CN115374366A - Matching information generation method, storage medium and electronic equipment - Google Patents
Matching information generation method, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115374366A CN115374366A CN202211124446.6A CN202211124446A CN115374366A CN 115374366 A CN115374366 A CN 115374366A CN 202211124446 A CN202211124446 A CN 202211124446A CN 115374366 A CN115374366 A CN 115374366A
- Authority
- CN
- China
- Prior art keywords
- matching
- sub
- information
- preset
- module
- 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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a generation method of matching information, a storage medium and electronic equipment. The main matching module determines a target sub-matching module from the initial matching modules. And the target sub-matching module performs second matching processing on the target characteristic information to generate target matching information. According to the invention, firstly, the matching category corresponding to the second matching can be determined through the first matching, and then, the second matching is carried out, so that the corresponding target matching information can be more accurately and specifically determined. Therefore, the matching degree of the target matching information determined by the method and the information actually required by the user is higher.
Description
Technical Field
The present invention relates to the field of information generation, and in particular, to a method for generating matching information, a storage medium, and an electronic device.
Background
With the development of data processing technology, information matching recommendation technology is more commonly applied in daily production and life of people. In the prior art, corresponding matching information can be recommended to a user through deep analysis processing on user feature data. Therefore, the user can conveniently acquire the information which is expected to be known more currently in time.
However, the information matching recommendation technology in the prior art has low matching accuracy, so that the matching degree of the generated matching information and the information actually required by the user is low.
Disclosure of Invention
Aiming at the technical problem, the technical scheme adopted by the invention is as follows:
according to one aspect of the invention, the invention provides a generation method of matching information, which is applied to a matching system. The information acquisition module is in communication connection with the main matching module. The main matching module is respectively in communication connection with the plurality of sub-matching modules. And a plurality of preset matching rules are configured in the main matching module and the sub-matching modules.
And controlling the matching system to operate according to the first method so as to generate corresponding matching information according to the characteristic information of the user. The first method comprises the following steps:
the information acquisition module acquires target characteristic information.
And the main matching module performs first matching processing on the target characteristic information according to a preset matching rule configured by the main matching module so as to generate first matching information.
When the first matching information contains n first matching values a 1 ,a 2 ,…,a i ,…,a n The main matching module judges each first matching value to determine the initial matching from the plurality of sub-matching modulesAnd (5) a module. Wherein each first matching value is used for representing a preset matching category of the corresponding sub-matching module, a i And the main matching module carries out first matching processing on the target characteristic information according to a preset rule configured by the main matching module to obtain a first matching value of the ith sub-matching module. i =1,2, …, n. n is the total number of sub-matching modules.
And the main matching module determines the initial matching module with the matching weight value larger than a first threshold value from the plurality of initial matching modules as a target sub-matching module.
And each target sub-matching module respectively carries out second matching processing on the target characteristic information according to the preset matching rule configured by the target sub-matching module so as to generate corresponding target matching information. The preset matching rule configured by the main matching module is used for determining the preset matching category corresponding to the target characteristic information, and each sub-matching module only corresponds to one preset matching category. The preset matching rules configured by the sub-matching module are used for determining preset sub-categories corresponding to the target characteristic information, and each preset matching category comprises at least one corresponding preset sub-category.
The determination process includes:
obtaining the matching grade value b corresponding to each first matching value 1 ,b 2 ,…,b i ,…,b n ，b i The following conditions are satisfied:
b i ＝a i -c i . Wherein, c i Is a i Corresponding matching threshold, b i Is a i The corresponding matching rank value.
Whenever b is i >At 0, a is judged i The corresponding sub-matching module is the initial matching module.
According to a second aspect of the present invention, there is provided a non-transitory computer-readable storage medium storing a computer program which, when executed by a processor, implements a method of generating matching information as described above.
According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for generating matching information when executing the computer program.
