CN117150114A - Information recommendation method, apparatus, computer device, storage medium, and program product - Google Patents
Information recommendation method, apparatus, computer device, storage medium, and program product Download PDFInfo
- Publication number
- CN117150114A CN117150114A CN202310876909.2A CN202310876909A CN117150114A CN 117150114 A CN117150114 A CN 117150114A CN 202310876909 A CN202310876909 A CN 202310876909A CN 117150114 A CN117150114 A CN 117150114A
- Authority
- CN
- China
- Prior art keywords
- information
- target user
- current query
- recommendation
- determining
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004590 computer program Methods 0.000 claims description 40
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 239000013598 vector Substances 0.000 description 20
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013515 script Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present application relates to an information recommendation method, apparatus, computer device, storage medium and program product. Relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring the current query characteristics of a current query statement input by a target user; determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information; determining second recommendation information through the chat robot model according to the current query characteristics; and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user. By adopting the method, the information recommendation effect can be improved.
Description
Technical Field
The present application relates to the field of artificial intelligence technology, and in particular, to an information recommendation method, apparatus, computer device, storage medium, and program product.
Background
With the development of the computer field, the acquisition of required information through the internet has become an important component of information acquisition. After the user inputs his own needs, the platform may provide the user with the required information in response to the user needs. For example, a financial institution develops a reservation channel platform where a user can learn the reservation knowledge desired by the user.
However, the platform can only screen out the information matched with the user from the information existing in the platform, the information fed back to the user may not be the most suitable, and the instant targeted information cannot be generated to feed back to the user. Accordingly, it is desirable to provide an information recommendation method capable of improving an information recommendation effect.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an information recommendation method, apparatus, computer device, storage medium, and program product that can improve the information recommendation effect.
In a first aspect, the present application provides an information recommendation method. The method comprises the following steps:
acquiring the current query characteristics of a current query statement input by a target user;
determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
determining second recommendation information through the chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
In one embodiment, determining information to be recommended of the target user according to the first recommendation information and the second recommendation information includes:
Determining occurrence frequency of the current query feature in the first recommendation information and the second recommendation information;
and taking the first recommendation information and/or the second recommendation information with the occurrence frequency larger than a preset threshold value as information to be recommended of the target user.
In one embodiment, obtaining the current query feature of the current query statement input by the target user includes:
acquiring a current query statement input by a target user;
based on the user representation of the target user, a current query feature of the current query statement is determined.
In one embodiment, determining the current query feature of the current query statement based on the user representation of the target user includes:
performing feature extraction operation on the current query statement to determine statement features of the current query statement;
and determining the current query characteristics of the target user according to the statement characteristics of the current query statement and the user portrait of the target user.
In one embodiment, the method further comprises:
based on a matrix decomposition algorithm, determining the user portrait of the target user according to the historical query statement, the historical feedback information and the attribute information of the target user.
In one embodiment, the historical feedback information includes historical recommendation information of the target user and feedback information of the target user for the historical recommendation information; after feeding back the information to be recommended to the target user, the method further comprises the following steps:
Acquiring current feedback information of a target user aiming at information to be recommended;
and updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
In a second aspect, the application further provides an information recommendation device. The device comprises:
the feature acquisition module is used for acquiring the current query feature of the current query statement input by the target user;
the first determining module is used for determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
the second determining module is used for determining second recommendation information through the chat robot model according to the current query characteristics;
the information feedback module is used for determining information to be recommended of the target user according to the first recommendation information and the second recommendation information and feeding the information to be recommended back to the target user.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring the current query characteristics of a current query statement input by a target user;
determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
Determining second recommendation information through the chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring the current query characteristics of a current query statement input by a target user;
determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
determining second recommendation information through the chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, performs the steps of:
acquiring the current query characteristics of a current query statement input by a target user;
Determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
determining second recommendation information through the chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
The information recommending method, the information recommending device, the computer equipment, the storage medium and the program product are used for extracting the characteristics of the current query statement input by the target user to obtain the current query characteristics of the target user, and determining the first recommending information according to the distance between the current query characteristics and the information characteristics of the local candidate information. Because the information characteristics of the local candidate information are all determined in advance, the process of determining the first recommended information is more convenient. Further, in this embodiment, the first recommendation information is not directly used as the information to be recommended of the target user, but in order to ensure the matching between the information to be recommended and the target user, the current query feature is further analyzed and processed through the chat robot model, and the second recommendation information is generated. And determining final information to be recommended according to the first recommendation information and the second recommendation information and feeding back the final information to be recommended to the target user. The whole process can enable the matching degree of the information to be recommended and the target user to be higher, so that the aim of improving the information recommendation effect is fulfilled.
