CN111951070B - Intelligent recommendation method, device, server and storage medium based on Internet of Vehicles - Google Patents
Intelligent recommendation method, device, server and storage medium based on Internet of Vehicles Download PDFInfo
- Publication number
- CN111951070B CN111951070B CN202010759544.1A CN202010759544A CN111951070B CN 111951070 B CN111951070 B CN 111951070B CN 202010759544 A CN202010759544 A CN 202010759544A CN 111951070 B CN111951070 B CN 111951070B
- Authority
- CN
- China
- Prior art keywords
- phrase
- behavior data
- preset
- data
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000011218 segmentation Effects 0.000 claims abstract description 46
- 230000006399 behavior Effects 0.000 claims description 179
- 238000011157 data evaluation Methods 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 abstract description 26
- 238000010586 diagram Methods 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides an intelligent recommendation method, device, server and storage medium based on the Internet of vehicles, wherein the method comprises the following steps: acquiring behavior data of a user; identifying user preference characteristics in the behavior data according to a word segmentation algorithm; the service of the Internet of vehicles is recommended according to the user preference characteristics, so that the user preference characteristics in the implicit behavior data can be identified according to the word segmentation algorithm, the user preference characteristics can be better identified, and the service recommendation efficiency of the Internet of vehicles is improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an intelligent recommendation method, device, server and storage medium based on the internet of vehicles.
Background
In existing vehicle network-based recommendation systems, user preference characteristics, such as user interests, etc., can be clarified based on explicit preference information feedback. However, there are many scenarios where explicit preference information does not exist, and user preference characteristics cannot be directly acquired. Therefore, how to better identify the preference characteristics of the user, and how to increase the effectiveness of intelligent recommendation of the vehicle network need to be solved.
Disclosure of Invention
The embodiment of the application provides an intelligent recommendation method, device, server and storage medium based on the Internet of vehicles, which can identify user preference characteristics in implicit behavior data according to a word segmentation algorithm, so that the user preference characteristics can be better identified, and the Internet of vehicles service recommendation efficiency is improved.
A first aspect of an embodiment of the present application provides an intelligent recommendation method based on internet of vehicles, the method including:
acquiring behavior data of a user;
identifying user preference characteristics in the behavior data according to a word segmentation algorithm;
and recommending the service of the Internet of vehicles according to the user preference characteristics.
A second aspect of the embodiments of the present application provides an intelligent recommendation device based on internet of vehicles, the device including:
the acquisition unit is used for acquiring behavior data of the user;
the identification unit is used for identifying user preference characteristics in the behavior data according to a word segmentation algorithm;
and the recommending unit is used for recommending the service of the Internet of vehicles according to the user preference characteristics.
A third aspect of the embodiments of the present application provides an intelligent recommendation apparatus based on internet of vehicles, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing steps in the method according to the first aspect of the embodiments of the present application.
A fourth aspect of the embodiments of the present application provides a computer readable storage medium for storing a computer program for execution by a processor to implement some or all of the steps described in the method of the first aspect of the embodiments of the present application.
A fifth aspect of the embodiments of the present application provides a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the method of the first aspect of the embodiments of the present application.
The implementation of the embodiment of the application has at least the following beneficial effects:
it can be seen that, according to the embodiment of the present application, behavior data of a user is obtained; identifying user preference characteristics in the behavior data according to a word segmentation algorithm; the service of the Internet of vehicles is recommended according to the user preference characteristics, so that the user preference characteristics in the implicit behavior data can be identified according to the word segmentation algorithm, the user preference characteristics can be better identified, and the service recommendation efficiency of the Internet of vehicles is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a system architecture diagram of an intelligent recommendation device based on internet of vehicles, provided in an embodiment of the present application;
fig. 2A is a schematic flow chart of an intelligent recommendation method based on internet of vehicles according to an embodiment of the present application;
fig. 2B is a schematic flow chart of another intelligent recommendation method based on internet of vehicles according to an embodiment of the present application;
fig. 3 is a schematic flow chart of another intelligent recommendation method based on internet of vehicles according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a server according to an embodiment of the present application;
fig. 5A is a schematic structural diagram of an intelligent recommendation device based on internet of vehicles according to an embodiment of the present application;
fig. 5B is a modified structure of the intelligent recommendation device based on internet of vehicles shown in fig. 5A according to the embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.
The embodiments of the present application are described in detail below.
Referring to fig. 1, fig. 1 is a schematic architecture diagram of an intelligent recommendation system based on internet of vehicles, where the intelligent recommendation system based on internet of vehicles includes: the system comprises a data processing module, a preference characteristic identification module, a data distribution module and a service recommendation module; wherein,
the data processing module is used for acquiring behavior data of a user, and the behavior data of the user can comprise at least one of the following: retrieval information, subscription information, browsing information, application use information, etc., specifically, retrieval information, subscription information, browsing information, application use information, etc. of a user may be obtained from a terminal device, a car machine, a service system, or other network information platforms; the data processing module is also used for acquiring task scheduling data of the data calculation batch; and inputting the behavior data of the user to the preference feature identification module in batches through a real-time data stream according to the task scheduling data.