The invention has at least the following beneficial effects:
according to the invention, first matching processing is carried out on target characteristic information through a main matching module to generate corresponding first matching information, judging processing is carried out according to the first matching information to determine a target sub-matching module from a plurality of sub-matching modules, then second matching processing is carried out on the target characteristic information through the target sub-matching module, and the matching information generated through the second matching processing is used as the target matching information. According to the invention, through first matching processing and judgment processing, the preset matching rule configured by the main matching module is used for determining the preset matching category corresponding to the target characteristic information, so that the matching category corresponding to the second matching can be determined, then, the sub-matching module corresponding to the category is used for performing second matching processing on the target characteristic information, and the preset matching rule configured by the sub-matching module is used for determining the preset sub-category corresponding to the target characteristic information, so that the corresponding preset sub-category, namely the target matching information, can be more accurately and specifically determined from the corresponding preset matching category. Therefore, after two-stage matching processing, the matching degree of the target matching information determined by the method and the information actually required by the user is higher.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for generating matching information according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
According to an aspect of the present invention, as shown in fig. 1, a method for generating matching information is provided, which is applied to a matching system, where the matching system includes an information obtaining module, a main matching module, and a plurality of sub-matching modules. The information acquisition module is in communication connection with the main matching module. The main matching module is respectively in communication connection with the plurality of sub-matching modules. And a plurality of preset matching rules are configured in the main matching module and the sub-matching modules.
The preset matching rule may be a rule configured manually according to a usage scenario. Each preset matching rule configured in the main matching module and the plurality of sub-matching modules can be used for performing corresponding matching processing on the target feature information to obtain corresponding matching information. Such as: each preset matching rule configured in the main matching module can perform corresponding matching processing on the target characteristic information to obtain a matching category corresponding to the second matching processing.
Correspondingly, each sub-matching module corresponds to one matching category, and the preset matching rule configured in each sub-matching module is the matching rule corresponding to the smaller hierarchical information in the corresponding matching category. As exemplified by the use scenario as an insurance recommendation scenario for airline travel: when the obtained matching category is a flight delay category, the preset matching rule configured in the sub-matching module corresponding to the flight delay category may be: the preset matching rule of the insurance information corresponding to the flight delay of 10 minutes, or the preset matching rule of the insurance information corresponding to the flight delay of 30 minutes, or the preset matching rule of the insurance information corresponding to the flight cancellation.
And controlling the matching system to operate according to the first method so as to generate corresponding matching information according to the characteristic information of the user. The first method comprises the following steps:
step S100: the information acquisition module acquires target characteristic information.
Specifically, if the usage scenario is air travel, the corresponding target characteristic information may be the corresponding departure and landing time of the flight, route information, historical delay information, departure and landing place information, weather information during flight, and the like.
Step S200: and the main matching module performs first matching processing on the target characteristic information according to a preset matching rule configured by the main matching module so as to generate first matching information.
Step S300: when the first matching information contains n first matching values a 1 ,a 2 ,…,a i ,…,a n The main matching module performs decision processing on each first matching value to determine an initial matching module from the plurality of sub-matching modules. Wherein each first matching value is used for representing a preset matching category of the corresponding sub-matching module, a i And the main matching module carries out first matching processing on the target characteristic information according to a preset rule configured by the main matching module to obtain a first matching value of the ith sub-matching module. i =1,2, …, n. n is the total number of sub-matching modules.
The determination process includes:
step S301: obtaining the matching grade value b corresponding to each first matching value 1 ,b 2 ,…,b i ,…,b n ，b i The following conditions are satisfied:
b i ＝a i -c i . Wherein, c i Is a i Corresponding matching threshold, b i Is a i The corresponding matching rank value.
Step S302: whenever b is i >At 0, a is judged i The corresponding sub-matching module is the initial matching module.
And setting a corresponding matching threshold value for each matching grade value according to the actual use condition, so that the initial matching module can be more accurately determined. According to the invention, the matching type corresponding to the second matching can be determined through the first matching processing and the judgment processing. That is, the general direction of the information of more interest to the user can be determined first, and thus, the information in the direction can be more specifically matched with higher precision at a later stage.
Specifically, when the preset matching rule is a first-class preset rule, the first matching information generated correspondingly is a 1 ,a 2 ,…,a n . The first type of rule is to assign a value to each first matching information according to the information carried in the target characteristic information. The specific assignment process may refer to the processing procedures corresponding to step S203 to step S205 described below.
Step S400: the main matching module determines an initial matching module with a matching weight value larger than a first threshold value from the plurality of initial matching modules as a target sub-matching module. Specifically, the first threshold Y1 may be determined by itself according to the actual usage scenario.