Drawings
Fig. 1 is an application environment diagram of an information recommendation method provided in this embodiment;
fig. 2 is a flowchart of a first information recommendation method provided in this embodiment;
fig. 3 is a schematic flow chart of determining information to be recommended of a target user according to the present embodiment;
fig. 4 is a schematic flow chart of acquiring a current query feature according to the present embodiment;
FIG. 5 is a flowchart of a process for updating a user portrait of a target user according to the present embodiment;
fig. 6 is a flowchart of a second information recommendation method according to the present embodiment;
fig. 7 is a block diagram of a first information recommendation apparatus according to the present embodiment;
fig. 8 is a block diagram of a second information recommendation apparatus according to the present embodiment;
fig. 9 is a block diagram of a third information recommendation apparatus according to the present embodiment;
fig. 10 is a block diagram of a fourth information recommendation apparatus according to the present embodiment;
fig. 11 is a block diagram of a fifth information recommendation apparatus according to the present embodiment;
fig. 12 is an internal structure diagram of a computer device according to the present embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The information recommendation method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in FIG. 1. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing relevant data for information recommendation. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an information recommendation method.
In one embodiment, as shown in fig. 2, an information recommendation method is provided, and the method is applied to the computer device in fig. 1 for illustration, and includes the following steps:
S201, acquiring the current query characteristics of the current query statement input by the target user.
The target user may be a user who has information recommendation requirements. The current query statement may be a statement entered by the target user on the information recommendation platform that describes the query requirements of the target user. The current query feature may be a feature word representing the current query statement, or may be a feature vector generated based on the feature word.
Optionally, in this embodiment, when the target user inputs the current query sentence on the information recommendation platform (for example, a learning-reserved information consultation platform developed by a financial institution), the computer device may acquire the current query sentence input by the target user, extract a keyword from the current query sentence, and use the keyword as the current query feature of the current query sentence. Another implementation manner may be that after the computer device obtains the current query sentence input by the target user and extracts the keyword, a vector value is given to the keyword in the current query sentence according to the predetermined keyword feature vector, and the current query feature of the target user is obtained after the fusion processing of the vector values.
The manner of performing the fusion processing on each vector value may include: the vectors are subjected to a summation process, and the vectors are subjected to a weighted summation process or the like, which is not limited thereto.
For example, if the content of the current query sentence input by the target user is "i want to go to the uk to read the high school", the academic fee budgets 10000 yuan ", after the computer device obtains the current query sentence, the computer device extracts the keywords of" uk "," high school "," academic fee "and" 10000 yuan ", searches the vectors of the keywords in the predetermined keyword vector library, and performs weighted addition processing on each vector to obtain the current query feature of the target user.
If the keyword extracted from the current query sentence does not exist in the keyword vector library, the feature vector corresponding to the word close to the keyword is used as the vector of the keyword. The weights of the keywords may be preset, for example, the weights of the keywords of a category are the same, and for example, the weights of the keywords of a category having the greatest influence on the query purpose of the current query sentence are the highest.
S202, determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information.
The local candidate information may be information existing in the information recommendation platform, and the candidate information may be various types of information, for example, information, articles, books, and the like. The information feature of the local candidate information is feature information for representing the local candidate information, and may be a feature vector or a keyword contained in the local candidate information. The first recommendation information may be information that matches the current query feature, as determined from the local information.
