in the candidate abnormal state;
and indexing in the candidate abnormal state according to the occurrence times and the necessary characteristic quantity, and determining at least one target abnormal state of the target object.
2. The method of claim 1, wherein said determining at least one target abnormal state of the target object by indexing among the candidate abnormal states according to the number of occurrences and the number of essential features comprises:
traversing M abnormal state sets, and comparing the occurrence times of the currently traversed candidate abnormal states with the necessary characteristic quantity;
and determining the currently traversed candidate abnormal state as the target abnormal state in response to the occurrence number of times larger than or equal to the necessary feature number until M abnormal state sets are traversed.
3. The method of claim 1, wherein the obtaining at least one candidate abnormal state to which the ith target feature belongs comprises:
searching the ith target feature in a preset first index library, and acquiring a candidate abnormal state comprising the ith target feature from the first index library, wherein the first index library comprises a first mapping relation between the abnormal state and necessary features of the abnormal state.
4. The method according to claim 1, wherein the obtaining of the necessary feature quantity included in the candidate abnormal state comprises:
searching the candidate abnormal state in a preset second index library, and acquiring the necessary feature quantity included in the candidate abnormal state from the second index library, wherein the second index library includes a second mapping relation between the candidate abnormal state and the necessary feature quantity of the candidate abnormal state.
5. The method of claim 3, wherein the building of the first index repository comprises:
acquiring historical abnormal states and characteristics related to the historical abnormal states;
counting the characteristics associated with the historical abnormal state, and acquiring necessary characteristics corresponding to the historical abnormal state to generate the first mapping relation;
and constructing the first index library based on the first mapping relation.
6. The method of claim 4, wherein the building process of the second index database comprises:
acquiring the necessary characteristic quantity included in historical abnormal states;
and constructing a second index library based on a second mapping relation between the historical abnormal state and the necessary characteristic quantity.
7. An abnormal state retrieval apparatus comprising:
the device comprises a first acquisition module, a second acquisition module and a searching module, wherein the first acquisition module is used for acquiring M target characteristics of a target object to be searched, and M is a positive integer;
a second obtaining module, configured to obtain at least one candidate abnormal state to which an ith target feature belongs, where the candidate abnormal state is used to generate a candidate abnormal state set i of the ith target feature, and i is a positive integer less than or equal to M;
a third obtaining module, configured to obtain the number of occurrences of the same candidate abnormal state in the M abnormal state sets;
a fourth obtaining module, configured to obtain the number of necessary features included in the candidate abnormal state;
and the determining module is used for indexing in the candidate abnormal state according to the occurrence times and the necessary characteristic quantity and determining at least one target abnormal state of the target object.
8. The apparatus of claim 7, wherein the means for determining is further configured to:
traversing M abnormal state sets, and comparing the occurrence times of the currently traversed candidate abnormal states with the necessary characteristic quantity;
and determining the currently traversed candidate abnormal state as the target abnormal state in response to the occurrence number of times being greater than or equal to the necessary feature number until the M abnormal state sets are traversed.
9. The apparatus of claim 7, wherein the second obtaining means is further configured to:
searching the ith target feature in a preset first index library, and acquiring a candidate abnormal state comprising the ith target feature from the first index library, wherein the first index library comprises a first mapping relation between the abnormal state and necessary features of the abnormal state.
10. The apparatus of claim 7, wherein the fourth obtaining means is further configured to:
searching the candidate abnormal state in a preset second index library, and acquiring the necessary feature quantity included in the candidate abnormal state from the second index library, wherein the second index library includes a second mapping relation between the candidate abnormal state and the necessary feature quantity of the candidate abnormal state.
11. The apparatus of claim 9, wherein the second obtaining means is further configured to:
acquiring historical abnormal states and characteristics related to the historical abnormal states;
counting the characteristics associated with the historical abnormal state, and acquiring necessary characteristics corresponding to the historical abnormal state to generate the first mapping relation;
and constructing the first index library based on the first mapping relation.
12. The apparatus of claim 10, wherein the fourth obtaining means is further configured to:
acquiring the necessary characteristic quantity included in historical abnormal states;
and constructing a second index library based on a second mapping relation between the historical abnormal state and the necessary characteristic quantity.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-6.
15. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727871.8A CN115033747B (en) | 2022-06-24 | 2022-06-24 | Abnormal state searching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727871.8A CN115033747B (en) | 2022-06-24 | 2022-06-24 | Abnormal state searching method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115033747A true CN115033747A (en) | 2022-09-09 |
| CN115033747B CN115033747B (en) | 2023-05-30 |
Family
ID=83127664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210727871.8A Active CN115033747B (en) | 2022-06-24 | 2022-06-24 | Abnormal state searching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115033747B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159938A (en) * | 2015-08-03 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Retrieval method and apparatus |
| CN105488165A (en) * | 2015-11-30 | 2016-04-13 | 北京金山安全软件有限公司 | Data retrieval method and system based on index database |
| US20160132592A1 (en) * | 2014-11-06 | 2016-05-12 | Fuji Xerox Co., Ltd. | Information processing apparatus, information processing method and non-transitory computer readable medium |
| CN109299135A (en) * | 2018-11-26 | 2019-02-01 | 平安科技（深圳）有限公司 | Abnormal inquiry recognition methods, identification equipment and medium based on identification model |
| CN110866030A (en) * | 2019-10-23 | 2020-03-06 | 中国科学院信息工程研究所 | Database abnormal access detection method based on unsupervised learning |
| CN111444408A (en) * | 2020-03-26 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Network search processing method and device and electronic equipment |
| US20210149789A1 (en) * | 2019-11-18 | 2021-05-20 | Bmc Software, Inc. | System and method for troubleshooting abnormal behavior of an application |
| CN114491287A (en) * | 2021-12-28 | 2022-05-13 | 武汉虹旭信息技术有限责任公司 | Abnormal behavior collaborative screening method and system based on mobile internet |
-
2022
- 2022-06-24 CN CN202210727871.8A patent/CN115033747B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160132592A1 (en) * | 2014-11-06 | 2016-05-12 | Fuji Xerox Co., Ltd. | Information processing apparatus, information processing method and non-transitory computer readable medium |
| CN105159938A (en) * | 2015-08-03 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Retrieval method and apparatus |
| CN105488165A (en) * | 2015-11-30 | 2016-04-13 | 北京金山安全软件有限公司 | Data retrieval method and system based on index database |
| CN109299135A (en) * | 2018-11-26 | 2019-02-01 | 平安科技（深圳）有限公司 | Abnormal inquiry recognition methods, identification equipment and medium based on identification model |
| CN110866030A (en) * | 2019-10-23 | 2020-03-06 | 中国科学院信息工程研究所 | Database abnormal access detection method based on unsupervised learning |
| US20210149789A1 (en) * | 2019-11-18 | 2021-05-20 | Bmc Software, Inc. | System and method for troubleshooting abnormal behavior of an application |
| CN111444408A (en) * | 2020-03-26 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Network search processing method and device and electronic equipment |
| CN114491287A (en) * | 2021-12-28 | 2022-05-13 | 武汉虹旭信息技术有限责任公司 | Abnormal behavior collaborative screening method and system based on mobile internet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115033747B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Singh et al. | A deep neural network for early detection and prediction of chronic kidney disease | |
| CN111414393B (en) | Semantic similar case retrieval method and equipment based on medical knowledge graph | |
| US7809660B2 (en) | System and method to optimize control cohorts using clustering algorithms | |
| CN113345577B (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| US10886025B2 (en) | Drug adverse event extraction method and apparatus | |
| CN112528660A (en) | Method, apparatus, device, storage medium and program product for processing text | |
| CN111986792A (en) | Medical institution scoring method, device, equipment and storage medium | |
| CN102405473A (en) | A point-of-care enactive medical system and method | |
| CN113792115B (en) | Entity correlation determination method, device, electronic equipment and storage medium | |
| EP2922018A1 (en) | Medical information analysis program, medical information analysis device, and medical information analysis method | |
| Li et al. | Predicting clinical outcomes with patient stratification via deep mixture neural networks | |
| CN111581969A (en) | Medical term vector representation method, device, storage medium and electronic equipment | |
| CN115438040A (en) | Pathological archive information management method and system | |
| CN114049952A (en) | Intelligent prediction method and device for postoperative acute kidney injury based on machine learning | |
| CN115620886B (en) | Data auditing method and device | |
| Chan et al. | Association patterns of ontological features signify electronic health records in liver cancer | |
| CN115033747B (en) | Abnormal state searching method and device | |
| CN115472257A (en) | Method and device for recruiting users, electronic equipment and storage medium | |
| CN114724693A (en) | Method and device for detecting abnormal diagnosis and treatment behaviors, electronic equipment and storage medium | |
| CN114461085A (en) | Medical input recommendation method, device, equipment and storage medium | |
| CN115526882A (en) | Medical image classification method, device, equipment and storage medium | |
| CN110931136B (en) | Event searching method and device, computer medium and electronic equipment | |
| CN114446470A (en) | Artificial intelligence model-based acute kidney injury recovery time prediction method | |
| CN113990514A (en) | Abnormality detection device for doctor diagnosis and treatment behavior, computer device and storage medium | |
| CN114566280A (en) | User state prediction method and device, electronic equipment and storage 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 |