Specifically, when there are a plurality of initial matching modules, the target sub-matching module may be determined from the initial matching modules according to the following steps:
step S401: obtaining a matching weight value d corresponding to each initial matching module 1 ,d 2 ,…,d j ,…,d m Wherein d is j And j =1,2, …, m is the matching weight value corresponding to the jth initial matching module. And m is less than or equal to n, and m is the total number of the initial matching modules.
Step S402: max (d) 1 ,d 2 ,…,d j ,…,d m ) And the corresponding initial matching module is determined as a target sub-matching module. Wherein Max () is a preset maximum function, max (d) 1 ,d 2 ,…,d j ,…,d m ) Is d 1 ,d 2 ,…,d j ,…,d m Is measured.
In this embodiment, the matching weight values are stored in a weight value table, and a mapping relationship exists between the module ID of each sub-matching module and the matching weight value, so that one matching weight value can be matched for the sub-matching module. Meanwhile, since the initial matching module is also a sub-matching module, the matching weight value of each initial matching module can also be determined by the corresponding mapping relationship. Specifically, the larger the matching weight value is, the higher the user attention degree indicating the matching category is. The size of each matching weight value in the weight value table can be updated once at intervals, so that the size of the matching weight value of each sub-matching module can be correspondingly adjusted according to the attention degree of the user at the current time interval, and the matching degree of the finally generated target matching information and the information actually required by the user is higher.
Step S500: and each target sub-matching module respectively performs second matching processing on the target characteristic information according to the preset matching rule configured by the target sub-matching module so as to generate corresponding target matching information. The preset matching rule configured by the main matching module is used for determining a preset matching category corresponding to the target characteristic information, and each sub-matching module only corresponds to one preset matching category. The preset matching rules configured by the sub-matching module are used for determining preset sub-categories corresponding to the target characteristic information, and each preset matching category comprises at least one corresponding preset sub-category.
According to the method, first matching processing is carried out on target characteristic information through a main matching module to generate corresponding first matching information, judgment processing is carried out according to the first matching information to determine a target sub-matching module from a plurality of sub-matching modules, namely, the general direction of information which is more interesting to a user is determined, then second matching processing is carried out on the target characteristic information through the target sub-matching module, and the matching information generated through the second matching processing is used as the target matching information. According to the invention, firstly, the matching category corresponding to the second matching can be determined through the first matching processing and the judgment processing, and then, the sub-matching module corresponding to the category is used for carrying out the second matching processing on the target characteristic information, so that the corresponding target matching information can be more accurately and specifically determined from the category. Therefore, after two-stage matching processing, the matching degree of the target matching information determined by the method and the information actually required by the user is higher.
As one possible embodiment of the present invention, the target feature information includes a plurality of sub-feature values e 1 ,e 2 ,…,e k ,…,e p Wherein e is k Is the k-th sub-feature value. k =1,2, …, p. p is larger than or equal to n, and p is the total number of the sub-characteristic values. And each sub-matching module corresponds to at least one sub-feature. Each sub-feature uniquely corresponds to one sub-feature value.
Specifically, the target feature information in different usage scenarios may include feature values of different sub-feature items. In the actual use process, it can be determined that all the sub-feature items are included in the corresponding target feature information according to a specific use scene. If the use scene is taken as an aviation trip as an example for explanation: the sub-feature items included in the scene can be flight departure and landing time sub-feature items, airline information sub-feature items, historical delay information sub-feature items, departure and landing place information sub-feature items, navigation weather information sub-feature items and the like.
And configuring a feature value mapping table of each sub-feature item according to the actual situation corresponding to the sub-feature item, wherein the feature value mapping table is used for generating the sub-feature value of the sub-feature according to the feature information in the corresponding sub-feature item. And if the corresponding sub-feature item does not have feature information, the sub-feature value of the sub-feature is 0.
The navigation weather sub-feature item is taken as an example for explanation: the feature value mapping table corresponding to the sub-feature item may be: the characteristic value corresponding to sunny days is 0, the characteristic value corresponding to light rain is 1, the characteristic value corresponding to medium rain is 2, and the characteristic value corresponding to heavy rain is 3.
When the preset matching rule is the first type of preset rule, step S200: the preset matching rule in the main matching module carries out first matching processing on the target characteristic information to generate first matching information, and the first matching information comprises the following steps:
step S203: e according to at least one sub-feature corresponding to each sub-matching module 1 ,e 2 ,…,e k ,…,e p And acquiring a sub-characteristic value corresponding to each sub-matching module as a target characteristic value.