Optionally, in this embodiment, the current query feature and the information features of all the local candidate information may be input into a pre-trained information recommendation model, where the information recommendation model analyzes and processes the received information, and outputs the first recommendation information. Another way to determine the first recommended information may be that after determining the current query feature (feature vector), the computer device determines information features (feature vectors) of each local candidate information, calculates a distance between the current query feature and the information feature of each local candidate information, and uses local candidate information corresponding to the information feature of the preset number of local candidate information closest to the current query feature as the first recommended information.
S203, determining second recommendation information through the chat robot model according to the current query characteristics.
The chat robot model can be a model which is trained in advance, can process query sentences input by a user and output information required by the user. Illustratively, chat robots ChatGPT (Chat Generative Pre-trained Transformer, chatGPT) may be provided. ChatGPT is a natural language processing tool driven by artificial intelligence technology, which can perform dialogue by understanding and learning human language, can interact according to the chat context, really chat and communicate like human, and even can complete the tasks of writing mails, video scripts, texts, translation, codes, writing papers and the like. The second recommendation information may be information matching the current query feature obtained after the chat robot model analyzes and processes the current query feature.
Specifically, in this embodiment, after the chat robot model receives the current query feature corresponding to the target user, it processes the current query feature and obtains the information matched with the current query feature.
It should be noted that the second recommended information is different from the first recommended information in that the first recommended information is selected from the local information; the second recommendation information is information generated by the chat robot model according to the current query characteristics. Thus, the second recommendation information may be more generic, more variable in content, and more matched with the current query characteristics.
S204, determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
The information to be recommended is information fed back to the target user.
Specifically, in this embodiment, the first recommendation information and the second recommendation information may be both fed back to the target user as the information to be recommended. In another implementation manner, part of the content with the highest correlation with the current query feature is screened out from the first recommendation information and the second recommendation information, the part of the content in the first recommendation information and the part of the content in the second recommendation information are combined, and the combined content is used as information to be recommended and fed back to the target user. In another implementation manner, if the first recommendation information can be determined according to the current query characteristics and the information characteristics of the local candidate information, the first recommendation information is fed back to the target user as the information to be recommended. And determining second recommendation information according to the current query characteristics and the chat robot model when the first recommendation information is not determined according to the current query characteristics and the information characteristics of the local candidate information, and feeding the second recommendation information back to the target user as information to be recommended.
Alternatively, in this embodiment, the information to be recommended may be fed back through a short message, a fifth generation mobile communication technology message (5th Generation Mobile Communication Technology,5G), or the like. In addition, in this embodiment, the information to be recommended may be fed back to the target user in a voice broadcast manner.
In the information recommendation method, feature extraction is performed on the current query statement input by the target user to obtain the current query feature of the target user, and the first recommendation information is determined according to the distance between the current query feature and the information feature of the local candidate information. Because the information characteristics of the local candidate information are all determined in advance, the process of determining the first recommended information is more convenient. Further, in this embodiment, the first recommendation information is not directly used as the information to be recommended of the target user, but in order to ensure the matching between the information to be recommended and the target user, the current query feature is further analyzed and processed through the chat robot model, and the second recommendation information is generated. And determining final information to be recommended according to the first recommendation information and the second recommendation information and feeding back the final information to be recommended to the target user. The whole process can enable the matching degree of the information to be recommended and the target user to be higher, so that the aim of improving the information recommendation effect is fulfilled.
Further, in order to make the matching degree between the determined information to be recommended and the target user higher, in one embodiment, as shown in fig. 3, a specific manner of determining the information to be recommended of the target user is provided, which includes the following steps:
s301, determining occurrence frequency of the current query feature in the first recommendation information and the second recommendation information.
Specifically, in this embodiment, the number of occurrences of the current query feature in the first recommendation information and the second recommendation information may be queried and determined, respectively. For example, each feature word in the current query feature may be determined, the occurrence number of each feature word is queried in the first recommendation information, and the sum of the occurrence numbers of each feature word is used as the occurrence frequency of the current query feature in the first recommendation information.
S302, the first recommendation information and/or the second recommendation information with the occurrence frequency larger than a preset threshold value are used as information to be recommended of the target user.