Optionally, the data processing module is further configured to filter the behavior data to obtain filtered behavior data; cleaning the filtered behavior data to obtain cleaned behavior data; classifying the cleaned behavior data to obtain classified behavior data; and storing the classified behavior data into a database. Therefore, invalid behavior data can be filtered, the quality of the behavior data is optimized, and unnecessary subsequent data identification is reduced.
The preference feature recognition module comprises a dictionary library construction service and a data matching service, wherein the dictionary library construction service is used for constructing a first dictionary library and constructing a second dictionary library, and the first dictionary library can comprise word groups for implicitly feeding back preference features of a user. The second dictionary library may include a plurality of preset phrases that do not exhibit the user preference feature and that occur more frequently than a preset frequency threshold. The data processing module can match the user behavior data with a second preset phrase in the second dictionary base, and clean out invalid and redundant behavior data. The data matching service can match the behavior data with a first preset phrase of the first dictionary base, and identify the preference characteristics of the user. Further, the data distribution module may output the user's preference characteristics to the service recommendation module via a real-time data stream. And recommending the service of the Internet of vehicles by a service recommendation module according to the user preference characteristics. The service recommendation module can recommend at least one of the following service recommendation types in the internet of vehicles: vehicle usage services, vehicle performance services, driving pattern recommendations, driving route recommendations, and the like, without limitation.
Referring to fig. 2A, fig. 2A is a schematic flow chart of an intelligent recommendation method based on internet of vehicles according to an embodiment of the present application. As shown in fig. 2A, the intelligent recommendation method based on the internet of vehicles provided in the embodiment of the present application is applied to an intelligent recommendation device based on the internet of vehicles, and the intelligent recommendation method based on the internet of vehicles may include the following steps:
201. and acquiring behavior data of the user.
Wherein, the behavior data of the user may include at least one of the following: retrieve information, subscription information, browsing information, application usage information, etc., without limitation.
In the embodiment of the application, the search information, the subscription information, the browsing information, the application program use information and the like of the user can be obtained from the terminal equipment, the vehicle machine, the service system or other network information platforms. The behavior data may include data in at least one of the following areas: food, music, scenic spots, hotels, gas stations, etc.
202. User preference features in the behavioral data are identified according to a word segmentation algorithm.
In the embodiment of the application, the behavior data with implicit feedback of the user preference can exist, the behavior data does not obviously show the preference characteristics of the user, and the preference characteristics of the user can not be directly extracted from the behavior data, so that the user preference characteristics in the behavior data can be identified according to the word segmentation algorithm, and the user preference characteristics are the user preference characteristics with implicit feedback in the behavior data.
Optionally, in step 202, the identifying the user preference feature in the behavior data according to a word segmentation algorithm includes:
21. constructing a first dictionary database;
22. word segmentation is carried out on the behavior data to obtain a single character set comprising a plurality of single characters;
23. and combining the words according to the order of the word numbers from small to large to obtain a first phrase, matching the first phrase with a first preset phrase in the first dictionary base, and if the first phrase is successfully matched with the first preset phrase, incorporating the first phrase into the user preference feature.
The first dictionary library can be constructed, and can comprise word groups for implicitly feeding back preference characteristics of the user, and specifically, the first dictionary library can comprise preset word groups in the fields of food, music, scenic spots, hotels, gas stations and the like. Therefore, the first phrase obtained by word segmentation can be matched with a first preset phrase in the first dictionary base, and user preference characteristics can be identified.
The behavior data may be divided into a plurality of words to obtain a word set, and then the words are combined to obtain a first phrase, in which, in a specific implementation, consecutive words may be first formed into a phrase with a minimum number, for example, if two words may form a phrase, then the first phrases of two words are formed; if three continuous words can form a phrase, a first phrase of the three words is formed.
For example, when a user travels, a travel group is reported on a terminal device of a mobile phone or a computer, and the travel route is recorded by the terminal device, travel behavior data can be generated, where the travel behavior data can include: travel mode, travel scenic spot, travel route, food, scenery picture, etc., for example, travel behavior data comprises a self-driving trip strategy, the travel behavior data can be segmented to obtain a word set comprising self-driving, running, tapping and slightly, then word combination is carried out according to the sequence of the word numbers from small to large to obtain self-driving, the self-driving is matched with a first preset word group in a first dictionary library, if the word group comprises the self-driving word group, the word group also comprises other word words, the word group can be continuously combined to obtain the self-driving trip, the self-driving trip is matched with a first preset word group in the first dictionary library, and if the first dictionary library comprises the self-driving trip, the self-driving trip of the first word group is successfully matched with the first preset word group, the self-driving trip of the first word group is incorporated into the user preference feature.