Step S204: generating a target characteristic set F corresponding to each sub-matching module according to the target characteristic value corresponding to each sub-matching module 1 ,F 2 ,…,F i ,…,F n Wherein, the target feature set F corresponding to the ith sub-matching module i Is composed of all its corresponding target characteristic values, and F i ＝(f i1 ,f i2 ,…,f ig ,…，f iQ )，F i A target feature set f corresponding to the ith sub-matching module ig Is F i G =1,2, …, Q. p is not less than Q, Q is F i The total number of target characteristic values.
Step S205: according to F 1 ,F 2 ,…,F n Generating a first matching value a corresponding to each sub-matching module 1 ,a 2 ,…,a i ,…,a n Wherein a is i The following conditions are satisfied:
a i ＝∑ Q g＝1 f ig 。
in actual use, each sub-matching module corresponds to one matching category, and each matching category corresponds to at least one influencing sub-item, which is also a sub-feature item. Each sub-matching module corresponds to at least one sub-feature item. In this embodiment, the sub-feature items corresponding to each sub-matching module may be determined by a preset matching rule, and the sum of the feature values of the corresponding sub-feature items is used as the first matching value of the corresponding sub-matching module. The sub-matching module is used for explaining the case that one matching category corresponding to the sub-matching module is a flight delay category, and the sub-feature items determined by the matching category through a preset matching rule can comprise a navigation weather sub-feature item and a historical delay information sub-feature item. If the feature value corresponding to the navigation weather sub-feature item is 2 and the feature value corresponding to the history delay information sub-feature item is 3, the first matching value corresponding to the sub-matching module is 5.
In this embodiment, the sum of the target feature values in the target feature set corresponding to the sub-matching modules is determined as the first matching value of the corresponding matching module, so that the assignment can be performed more accurately for the matching category corresponding to each matching module. Therefore, which matching categories are more interesting to the user can be more accurately determined in the process of judging. That is, which sub-matching modules are the initial matching modules can be determined more accurately.
As a possible embodiment of the present invention, in step S200: after the main matching module performs first matching processing on the target feature information according to a preset matching rule configured by the main matching module to generate first matching information, the method further includes:
step S210: and when the preset matching rule is a second type of preset rule, the correspondingly generated first matching information is preset event information. And when the first matching information is the preset event information, determining the first matching information as the target matching information.
The second type of preset rule is a rule which can directly determine target matching information according to the target characteristic information. In an actual use process, when some corresponding sub-feature values in several sub-feature values included in the target feature information meet a preset condition, the determined first matching information is the same as the target matching information determined in the above embodiment in a hierarchical matching manner. Therefore, at this time, the target matching information is not determined according to the step of hierarchical matching mentioned in the previous embodiment, but the first matching information is directly determined as the target matching information. Therefore, the matching steps can be saved, and the whole generation process of the matching information is more efficient and faster.
As a possible embodiment of the present invention, the matching system further includes a preset information base, and the preset information base includes a plurality of second matching information.
In step S200: after the main matching module performs first matching processing on the target feature information according to a preset matching rule configured by the main matching module to generate first matching information, the method further includes:
step S220: and when the first matching information is the empty set, acquiring second matching information from a preset information base and determining the second matching information as target matching information.
In this embodiment, the preset information base includes a plurality of pieces of second matching information as bottom-of-pocket information, and when first matching processing is performed on the target feature information and the generated first matching information is empty, one piece of second matching information is determined as the target matching information. Thus, it can be ensured that the target matching information can be generated under any condition.
As one possible embodiment of the present invention, in step S401: obtaining a matching weight value d corresponding to each initial matching module 1 ,d 2 ,…,d j ,…,d m Previously, the method further comprises:
step S411: from F 1 ,F 2 ,…,F i ,…,F n The sub-target feature set H corresponding to each initial matching module is obtained 1 ,H 2 ,…,H j ,…,H m Wherein H is j ＝(H j1 ,H j2 ,…,H jt ,…,H jr )，H j Is the sub-target feature set corresponding to the jth initial matching module, H jt Is H j The t-th target feature value of (1). t =1,2, …, r. p is more than or equal to r, r is H j The total number of target characteristic values.