The preset threshold may be used to determine whether the occurrence frequency of the current query feature in the first recommendation information or the second recommendation information reaches the information to be recommended.
Optionally, in this embodiment, if the occurrence frequency of the current query feature in the first recommendation information is greater than a preset threshold, the first recommendation information is used as the information to be recommended. And if the occurrence frequency of the current query feature in the second recommendation information is greater than a preset threshold value, the second recommendation information is used as the information to be recommended. Of course, if the occurrence frequency of the current query feature in the first recommendation information and the second recommendation information is greater than the preset threshold, the first recommendation information and the second recommendation information are both used as the information to be recommended.
Further, in one embodiment, in order to make the current query feature more accurate and better characterize the query requirement of the target user, in one embodiment, as shown in fig. 4, the manner of obtaining the current query feature of the current query statement input by the target user specifically includes the following steps:
s401, acquiring a current query sentence input by a target user.
Specifically, in this embodiment, when the target user inputs the current query sentence on the information recommendation platform (for example, a learning-reserved information consultation platform developed by a financial institution), the computer device may acquire the current query sentence input by the target user.
S402, determining the current query feature of the current query statement based on the user portrait of the target user.
The user portrait of the target user can be information which is determined in advance and used for representing the user characteristics, the query habits, the query preferences and the like of the target user.
Optionally, in this embodiment, the user portrait of the target user may be determined based on the matrix decomposition algorithm according to the historical query statement, the historical feedback information and the attribute information of the target user. The historical query statement may be a query statement input by a target user during a query operation on the information recommendation platform in a historical time. The historical feedback information may be recommendation information output by the computer device in response to the historical query statement. The attribute information may be basic information of the target user, such as gender, age, etc.
In this embodiment, the user image of the target user may be obtained by inputting the historical query statement, the historical feedback information and the attribute information of the target user into a pre-trained matrix-based decomposition model, and analyzing and processing the received data by the matrix decomposition model to output the user image of the target user. For example, in this embodiment, the manner of determining the user portrait of the target user based on the matrix decomposition algorithm may be to construct a scoring matrix according to the historical query statement, the historical feedback information and the attribute information of the target user (the scoring matrix records the occurrence times of the target user in each query operation and each query keyword). And decomposing the scoring matrix into a form of two matrix products according to the category of each query keyword and the occurrence frequency of each category. And then calculating the inner products of the two matrixes, sorting the inner products from large to small, and taking out the preset keywords with the front sorting and the corresponding occurrence times as the user portrait of the target user.
The user portrait of the target user is determined in the mode, and a basis is provided for determining the current query characteristics of the current query statement.
Optionally, in this embodiment, the current query statement and the user portrait of the target user may be input into a predetermined current query feature determination model, and the model processes the received data to obtain the current query feature of the current query statement. Another implementation manner may be that feature extraction operation is performed on the current query statement to determine statement features of the current query statement; and determining the current query characteristics of the target user according to the statement characteristics of the current query statement and the user portrait of the target user. Where the statement feature may be a keyword vector in the current query statement. Specifically, in this embodiment, each keyword vector in the current query sentence may be obtained, then the word vector of the keyword in the user image of the target user may be obtained, and the two types of keyword vectors may be summed to obtain the current query feature of the target user.
In the above embodiment, the current query feature of the target user is determined according to the statement feature of the current query statement and the user portrait of the target user, so that the determined current query feature can represent the requirement of the target user.
In addition, to enable the user profile of the target user to accurately characterize the query needs of the target user, in one embodiment, the historical feedback information includes historical recommendation information of the target user, and feedback information of the target user for the historical recommendation information. That is, the history feedback information includes history recommendation information recommended by the computer device for the target user when the history inquiry operation is performed, and an operation of the target user on the history recommendation information after receiving the history recommendation information. The operation of the target user on the historical recommended information comprises operations such as checking, downloading, collecting and the like, and information such as checking times, downloading records, collecting records and the like of the target user on the historical recommended information can be used as feedback information.