Optionally, after the matching the first phrase with a first preset phrase in the dictionary base, the method further includes:
24. if the first phrase is a part of the first preset phrase, adding at least one single word behind the first phrase to form a new first phrase;
25. and matching the new first phrase with the first preset phrase, and if the new first phrase is successfully matched with the first preset phrase, incorporating the new first phrase into the user preference feature.
If the first word group is formed, a new first word group can be formed by the first word group and other single words, and the formed first word group can be matched with a first preset word group in a first dictionary base; and matching the new first phrase with a first preset phrase in the first dictionary database, so that the combination form of missing phrases can be avoided, and the accuracy of user preference identification is improved.
Optionally, before the identifying the user preference feature in the behavior data according to the word segmentation algorithm, the method further comprises:
a1, filtering the behavior data to obtain filtered behavior data;
a2, cleaning the filtered behavior data to obtain cleaned behavior data;
a3, classifying the cleaned behavior data to obtain classified behavior data; and storing the classified behavior data into a database.
The behavior data is filtered to obtain filtered behavior data, specifically, preset data conditions can be set, and data meeting the preset data conditions is filtered, wherein the preset data conditions specifically can include at least one of the following: character strings belonging to preset character types, such as ellipses, exclamation marks, non-english word letters, etc.; repeating a phrase or sentence; the data length is smaller than the preset length; belonging to a preset data format, for example, data in tables, brackets, signature numbers, quotation marks. Therefore, the behavior data which do not meet the preset data conditions can be filtered, invalid data can be removed, and the data quality is improved.
Optionally, in the step A1, the filtering the behavior data to obtain filtered behavior data includes:
a11, constructing a data evaluation function;
a12, evaluating the behavior data according to the data evaluation function to obtain a data evaluation value;
and A13, filtering the behavior data with the corresponding data evaluation value lower than a preset value in the behavior data.
In a specific implementation, the behavior data may be analyzed to obtain at least one data evaluation index parameter, where the data evaluation index parameter may include at least one of: and substituting at least one data evaluation index parameter into a data evaluation function to calculate to obtain a data evaluation value, wherein if the data evaluation value is lower than a preset value, the behavior data does not accord with the preset data condition, so that the behavior data, corresponding to the behavior data, with the data evaluation value lower than the preset value can be filtered.
The data instantaneity level refers to a level for dividing the data instantaneity, specifically, the closer the time of data generation is to the current time, the higher the data instantaneity is, the better the current preference of the user can be reflected, the longer the time of data generation is from the current time, the lower the instantaneity is, and the situation that the preference of the user is changed may exist. The data timeliness grade is a grade of grading the data timeliness, specifically, the data timeliness is the effectiveness of preference characteristics of the data feedback user in the time dimension, in practical application, some preference of the user may be maintained for a longer time, and some preference may be maintained for a shorter time, so that the higher the data effectiveness grade of the preference characteristics of the behavior data feedback user is, the longer the data effectiveness is, and the lower the data effectiveness grade of the preference characteristics of the behavior data feedback user is, the shorter the data effectiveness is. In addition, the greater the degree of association between the behavior data and the preference feature, the more the behavior data can feed back the preference feature of the user, and the smaller the degree of association between the data and the preference feature, the more difficult the behavior data feeds back the preference feature of the user, so that the behavior data can be analyzed to obtain at least one of the following data evaluation index parameters: the data real-time level, the data timeliness level and the association degree of behavior data and preference characteristics; and then calculating according to the data real-time grade, the data timeliness grade, the association degree of the behavior data and the preference characteristics and the data evaluation function to obtain a data evaluation value, so that the data can be evaluated more accurately, and the behavior data with the data evaluation value lower than a preset value can be filtered.
Optionally, in the step A2, the cleaning the behavior data to obtain cleaned behavior data includes:
a21, word segmentation is carried out on the behavior data to obtain a plurality of second phrase groups;
a22, constructing a second dictionary database;
a23, sequentially matching the plurality of second phrases with second preset phrases in the second dictionary database, and deleting the second phrases repeatedly appearing in the behavior data if the second phrases are successfully matched with the second preset phrases.
The second dictionary library can be constructed, and the first dictionary library can comprise a plurality of preset phrase groups which do not reflect the preference characteristics of the user and have the occurrence frequency larger than a preset frequency threshold value. Therefore, the second phrase obtained by word segmentation can be matched with a second preset phrase in the second dictionary database, if the second phrase is successfully matched with the second preset phrase in the second dictionary database, all second phrases which are repeated with the successfully matched second phrase are searched in the behavior data, and are deleted, so that the quality of the behavior data can be further optimized.