Step S421: according to the sub-target feature set H corresponding to each initial matching module 1 ,H 2 ,…,H j ,…,H m Generating a matching weight value d corresponding to each initial matching module 1 ,d 2 ,…,d j ,…,d m Wherein d is j The following conditions are satisfied:
d j ＝k j1 *H j1 +k j2 *H j2 +…+k jr *H jr 。
wherein k is j1 ,k j1 ,…,k jr Are respectively H j1 ,H j2 ,…,H jr Corresponding impact weight coefficients.
k j1 ,k j1 ,…,k jr Are respectively equal to H 1 ,H 2 ,…,H m The degree of influence of the corresponding sub-feature item on the matching category is proportional. Specifically, the larger the influence degree of the corresponding sub-feature item on the matching category is, the larger the numerical value of the influence weight coefficient of the corresponding sub-feature item to the matching is. Therefore, the matching weight value corresponding to each initial matching module which is finally calculated can better accord with the actual use condition, and the accuracy of the finally generated target matching information can be further ensured.
Corresponding an initial matching module to a matching classThe category is explained as the class of flight delay, and the sub-target feature set H corresponding to the initial matching module j Target characteristic value H comprising navigation weather sub-characteristic item j1 And the characteristic value H of the sub-characteristic item of the history delay information j2 . Since the influence degree of the navigation weather sub-feature item on flight delay is larger, the corresponding influence weight coefficient can be determined as follows: k is a radical of j1 ＝2，k j2 ＝1。
In addition, the influence weight coefficient may also be determined according to a function in which K is jt ＝I jt /G jt (ii) a Wherein, I jt For H within a preset time period jt The total browsing duration of the display information of the corresponding sub-feature item; g jt For H within a preset time period jt And the total browsing times of the display information of the corresponding sub-characteristic item. The preset time period may be a time period from a point in time when the user purchases a flight ticket to a point in time when the flight takes off. The presentation information may be historical information and/or future prediction information corresponding to one sub-feature item.
Taking the navigation weather sub-feature item as an example, the corresponding display information may be weather information in the navigation period of the corresponding flight. Or, taking the historical delay information sub-feature item as an example, the corresponding display information may be delay information of each flight in the last 7 flights of the corresponding flight, where the delay information includes two kinds of information, namely punctuation and delay. In addition, in order to obtain more accurate calculation results, the total browsing times can be the sum of the browsing times of all users who purchase the same flight and the display information of the corresponding sub-feature item. The total browsing duration may be the sum of browsing durations of all users who purchase the same flight for the presentation information of the corresponding sub-feature item.
Therefore, the influence weight coefficient of each sub-feature item can be determined according to the average browsing time of each sub-feature item in the preset time period, and the influence weight coefficient of each sub-feature item can be more accurate along with the time.
Further, in step S411: from F 1 ,F 2 ,…,F i ,…,F n Each initial matching module is obtainedCorresponding set of sub-target characteristics H 1 ,H 2 ,…,H j ,…,H m Afterwards, the method further comprises the following steps:
step S431: according to the sub-target feature set H corresponding to each initial matching module 1 ,H 2 ,…,H j ,…,H m Generating a matching weight value d corresponding to each initial matching module 1 ,d 2 ,…,d j ,…,d m Wherein d is j The following conditions are satisfied:
d j ＝r*(k j1 *H j1 +k j2 *H j2 +…+k jr *H jr )。
in practical use, each influencing sub-item corresponding to the matching category can cause an event corresponding to the matching category to be triggered. If the flight delay category corresponds to two influence sub-items, namely a navigation weather sub-characteristic item and a historical delay information sub-characteristic item, any one of the influence sub-items can cause a flight delay event to be triggered. Therefore, when the number of the influencing sub-items corresponding to one matching category is larger, the event corresponding to the matching category is more easily triggered, and therefore the target matching information corresponding to the matching category is more easily generated.
Therefore, in this embodiment, the matching weight value and the number of the target feature values in the sub-target feature set corresponding to the initial matching module are set to be positively correlated, so that the accuracy of the finally generated target matching information can be further ensured.
Embodiments of the present invention also provide a non-transitory computer-readable storage medium, which may be disposed in an electronic device to store at least one instruction or at least one program for implementing a method of the method embodiments, where the at least one instruction or the at least one program is loaded into and executed by a processor to implement the method provided by the above embodiments.
Embodiments of the present invention also provide an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium.