Further, in order to ensure that the user image of the target user can be updated in real time, and ensure that the user image used when determining the current query feature is more accurate when the target user performs the information query operation next time, in one embodiment, after feeding back the information to be recommended to the target user, as shown in fig. 5, the method further includes:
S501, current feedback information of a target user aiming at information to be recommended is obtained.
The current feedback information comprises information to be recommended fed back by the computer equipment for the target user in response to the current query statement, and processing records of the information to be recommended after the target user receives the information to be recommended. The processing mode of the information to be recommended is the same as the processing mode of the history recommended information, and is not described in detail herein.
Optionally, the method for obtaining the current feedback information of the target user for the information to be recommended may be to obtain the information to be recommended, and feed back the information to be recommended through the corresponding operation record. For example, an operation tracking program may be set on a page of the information to be recommended, and the operation tracking program is used for recording and feeding back an operation record of the information to be recommended to the target user to the computer device. And taking the information to be recommended and the operation record as current feedback information.
S502, updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
Specifically, in this embodiment, the current query statement, the information to be recommended, and the current feedback information may be respectively added to corresponding positions in the user portrait of the target user, so that the user portrait of the target user is synchronized with the current query operation, thereby completing the update operation of the user portrait of the target user.
In the embodiment, the user portrait of the target user is updated in real time according to the current query statement, the information to be recommended and the current feedback information, and the accuracy of the query feature is guaranteed on the basis of guaranteeing the real-time accuracy of the user portrait.
For the convenience of understanding of those skilled in the art, the above information recommendation method will be described in detail, and as shown in fig. 6, the method may include:
s601, acquiring a current query sentence input by a target user.
S602, performing feature extraction operation on the current query sentence, and determining the sentence features of the current query sentence.
S603, determining the user portrait of the target user according to the historical query statement, the historical feedback information and the attribute information of the target user based on a matrix decomposition algorithm.
S604, determining the current query characteristics of the target user according to the statement characteristics of the current query statement and the user portrait of the target user.
S605, determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information.
S606, determining second recommendation information through the chat robot model according to the current query characteristics.
S607, determining the occurrence frequency of the current query feature in the first recommendation information and the second recommendation information.
And S608, taking the first recommendation information and/or the second recommendation information with the occurrence frequency larger than a preset threshold value as information to be recommended of the target user. And feeding back the information to be recommended to the target user.
S609, current feedback information of the target user aiming at the information to be recommended is obtained.
And S610, updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an information recommendation device for realizing the above related information recommendation method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of one or more information recommendation devices provided below may refer to the limitation of the information recommendation method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 7, there is provided an information recommendation apparatus 1 including: a feature acquisition module 10, a first determination module 11, a second determination module 12, and an information feedback module 13, wherein:
the feature acquisition module 10 is configured to acquire a current query feature of a current query sentence input by a target user.
The first determining module 11 is configured to determine first recommendation information according to the current query feature and the information feature of the local candidate information.
A second determining module 12, configured to determine second recommendation information according to the current query feature through the chat robot model.
The information feedback module 13 is configured to determine information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feedback the information to be recommended to the target user.
In one embodiment, as shown in fig. 8, the information feedback module 13 includes a frequency determining unit 130 and an information determining unit 131. Wherein:
the frequency determining unit 130 is configured to determine a frequency of occurrence of the current query feature in the first recommendation information and the second recommendation information.
The information determining unit 131 is configured to take the first recommendation information and/or the second recommendation information, where the occurrence frequency of the first recommendation information and/or the second recommendation information is greater than a preset threshold, as information to be recommended of the target user.
In one embodiment, as shown in fig. 9, the feature acquisition module 10 includes a sentence acquisition unit 100 and a feature acquisition unit 101. Wherein:
the sentence acquisition unit 100 is configured to acquire a current query sentence input by a target user.
A feature acquisition unit 101 for determining a current query feature of a current query sentence based on a user portrait of a target user.
In one embodiment, the feature acquisition unit 101 includes a first determination subunit and a second determination subunit. Wherein:
and the first determining subunit is used for carrying out feature extraction operation on the current query statement and determining statement features of the current query statement.
The second determining subunit determines the current query feature of the target user according to the statement feature of the current query statement and the user portrait of the target user.