Optionally, in step a23, the matching the plurality of second phrases with the second preset phrases in the second dictionary database sequentially includes:
matching the words at two ends of the second phrase with the words at two ends of the second preset phrase; if the matching is successful, the remaining single words in the second phrase and the second preset phrase are matched according to the sequence from two ends to the middle until the second phrase and all the single words in the second preset phrase are successfully matched, and the second phrase and the second preset phrase are successfully matched.
The second word group and the single words in the second preset word group can be matched according to the sequence from two ends to the middle, so that if the single words at two ends are not successfully matched, the continuous matching of the middle single word is not needed, and if the single words at two ends are successfully matched, the continuous matching of the middle single word is realized, thereby reducing the matching time and improving the matching efficiency.
For example, referring to fig. 2B, fig. 2B is a flow chart of another intelligent recommendation method based on internet of vehicles according to an embodiment of the present application, where behavior data of a user may be obtained, where the behavior data of the user may include at least one of the following: retrieving information, subscription information, browsing information, application program use information and the like, filtering and cleaning behavior data to obtain behavior data with more optimized quality, and storing the optimized behavior data into a database; and then retrieving behavior data from the database in batches, and performing word segmentation on the behavior data according to a word segmentation algorithm, wherein the word segmentation algorithm can be specifically called, the word segmentation algorithm can be a bidirectional maximum matching word segmentation algorithm, then performing circular word segmentation to obtain a first word group, searching whether a preset first dictionary library comprises the first word group, if yes, storing the first word group as a preference characteristic of a user, if not, judging whether the first word group is a word group obtained by last word segmentation, if yes, ending the word segmentation flow, and if not, continuing to identify the preference characteristic of the user according to the first word group obtained by the next word segmentation.
203. And recommending the service of the Internet of vehicles according to the user preference characteristics.
Wherein, the service recommendation of the vehicle network may include at least one of the following service recommendation types: vehicle usage services, vehicle performance services, driving pattern recommendations, driving route recommendations, etc., without limitation, for example, if the user preference characteristics described above include user preference characteristics for attractions, a route including user-preferred attractions may be recommended to the user in the driving route recommendation service. For another example, when the user wants to rent, get a car or purchase a car, the user may be recommended a model, brand car that meets the user's preference according to the user's preference characteristics. For another example, when the user drives the vehicle, the vehicle-mounted music may be played according to the user's preference characteristics for music (e.g., the user's preferred style of music).
It can be seen that, in the embodiment of the present application, behavior data of a user is obtained; identifying user preference characteristics in the behavior data according to a word segmentation algorithm; the service of the Internet of vehicles is recommended according to the user preference characteristics, so that the user preference characteristics in the implicit behavior data can be identified according to the word segmentation algorithm, the user preference characteristics can be better identified, and the service recommendation efficiency of the Internet of vehicles is improved.
Referring to fig. 3, fig. 3 is a flow chart of another intelligent recommendation method based on the internet of vehicles provided in an embodiment of the present application, where the intelligent recommendation method based on the internet of vehicles provided in the embodiment of the present application is applied to an intelligent recommendation device based on the internet of vehicles, and the intelligent recommendation method based on the internet of vehicles includes:
301. and acquiring behavior data of the user.
302. And constructing a data evaluation function.
Alternatively, the data evaluation function may be:
Z＝u*S*D/T
wherein Z is a data evaluation value, S is a data real-time performance grade, T is a data timeliness grade, u is a data value factor, and D is the association degree of behavior data and preference characteristics.
303. And evaluating the behavior data according to the data evaluation function to obtain a data evaluation value.
304. And filtering the behavior data with the corresponding data evaluation value lower than a preset value in the behavior data.
305. And word segmentation is carried out on the behavior data to obtain a plurality of second phrase groups.
306. A second dictionary library is constructed.
307. And sequentially matching the plurality of second phrases with second preset phrases in the second dictionary base, and deleting the second phrases repeatedly appearing in the behavior data if the second phrases are successfully matched with the second preset phrases, so as to obtain the behavior data after cleaning.
308. Classifying the cleaned behavior data to obtain classified behavior data; and storing the classified behavior data into a database.
309. And constructing a first dictionary base, and performing word segmentation on the behavior data to obtain a single word set comprising a plurality of single words.
310. And combining the words according to the order of the word numbers from small to large to obtain a first phrase, matching the first phrase with a first preset phrase in the first dictionary base, and if the first phrase is successfully matched with the first preset phrase, incorporating the first phrase into the user preference feature.
311. And recommending the service of the Internet of vehicles according to the user preference characteristics.
The specific implementation process of 301-311 may refer to the corresponding description in the method shown in fig. 1, and will not be described herein.