Embodiments of the present invention further provide a computer program product comprising program code means for causing an electronic device to carry out the steps of the method according to various exemplary embodiments of the invention described above when the program product is run on the electronic device.
Although some specific embodiments of the present invention have been described in detail by way of illustration, it should be understood by those skilled in the art that the above illustration is only for the purpose of illustration and is not intended to limit the scope of the invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.
Claims (10)
1. The method for generating the matching information is characterized by being applied to a matching system, wherein the matching system comprises an information acquisition module, a main matching module and a plurality of sub-matching modules; the information acquisition module is in communication connection with the main matching module; the main matching module is respectively in communication connection with the plurality of sub-matching modules; the main matching module and the sub matching module are both provided with a plurality of preset matching rules;
controlling the matching system to operate according to a first method so as to generate corresponding matching information according to the characteristic information of the user; the first method comprises the following steps:
the information acquisition module acquires target characteristic information;
the main matching module carries out first matching processing on the target characteristic information according to a preset matching rule configured by the main matching module so as to generate first matching information;
when the first matching information contains n first matching values a 1 ,a 2 ,…,a i ,…,a n When the information is received, the main matching module judges each first matching value so as to determine an initial matching module from the plurality of sub-matching modules; wherein each first matching value is used for representing a preset matching category of the corresponding sub-matching module, a i The main matching module carries out first matching processing on the target characteristic information according to a preset rule configured by the main matching module to obtainThe first matching value of the ith sub-matching module of (1); i =1,2, …, n; n is the total number of sub-matching modules;
the main matching module determines an initial matching module with a matching weight value larger than a first threshold value from the plurality of initial matching modules as a target sub-matching module;
each target sub-matching module carries out second matching processing on the target characteristic information according to a preset matching rule configured by the target sub-matching module so as to generate corresponding target matching information; the preset matching rule configured by the main matching module is used for determining a preset matching category corresponding to the target characteristic information, and each sub-matching module only corresponds to one preset matching category; the preset matching rules configured by the sub-matching module are used for determining preset sub-categories corresponding to the target characteristic information, and each preset matching category comprises at least one corresponding preset sub-category;
the determination process includes:
obtaining a matching grade value b corresponding to each first matching value 1 ,b 2 ,…,b i ,…,b n ，b i The following conditions are satisfied:
b i ＝a i -c i (ii) a Wherein, c i Is a i Corresponding matching threshold, b i Is a i Corresponding matching grade values;
whenever b is i >At 0, a is judged i The corresponding sub-matching module is the initial matching module.
2. The method of claim 1, wherein the initial matching module is plural;
the main matching module determines a target sub-matching module from the initial matching module, and the method comprises the following steps:
obtaining a matching weight value d corresponding to each initial matching module 1 ,d 2 ,…,d j ,…,d m Wherein d is j J =1,2, …, m, which is the matching weight value corresponding to the jth initial matching module; m is less than or equal to n, and m is the total number of the initial matching modules;
max (d) 1 ,d 2 ,…,d j ,…,d m ) The corresponding initial matching module is determined as a target sub-matching module; wherein Max () is a preset maximum function, max (d) 1 ,d 2 ,…,d j ,…,d m ) Is d 1 ,d 2 ,…,d j ,…,d m Is measured.
3. The method according to claim 2, wherein after the main matching module performs the first matching processing on the target feature information according to a preset matching rule configured by the main matching module to generate first matching information, the method further comprises:
and when the first matching information is preset event information, determining the first matching information as the target matching information.
4. The method according to claim 1, wherein the matching system further comprises a preset information base, and the preset information base comprises a plurality of second matching information;
after the main matching module performs first matching processing on the target feature information according to a preset matching rule configured by the main matching module to generate first matching information, the method further includes:
and when the first matching information is an empty set, acquiring one piece of second matching information from the preset information base and determining the second matching information as the target matching information.
5. The method according to claim 3, wherein the preset matching rule in the main matching module is a first type of preset rule or a second type of preset rule;
the main matching module performs first matching processing on the target feature information according to a preset matching rule configured by the main matching module to generate first matching information, and the first matching processing comprises the following steps:
when the preset matching rule is a first-class preset rule, the first matching information generated correspondingly is a 1 ,a 2 ,…,a i ,…,a n ；
When the preset matching rule is a second type of preset rule, the correspondingly generated first matching information is the preset event information; the second type of preset rule is a rule for directly determining target matching information according to the target characteristic information.