In one embodiment, as shown in fig. 10, the information recommendation apparatus 1 further includes a user portrayal determination module 14 for determining a user portrayal of the target user based on the historical query sentence, the historical feedback information and the attribute information of the target user based on the matrix factorization algorithm.
In one embodiment, the history feedback information includes history recommendation information of the target user, and as shown in fig. 11, the information recommendation apparatus 1 further includes a user portrait update module 15. Comprises a feedback information acquisition unit 150 and a user portrait update module 151. Wherein:
and the feedback information obtaining unit 150 is configured to obtain current feedback information of the target user for the information to be recommended.
The user portrait updating unit 151 is used for updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
The respective modules in the information recommendation apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 12. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement an information recommendation method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 12 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring the current query characteristics of a current query statement input by a target user;
determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
determining second recommendation information through the chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining occurrence frequency of the current query feature in the first recommendation information and the second recommendation information;
And taking the first recommendation information and/or the second recommendation information with the occurrence frequency larger than a preset threshold value as information to be recommended of the target user.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring a current query statement input by a target user;
based on the user representation of the target user, a current query feature of the current query statement is determined.
In one embodiment, the processor when executing the computer program further performs the steps of:
performing feature extraction operation on the current query statement to determine statement features of the current query statement;
and determining the current query characteristics of the target user according to the statement characteristics of the current query statement and the user portrait of the target user.
In one embodiment, the processor when executing the computer program further performs the steps of:
based on a matrix decomposition algorithm, determining the user portrait of the target user according to the historical query statement, the historical feedback information and the attribute information of the target user.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring current feedback information of a target user aiming at information to be recommended;
and updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring the current query characteristics of a current query statement input by a target user;
determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
determining second recommendation information through the chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining occurrence frequency of the current query feature in the first recommendation information and the second recommendation information;
and taking the first recommendation information and/or the second recommendation information with the occurrence frequency larger than a preset threshold value as information to be recommended of the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a current query statement input by a target user;
based on the user representation of the target user, a current query feature of the current query statement is determined.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing feature extraction operation on the current query statement to determine statement features of the current query statement;
and determining the current query characteristics of the target user according to the statement characteristics of the current query statement and the user portrait of the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
based on a matrix decomposition algorithm, determining the user portrait of the target user according to the historical query statement, the historical feedback information and the attribute information of the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring current feedback information of a target user aiming at information to be recommended;
and updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
acquiring the current query characteristics of a current query statement input by a target user;
determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
Determining second recommendation information through the chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining occurrence frequency of the current query feature in the first recommendation information and the second recommendation information;
and taking the first recommendation information and/or the second recommendation information with the occurrence frequency larger than a preset threshold value as information to be recommended of the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring a current query statement input by a target user;
based on the user representation of the target user, a current query feature of the current query statement is determined.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing feature extraction operation on the current query statement to determine statement features of the current query statement;
and determining the current query characteristics of the target user according to the statement characteristics of the current query statement and the user portrait of the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Based on a matrix decomposition algorithm, determining the user portrait of the target user according to the historical query statement, the historical feedback information and the attribute information of the target user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring current feedback information of a target user aiming at information to be recommended;
and updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
It should be noted that, the user information (including but not limited to user attribute information, historical feedback information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (10)
1. An information recommendation method, the method comprising:
acquiring the current query characteristics of a current query statement input by a target user;
determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
determining second recommendation information through a chat robot model according to the current query characteristics;
and determining information to be recommended of the target user according to the first recommendation information and the second recommendation information, and feeding back the information to be recommended to the target user.
2. The method of claim 1, wherein the determining the information to be recommended for the target user based on the first recommendation information and the second recommendation information comprises:
determining occurrence frequency of the current query feature in the first recommendation information and the second recommendation information;
and taking the first recommendation information and/or the second recommendation information with the occurrence frequency larger than a preset threshold value as information to be recommended of the target user.