It can be seen that, in the embodiment of the present application, the behavior data after being filtered is obtained by filtering the behavior data; word segmentation is carried out on the behavior data to obtain a plurality of second phrase groups; constructing a second dictionary database; sequentially matching the plurality of second phrases with second preset phrases in a second dictionary database, and deleting the second phrases repeatedly appearing in the behavior data if the second phrases are successfully matched with the second preset phrases; classifying the cleaned behavior data to obtain classified behavior data; storing the classified behavior data into a database to construct a first dictionary base; word segmentation is carried out on the behavior data to obtain a single character set comprising a plurality of single characters; and combining the plurality of single words according to the sequence from small number to large number of the single words to obtain a first phrase, matching the first phrase with a first preset phrase in the first dictionary base, if the first phrase is successfully matched with the first preset phrase, incorporating the first phrase into the user preference feature, recommending the service of the Internet of vehicles according to the user preference feature, filtering redundant behavior data, optimizing the quality of the behavior data, and improving the efficiency of identifying the user preference feature in the behavior data according to a word segmentation algorithm, thereby improving the service recommendation efficiency of the Internet of vehicles.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a server disclosed in an embodiment of the present application, as shown in the fig. 4, the server includes a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing the following steps:
acquiring behavior data of a user;
identifying user preference characteristics in the behavior data according to a word segmentation algorithm;
and recommending the service of the Internet of vehicles according to the user preference characteristics.
In one possible example, in said identifying user preference features in said behavioural data according to a word segmentation algorithm, the program comprises instructions for:
constructing a first dictionary database;
word segmentation is carried out on the behavior data to obtain a single character set comprising a plurality of single characters;
and combining the words according to the order of the word numbers from small to large to obtain a first phrase, matching the first phrase with a first preset phrase in the first dictionary base, and if the first phrase is successfully matched with the first preset phrase, incorporating the first phrase into the user preference feature.
In one possible example, after said matching the first phrase with a first preset phrase in the first dictionary base, the program further includes instructions for:
if the first phrase is a part of the first preset phrase, adding at least one single word behind the first phrase to form a new first phrase;
and matching the new first phrase with the first preset phrase, and if the new first phrase is successfully matched with the first preset phrase, incorporating the new first phrase into the user preference feature.
In one possible example, before the identifying of the user preference feature in the behavior data according to the word segmentation algorithm, the program further comprises instructions for:
filtering the behavior data to obtain filtered behavior data;
cleaning the filtered behavior data to obtain cleaned behavior data;
classifying the cleaned behavior data to obtain classified behavior data; and storing the classified behavior data into a database.
In one possible example, in said filtering the behavior data, resulting in filtered behavior data, the program comprises instructions for:
constructing a data evaluation function;
evaluating the behavior data according to the data evaluation function to obtain a data evaluation value;
and filtering the behavior data with the corresponding data evaluation value lower than a preset value in the behavior data.
In one possible example, in terms of said cleaning said behavior data resulting in cleaned behavior data, the program comprises instructions for:
word segmentation is carried out on the behavior data to obtain a plurality of second phrase groups;
constructing a second dictionary database;
and sequentially matching the plurality of second phrases with second preset phrases in the second dictionary database, and deleting the second phrases repeatedly appearing in the behavior data if the second phrases are successfully matched with the second preset phrases.
In one possible example, in said matching the plurality of second phrases with second preset phrases in the second dictionary library in sequence, the program includes instructions for:
matching the words at two ends of the second phrase with the words at two ends of the second preset phrase; if the matching is successful, the remaining single words in the second phrase and the second preset phrase are matched according to the sequence from two ends to the middle until the second phrase and all the single words in the second preset phrase are successfully matched, and the second phrase and the second preset phrase are successfully matched.
Referring to fig. 5A, fig. 5A is a schematic structural diagram of an intelligent recommendation device based on internet of vehicles according to an embodiment of the present application, where the intelligent recommendation device 500 based on internet of vehicles includes an obtaining unit 501, an identifying unit 502 and a recommending unit 503, where,
the acquiring unit 501 is configured to acquire behavior data of a user;
the identifying unit 502 is configured to identify user preference features in the behavior data according to a word segmentation algorithm;
the recommending unit 503 is configured to recommend the service of the internet of vehicles according to the user preference feature.
Optionally, in the aspect of identifying the user preference feature in the behavior data according to the word segmentation algorithm, the identifying unit 502 is specifically configured to:
constructing a first dictionary database;
word segmentation is carried out on the behavior data to obtain a single character set comprising a plurality of single characters;
and combining the words according to the order of the word numbers from small to large to obtain a first phrase, matching the first phrase with a first preset phrase in the first dictionary base, and if the first phrase is successfully matched with the first preset phrase, incorporating the first phrase into the user preference feature.