6. The method according to claim 5, wherein the target feature information comprises a plurality of sub-feature values e 1 ,e 2 ,…,e k ,…,e p Wherein e is k Is the kth sub-feature value; k =1,2, …, p; p is more than or equal to n, and p is the total number of the sub-characteristic values; at least one sub-feature corresponding to each sub-matching module; each sub-feature uniquely corresponds to one sub-feature value;
when the preset matching rule is a first type of preset rule, the main matching module performs first matching processing on the target feature information according to the preset matching rule configured by the main matching module to generate first matching information, including:
e according to at least one sub-feature corresponding to each sub-matching module 1 ,e 2 ,…,e k ,…,e p Obtaining a sub-characteristic value corresponding to each sub-matching module as a target characteristic value;
generating a target feature set F corresponding to each sub-matching module according to the target feature value corresponding to each sub-matching module 1 ,F 2 ,…,F i ,…,F n Wherein, the target characteristic set F corresponding to the ith sub-matching module i Is composed of all its corresponding target characteristic values, and F i ＝(f i1 ,f i2 ,…,f ig ,…，f iQ )，F i A target feature set f corresponding to the ith sub-matching module ig Is F i G =1,2, …, Q; p is not less than Q, Q is F i The total number of target feature values;
according to F 1 ,F 2 ,…,F n Generating a first matching value a corresponding to each sub-matching module 1 ,a 2 ,…,a i ,…,a n Wherein a is i The following conditions are satisfied:
a i ＝∑ Q g＝1 f ig 。
7. the method of claim 6, wherein a matching weight value d corresponding to each initial matching module is obtained 1 ,d 2 ,…,d j ,…,d m Previously, the method further comprises:
from F 1 ,F 2 ,…,F i ,…,F n Obtaining a sub-target feature set H corresponding to each initial matching module 1 ,H 2 ,…,H j ,…,H m Wherein H is j ＝(H j1 ,H j2 ,…,H jt ,…,H jr )，H j Is the sub-target feature set corresponding to the jth initial matching module, H jt Is H j The tth target feature value of (1); t =1,2, …, r; p is more than or equal to r, r is H j The total number of target feature values;
according to the sub-target feature set H corresponding to each initial matching module 1 ,H 2 ,…,H j ,…,H m Generating a matching weight value d corresponding to each initial matching module 1 ,d 2 ,…,d j ,…,d m Wherein d is j The following conditions are satisfied:
d j ＝k j1 *H j1 +k j2 *H j2 +…+k jr *H jr ；
wherein k is j1 ,k j1 ,…,k jr Are respectively H j1 ,H j2 ,…,H jr Corresponding impact weight coefficients.
8. The method of claim 7, wherein d is j ＝k j1 *H j1 +k j2 *H j2 +…+k jr *H jr Replacing the steps as follows:
d j ＝r*(k j1 *H j1 +k j2 *H j2 +…+k jr *H jr )。
9. a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a method of generating matching information according to any one of claims 1 to 8.