3. The method of claim 1, wherein the obtaining the current query feature of the current query statement input by the target user comprises:
acquiring a current query statement input by a target user;
and determining the current query characteristics of the current query statement based on the user portrait of the target user.
4. The method of claim 3, wherein the determining the current query feature of the current query statement based on the user representation of the target user comprises:
performing feature extraction operation on the current query statement to determine statement features of the current query statement;
and determining the current query characteristics of the target user according to the statement characteristics of the current query statement and the user portrait of the target user.
5. The method according to claim 3 or 4, characterized in that the method further comprises:
and determining the user portrait of the target user according to the historical query statement, the historical feedback information and the attribute information of the target user based on a matrix decomposition algorithm.
6. The method of claim 5, wherein the historical feedback information includes historical recommendation information for the target user and feedback information for the target user for the historical recommendation information; after the information to be recommended is fed back to the target user, the method further comprises the following steps:
acquiring current feedback information of the target user aiming at the information to be recommended;
and updating the user portrait of the target user according to the current query statement, the information to be recommended and the current feedback information.
7. An information recommendation device, characterized in that the device comprises:
the feature acquisition module is used for acquiring the current query feature of the current query statement input by the target user;
the first determining module is used for determining first recommendation information according to the current query characteristics and the information characteristics of the local candidate information;
the second determining module is used for determining second recommendation information through the chat robot model according to the current query characteristics;
And the information feedback module is used for determining information to be recommended of the target user according to the first recommendation information and the second recommendation information and feeding the information to be recommended back to the target user.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310876909.2A CN117150114A (en) | 2023-07-17 | 2023-07-17 | Information recommendation method, apparatus, computer device, storage medium, and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310876909.2A CN117150114A (en) | 2023-07-17 | 2023-07-17 | Information recommendation method, apparatus, computer device, storage medium, and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117150114A true CN117150114A (en) | 2023-12-01 |
Family
ID=88905060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310876909.2A Pending CN117150114A (en) | 2023-07-17 | 2023-07-17 | Information recommendation method, apparatus, computer device, storage medium, and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117150114A (en) |
-
2023
- 2023-07-17 CN CN202310876909.2A patent/CN117150114A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046304B (en) | User recommendation method and device | |
| CN109376222B (en) | Question-answer matching degree calculation method, question-answer automatic matching method and device | |
| CN111444320A (en) | Text retrieval method and device, computer equipment and storage medium | |
| CN111079056A (en) | Method, device, computer equipment and storage medium for extracting user portrait | |
| US10685012B2 (en) | Generating feature embeddings from a co-occurrence matrix | |
| CN111522889B (en) | User interest tag expansion method and device, electronic equipment and storage medium | |
| CN113343091A (en) | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program | |
| CN111291563B (en) | Word vector alignment method and word vector alignment model training method | |
| CN112131261A (en) | Community query method and device based on community network and computer equipment | |
| CN110377618B (en) | Method, device, computer equipment and storage medium for analyzing decision result | |
| CN113641835B (en) | Multimedia resource recommendation method and device, electronic equipment and medium | |
| CN114330704A (en) | Statement generation model updating method and device, computer equipment and storage medium | |
| CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
| CN112445899A (en) | Neural network-based attribute matching method in knowledge base question answering | |
| CN117150114A (en) | Information recommendation method, apparatus, computer device, storage medium, and program product | |
| CN115186173A (en) | Multimedia resource pushing and intelligent agent network generating method and device | |
| CN112148855A (en) | Intelligent customer service problem retrieval method, terminal and storage medium | |
| CN115455306B (en) | Push model training method, information push device and storage medium | |
| CN117473149A (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN113722608B (en) | Collaborative filtering method and device based on association relation learning under guidance of iterative auxiliary information | |
| CN117093874A (en) | Text generation method, apparatus, computer device, medium, and program product | |
| EP4207035A1 (en) | Sorting method, apparatus and device, and computer storage medium | |
| CN114118059A (en) | Sample statement processing method and device, computer equipment and storage medium | |
| CN117435700A (en) | Data searching method, device, computer equipment and storage medium | |
| CN115422214A (en) | Corpus updating method, apparatus, computer device, storage medium and product |
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 |