Optionally, after the matching the first phrase with a first preset phrase in the first dictionary base, the identifying unit 502 is specifically configured to:
if the first phrase is a part of the first preset phrase, adding at least one single word behind the first phrase to form a new first phrase;
and matching the new first phrase with the first preset phrase, and if the new first phrase is successfully matched with the first preset phrase, incorporating the new first phrase into the user preference feature.
Optionally, as shown in fig. 5B, fig. 5B is a modified device of the intelligent recommendation device based on internet of vehicles described in fig. 5A, and compared with fig. 5A, the modified device may further include: a processing unit 504, wherein, before the identifying the user preference feature in the behavior data according to the word segmentation algorithm, the processing unit 504 is specifically configured to:
filtering the behavior data to obtain filtered behavior data;
cleaning the filtered behavior data to obtain cleaned behavior data;
classifying the cleaned behavior data to obtain classified behavior data; and storing the classified behavior data into a database.
Optionally, in the aspect of filtering the behavior data to obtain filtered behavior data, the processing unit 504 is specifically configured to:
constructing a data evaluation function;
evaluating the behavior data according to the data evaluation function to obtain a data evaluation value;
and filtering the behavior data with the corresponding data evaluation value lower than a preset value in the behavior data.
Optionally, in the aspect of cleaning the behavior data to obtain cleaned behavior data, the processing unit 504 is specifically configured to:
word segmentation is carried out on the behavior data to obtain a plurality of second phrase groups;
constructing a second dictionary database;
and sequentially matching the plurality of second phrases with second preset phrases in the second dictionary database, and deleting the second phrases repeatedly appearing in the behavior data if the second phrases are successfully matched with the second preset phrases.
Optionally, in the aspect of sequentially matching the plurality of second phrases with a second preset phrase in the second dictionary database, the processing unit 504 is specifically configured to:
matching the words at two ends of the second phrase with the words at two ends of the second preset phrase; if the matching is successful, the remaining single words in the second phrase and the second preset phrase are matched according to the sequence from two ends to the middle until the second phrase and all the single words in the second preset phrase are successfully matched, and the second phrase and the second preset phrase are successfully matched.
It can be seen that, in the embodiment of the present application, behavior data of a user is obtained; identifying user preference characteristics in the behavior data according to a word segmentation algorithm; the service of the Internet of vehicles is recommended according to the user preference characteristics, so that the user preference characteristics in the implicit behavior data can be identified according to the word segmentation algorithm, the user preference characteristics can be better identified, and the service recommendation efficiency of the Internet of vehicles is improved.
The embodiment of the application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program makes a computer execute part or all of the steps of any intelligent recommendation method based on internet of vehicles as described in the embodiment of the method.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the intelligent internet of vehicles-based recommendation methods described in the method embodiments above.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units described above may be implemented either in hardware or in software program modules.
The integrated units, if implemented in the form of software program modules, may be stored in a computer-readable memory for sale or use as a stand-alone product. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory includes: a U-disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-only memory, random access memory, magnetic or optical disk, etc.
The foregoing has outlined rather broadly the more detailed description of embodiments of the present application, wherein specific examples are provided herein to illustrate the principles and embodiments of the present application, the above examples being provided solely to assist in the understanding of the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (5)
1. An intelligent recommendation method based on the internet of vehicles is characterized by comprising the following steps:
acquiring behavior data of a user;
constructing a data evaluation function;
analyzing the behavior data to obtain at least one data evaluation index parameter, wherein the data evaluation index parameter comprises at least one of a data real-time performance level, a data timeliness level and a correlation degree of the behavior data and preference characteristics;
evaluating the behavior data according to the data evaluation function and the data evaluation index parameter to obtain a data evaluation value;
filtering the behavior data with the corresponding data evaluation value lower than a preset value in the behavior data;
cleaning the filtered behavior data to obtain cleaned behavior data;
classifying the cleaned behavior data to obtain classified behavior data; storing the classified behavior data into a database; constructing a first dictionary database;
word segmentation is carried out on the behavior data to obtain a single character set comprising a plurality of single characters;
combining the words according to the order of the word numbers from small to large to obtain a first phrase, matching the first phrase with a first preset phrase in the first dictionary base, and if the first phrase is successfully matched with the first preset phrase, incorporating the first phrase into the user preference feature;
if the first phrase is a part of the first preset phrase, adding at least one single word behind the first phrase to form a new first phrase;
matching the new first phrase with the first preset phrase, and if the new first phrase is successfully matched with the first preset phrase, incorporating the new first phrase into the user preference feature;
recommending the service of the Internet of vehicles according to the user preference characteristics;
the step of cleaning the filtered behavior data, wherein the step of obtaining the cleaned behavior data comprises the following steps:
word segmentation is carried out on the behavior data to obtain a plurality of second phrase groups;
constructing a second dictionary database, wherein the second dictionary database comprises a plurality of second preset phrase groups which do not reflect the preference characteristics of the user and have the occurrence frequency larger than a preset frequency threshold value;
and sequentially matching the plurality of second phrases with the second preset phrases in the second dictionary database, and deleting the second phrases repeatedly appearing in the behavior data if the second phrases are successfully matched with the second preset phrases.