10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements a method of generating matching information according to any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211124446.6A CN115374366B (en) | 2022-09-15 | 2022-09-15 | Matching information generation method, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211124446.6A CN115374366B (en) | 2022-09-15 | 2022-09-15 | Matching information generation method, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115374366A true CN115374366A (en) | 2022-11-22 |
| CN115374366B CN115374366B (en) | 2023-04-07 |
Family
ID=84071316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211124446.6A Active CN115374366B (en) | 2022-09-15 | 2022-09-15 | Matching information generation method, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115374366B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291733A (en) * | 2016-03-31 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of method and device for rule matching |
| US20190317954A1 (en) * | 2014-01-06 | 2019-10-17 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for processing text information |
| CN110377702A (en) * | 2019-07-18 | 2019-10-25 | 中科鼎富（北京）科技发展有限公司 | A kind of biographic information matching process and device |
| CN111104588A (en) * | 2019-11-11 | 2020-05-05 | 广州赛宝认证中心服务有限公司 | Product information matching method and device, computer equipment and storage medium |
| CN111177362A (en) * | 2019-12-30 | 2020-05-19 | 深圳市梦网科技发展有限公司 | Information processing method, device, server and medium |
| CN113344433A (en) * | 2021-06-28 | 2021-09-03 | 平安信托有限责任公司 | Product matching method and device, electronic equipment and readable storage medium |
| CN114153962A (en) * | 2021-11-26 | 2022-03-08 | 浙江大华技术股份有限公司 | Data matching method and device and electronic equipment |
| CN114461909A (en) * | 2022-02-07 | 2022-05-10 | 北京沃东天骏信息技术有限公司 | Information processing method, information processing apparatus, electronic device, and storage medium |
-
2022
- 2022-09-15 CN CN202211124446.6A patent/CN115374366B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190317954A1 (en) * | 2014-01-06 | 2019-10-17 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for processing text information |
| CN107291733A (en) * | 2016-03-31 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of method and device for rule matching |
| CN110377702A (en) * | 2019-07-18 | 2019-10-25 | 中科鼎富（北京）科技发展有限公司 | A kind of biographic information matching process and device |
| CN111104588A (en) * | 2019-11-11 | 2020-05-05 | 广州赛宝认证中心服务有限公司 | Product information matching method and device, computer equipment and storage medium |
| CN111177362A (en) * | 2019-12-30 | 2020-05-19 | 深圳市梦网科技发展有限公司 | Information processing method, device, server and medium |
| CN113344433A (en) * | 2021-06-28 | 2021-09-03 | 平安信托有限责任公司 | Product matching method and device, electronic equipment and readable storage medium |
| CN114153962A (en) * | 2021-11-26 | 2022-03-08 | 浙江大华技术股份有限公司 | Data matching method and device and electronic equipment |
| CN114461909A (en) * | 2022-02-07 | 2022-05-10 | 北京沃东天骏信息技术有限公司 | Information processing method, information processing apparatus, electronic device, and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| WANG NIHONG 等: "The Research on Identification Model and Related Regulation Strategies Selection for Forest Disease and Insect Pest", 《2009 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTATION TECHNOLOGY AND AUTOMATION》 * |
| 任宁 等: "基于分段分级的地址归一化匹配技术", 《信息与电脑（理论版）》 * |
| 方志坚等: "基于置信规则库推理的多属性双边匹配决策方法", 《南京大学学报(自然科学)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115374366B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200293924A1 (en) | Gbdt model feature interpretation method and apparatus | |
| US6397200B1 (en) | Data reduction system for improving classifier performance | |
| KR101699720B1 (en) | Apparatus for voice command recognition and method thereof | |
| CN113657465A (en) | Pre-training model generation method and device, electronic equipment and storage medium | |
| CN109598566B (en) | Ordering prediction method, ordering prediction device, computer equipment and computer readable storage medium | |
| CN110472675A (en) | Image classification method, image classification device, storage medium and electronic equipment | |
| US10592550B2 (en) | System and method for species and object recognition | |
| CN106919957B (en) | Method and device for processing data | |
| CN113222942A (en) | Training method of multi-label classification model and method for predicting labels | |
| CN104599002B (en) | Method and equipment for predicting order value | |
| CN113177968A (en) | Target tracking method and device, electronic equipment and storage medium | |
| US20200272906A1 (en) | Discriminant model generation device, discriminant model generation method, and discriminant model generation program | |
| US20190311288A1 (en) | Method for machine learning, non-transitory computer-readable storage medium for storing program, apparatus for machine learning | |
| CN115374366B (en) | Matching information generation method, storage medium and electronic equipment | |
| WO2024067137A1 (en) | Intelligent endurance management method and system for unmanned aircraft, and medium | |
| CN110348581B (en) | User feature optimizing method, device, medium and electronic equipment in user feature group | |
| CN117034090A (en) | Model parameter adjustment and model application methods, devices, equipment and media | |
| CN104572820B (en) | The generation method and device of model, importance acquisition methods and device | |
| CN116342164A (en) | Target user group positioning method and device, electronic equipment and storage medium | |
| CN115641470A (en) | Method, device and equipment for training classification model and vehicle image classification model | |
| US20220051569A1 (en) | Flight risk analysis system | |
| CN115375869A (en) | Robot repositioning method, robot and computer-readable storage medium | |
| US20170300825A1 (en) | Hidden markov model for jammer behavior prediction | |
| CN110347583A (en) | A kind of data analysis system consultation of doctors method and relevant apparatus | |
| CN111382247A (en) | Content pushing optimization method, content pushing optimization device and electronic equipment |
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 |