2. The method of claim 1, wherein sequentially matching the plurality of second phrases with a second preset phrase in the second dictionary database comprises:
matching the words at two ends of the second phrase with the words at two ends of the second preset phrase; if the matching is successful, the remaining single words in the second phrase and the second preset phrase are matched according to the sequence from two ends to the middle until the second phrase and all the single words in the second preset phrase are successfully matched, and the second phrase and the second preset phrase are successfully matched.
3. An intelligent recommendation device based on internet of vehicles, characterized in that the device comprises:
the acquisition unit is used for acquiring behavior data of the user;
the processing unit is used for constructing a data evaluation function; the data evaluation index parameter comprises at least one of data real-time performance level, data timeliness level and association degree of behavior data and preference characteristics; the data evaluation function is used for evaluating the behavior data according to the data evaluation function and the data evaluation index parameter to obtain a data evaluation value; the behavior data are used for filtering the behavior data with the corresponding data evaluation value lower than a preset value; cleaning the filtered behavior data to obtain cleaned behavior data; the method comprises the steps of classifying the cleaned behavior data to obtain classified behavior data; storing the classified behavior data into a database;
the recognition unit is used for constructing a first dictionary base; the method comprises the steps of performing word segmentation on behavior data to obtain a single character set comprising a plurality of single characters; the method comprises the steps of combining the words according to the sequence from small number to large number of the words to obtain a first phrase, matching the first phrase with a first preset phrase in a first dictionary base, and if the first phrase is successfully matched with the first preset phrase, incorporating the first phrase into the user preference feature; if the first phrase is a part of the first preset phrase, adding at least one single word behind the first phrase to form a new first phrase; and the method is used for matching the new first phrase with the first preset phrase, and if the new first phrase is successfully matched with the first preset phrase, the new first phrase is included in the user preference characteristic;
the recommending unit is used for recommending the service of the Internet of vehicles according to the user preference characteristics;
the processing unit is specifically configured to segment the behavior data to obtain a plurality of second phrases; the method comprises the steps of constructing a second dictionary database, wherein the second dictionary database comprises a plurality of second preset phrase which does not reflect the preference characteristics of a user and has the occurrence frequency larger than a preset frequency threshold value; and the second word groups are used for sequentially matching the plurality of second word groups with the second preset word groups in the second dictionary database, and if the second word groups are successfully matched with the second preset word groups, the repeated second word groups in the behavior data are deleted.
4. A server comprising a processor, a memory for storing one or more programs and configured to be executed by the processor, the program comprising instructions for performing the steps in the method of any of claims 1-2, and a communication interface.
5. A computer readable storage medium for storing a computer program for execution by a processor to implement the method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010759544.1A CN111951070B (en) | 2020-07-31 | 2020-07-31 | Intelligent recommendation method, device, server and storage medium based on Internet of Vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010759544.1A CN111951070B (en) | 2020-07-31 | 2020-07-31 | Intelligent recommendation method, device, server and storage medium based on Internet of Vehicles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111951070A CN111951070A (en) | 2020-11-17 |
| CN111951070B true CN111951070B (en) | 2023-12-22 |
Family
ID=73339843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010759544.1A Active CN111951070B (en) | 2020-07-31 | 2020-07-31 | Intelligent recommendation method, device, server and storage medium based on Internet of Vehicles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111951070B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112989194B (en) * | 2021-03-18 | 2022-11-29 | 南京邮电大学 | Recommendation method and system integrating user request and service preference of Internet of vehicles |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999534A (en) * | 2011-09-19 | 2013-03-27 | 北京金和软件股份有限公司 | Chinese word segmentation algorithm based on reverse maximum matching |
| CN107103066A (en) * | 2017-04-18 | 2017-08-29 | 北京思特奇信息技术股份有限公司 | The search method and device of a kind of user preference |
| CN107274257A (en) * | 2017-06-02 | 2017-10-20 | 携程计算机技术（上海）有限公司 | Method and device is recommended in a kind of hotel service |
| CN107871144A (en) * | 2017-11-24 | 2018-04-03 | 税友软件集团股份有限公司 | Invoice trade name sorting technique, system, equipment and computer-readable recording medium |
| CN109086419A (en) * | 2018-08-07 | 2018-12-25 | 广州小鹏汽车科技有限公司 | A kind of social communication method and system distributed based on scene and voice |
| CN109559208A (en) * | 2019-01-04 | 2019-04-02 | 平安科技（深圳）有限公司 | A kind of information recommendation method, server and computer-readable medium |
| CN110297968A (en) * | 2019-05-22 | 2019-10-01 | 中国平安人寿保险股份有限公司 | Product method for pushing, device, computer equipment and storage medium |
| CN110750713A (en) * | 2019-09-24 | 2020-02-04 | 中国第一汽车股份有限公司 | Vehicle-mounted service content recommendation method and device, vehicle and storage medium |
-
2020
- 2020-07-31 CN CN202010759544.1A patent/CN111951070B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999534A (en) * | 2011-09-19 | 2013-03-27 | 北京金和软件股份有限公司 | Chinese word segmentation algorithm based on reverse maximum matching |
| CN107103066A (en) * | 2017-04-18 | 2017-08-29 | 北京思特奇信息技术股份有限公司 | The search method and device of a kind of user preference |
| CN107274257A (en) * | 2017-06-02 | 2017-10-20 | 携程计算机技术（上海）有限公司 | Method and device is recommended in a kind of hotel service |
| CN107871144A (en) * | 2017-11-24 | 2018-04-03 | 税友软件集团股份有限公司 | Invoice trade name sorting technique, system, equipment and computer-readable recording medium |
| CN109086419A (en) * | 2018-08-07 | 2018-12-25 | 广州小鹏汽车科技有限公司 | A kind of social communication method and system distributed based on scene and voice |
| CN109559208A (en) * | 2019-01-04 | 2019-04-02 | 平安科技（深圳）有限公司 | A kind of information recommendation method, server and computer-readable medium |
| CN110297968A (en) * | 2019-05-22 | 2019-10-01 | 中国平安人寿保险股份有限公司 | Product method for pushing, device, computer equipment and storage medium |
| CN110750713A (en) * | 2019-09-24 | 2020-02-04 | 中国第一汽车股份有限公司 | Vehicle-mounted service content recommendation method and device, vehicle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111951070A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN109325182B (en) | Information pushing method and device based on session, computer equipment and storage medium | |
| US7849066B2 (en) | Apparatus and method for determining adequacy of information retrieving process | |
| CN110990685B (en) | Voiceprint-based voice searching method, voiceprint-based voice searching equipment, storage medium and storage device | |
| CN109033075B (en) | Intention matching method and device, storage medium and terminal equipment | |
| CN109829045A (en) | A kind of answering method and device | |
| CN108959531A (en) | Information search method, device, equipment and storage medium | |
| CN105512156B (en) | Click model generation method and device | |
| CN111078832A (en) | Auxiliary response method and system for intelligent customer service | |
| CN110457454A (en) | A kind of dialogue method, server, conversational system and storage medium | |
| CN111611358A (en) | Information interaction method and device, electronic equipment and storage medium | |
| KR101341816B1 (en) | System and method for extracting analogous queries | |
| CN111951070B (en) | Intelligent recommendation method, device, server and storage medium based on Internet of Vehicles | |
| CN112631945A (en) | Test case generation method and device and storage medium | |
| CN111813916A (en) | Intelligent question and answer method, device, computer equipment and medium | |
| CN114282119B (en) | Scientific and technological information resource retrieval method and system based on heterogeneous information network | |
| CN111353015A (en) | Crowdsourcing question recommendation method, device, equipment and storage medium | |
| CN108694171B (en) | Information pushing method and device | |
| CN112732901B (en) | Digest generation method, digest generation device, computer-readable storage medium, and electronic device | |
| CN113392289B (en) | Search recommendation method and device and electronic equipment | |
| CN112434140B (en) | Reply information processing method and system | |
| CN109739848B (en) | Data extraction method | |
| CN116415063A (en) | Cloud service recommendation method and device | |
| CN114281942A (en) | Question and answer processing method, related equipment and readable storage medium | |
| CN113704422A (en) | Text recommendation method and device, computer 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 | ||
| CB02 | Change of applicant information |
Address after: 201821 room 208, building 4, No. 1411, Yecheng Road, Jiading Industrial Zone, Jiading District, Shanghai Applicant after: Botai vehicle networking technology (Shanghai) Co.,Ltd. Address before: Room 208, building 4, 1411 Yecheng Road, Jiading Industrial Zone, Jiading District, Shanghai, 201800 Applicant before: SHANGHAI PATEO ELECTRONIC EQUIPMENT MANUFACTURING Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: Room 3701, No. 866 East Changzhi Road, Hongkou District, Shanghai, 200000 Patentee after: Botai vehicle networking technology (Shanghai) Co.,Ltd. Country or region after: China Address before: 201821 room 208, building 4, No. 1411, Yecheng Road, Jiading Industrial Zone, Jiading District, Shanghai Patentee before: Botai vehicle networking technology (Shanghai) Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |