CN111966784A - Information recommendation method, electronic device and storage medium - Google Patents
Information recommendation method, electronic device and storage medium Download PDFInfo
- Publication number
- CN111966784A CN111966784A CN202010676201.9A CN202010676201A CN111966784A CN 111966784 A CN111966784 A CN 111966784A CN 202010676201 A CN202010676201 A CN 202010676201A CN 111966784 A CN111966784 A CN 111966784A
- Authority
- CN
- China
- Prior art keywords
- information
- semantic vector
- text
- information text
- recommendation method
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Abstract
The invention discloses an information recommendation method, a computing device and a storage medium, which comprises the steps of obtaining a first information text, and performing keyword matching on the first information text to obtain matching data; obtaining a first semantic vector from the matching data through a BERT model; acquiring a second information text, and obtaining a second semantic vector from the second information text through a BERT model; comparing the first semantic vector with the second semantic vector according to the similarity of the first semantic vector and the second semantic vector to obtain comparison data; and distributing the corresponding first information text to the terminal matched with the first information text according to the comparison data. By applying the method and the device, the efficiency of information recommendation can be effectively improved.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to an information recommendation method, an electronic device, and a storage medium.
Background
With the development of information technology, information of news, self-media and forums on the network is in an explosion trend, the current public opinion service mainly takes keyword matching and manual processing as main services, and has the defects of low processing efficiency, low processing speed, time lag of discovery, time blind zone and the like, so that the public opinion service cannot adapt to the development requirement of the current public opinion processing. The natural language expression has diversity, the same meaning has multiple expressions, and the keywords can only be matched with a fixed mode and can not capture the semantics. The keyword matching has the characteristics of large scale, high cost and difficult maintenance, and the manual processing efficiency is low, so that the keyword is issued through a website, and then the client can look up the keyword to the website with time delay, thereby increasing the difficulty of receiving public opinion early warning by the client.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides an information recommendation method, a computing device and a storage medium, which can effectively improve the information recommendation efficiency.
In a first aspect of the embodiments of the present invention, an information recommendation method is provided, including the following steps:
acquiring a first information text, and performing keyword matching on the first information text to obtain matching data;
obtaining a first semantic vector from the matching data through a BERT model;
acquiring a second information text, and obtaining a second semantic vector from the second information text through the BERT model;
comparing the similarity of the first semantic vector and the second semantic vector to obtain comparison data;
and distributing the corresponding first information text to a terminal matched with the first information text according to the comparison data.
The information recommendation method provided by the embodiment of the invention at least has the following beneficial effects: acquiring a first information text, and performing keyword matching on the first information text to obtain matching data. Then, obtaining a first semantic vector by the matching data through a BERT model; acquiring a second information text, obtaining a second semantic vector from the second information text through the BERT model, comparing the similarity of the first semantic vector and the second semantic vector to obtain comparison data, and distributing the corresponding first information text to a terminal matched with the first information text according to the comparison data. In summary, in the embodiments of the present invention, a first semantic vector and a second semantic vector are obtained through a BERT model, and the first semantic vector and the second semantic vector are compared with each other in terms of similarity, so as to finally obtain an information text meeting the user requirement, and the information text is pushed to a user terminal. Compared with the current information text distribution mode needing manual participation, the information recommendation and distribution method and the information recommendation and distribution device can effectively improve the information recommendation and distribution efficiency.
According to some embodiments of the invention, the obtaining the second information text comprises:
carrying out similarity duplication elimination on the first information text to obtain duplication elimination text information;
and carrying out time deduplication on the deduplication text information to obtain the second information text.
According to some embodiments of the present invention, the performing similarity deduplication on the first information text to obtain deduplication text information includes the following steps:
acquiring all historical semantic vectors in a preset time period;
comparing the cosine similarity of the first semantic vector with the historical semantic vector to obtain a comparison difference value of the values of the first semantic vector and the historical semantic vector;
and carrying out duplication elimination processing on the first semantic vector with the comparison difference value larger than a first preset value to obtain duplication elimination text information.
According to some embodiments of the invention, said time-deduplicating the deduplicating text information to obtain the second information text comprises:
extracting time data of the first information text;
comparing the time data with the current time to obtain a time difference value;
and carrying out deduplication processing on the first information text with the time difference value exceeding a second preset value.
According to some embodiments of the present invention, the obtaining a first information text and performing keyword matching on the first information text to obtain matching data includes:
acquiring the first information text;
performing word segmentation operation on the acquired first information text to obtain a word list;
and querying the word list according to the keyword condition to obtain the matching data.
According to some embodiments of the invention, the passing the matching data through a BERT model to obtain a first semantic vector comprises:
inputting the matching data into the BERT model;
and receiving a first semantic vector which is output by the BERT model and corresponds to the matching data.
According to some embodiments of the invention, the comparing according to the similarity of the first semantic vector and the second semantic vector to obtain comparison data comprises:
acquiring all historical semantic vectors, calculating the average value of all the historical semantic vectors, and taking the average value as the second semantic vector;
and respectively analyzing the cosine similarity of the first semantic vector and the second semantic vector to obtain the cosine similarity of the first semantic vector and the second semantic vector.
According to some embodiments of the present invention, the comparing according to the similarity of the first semantic vector and the second semantic vector to obtain comparison data further comprises:
and comparing the cosine similarity value with a preset cosine similarity threshold value to obtain comparison data of the magnitude of the cosine similarity value and the preset cosine similarity threshold value.
In a second aspect of the embodiments of the present invention, there is provided an electronic device, including:
at least one memory;
at least one processor;
at least one program;
the programs are stored in the memory, and the processor executes the at least one program to implement the above-described information recommendation method.
In a third aspect of the embodiments of the present invention, a computer-readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the information recommendation method described above.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of an information recommendation method according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a particular embodiment of the information recommendation method shown in FIG. 1;
FIG. 3 is a flowchart of a keyword matching embodiment of the present invention;
FIG. 4 is a flowchart of a specific embodiment of building semantic vectors by the BERT model according to an embodiment of the present invention;
FIG. 5 is a flow chart of a similarity deduplication embodiment of the present invention;
FIG. 6 is a flow chart of a temporal deduplication embodiment of the present invention;
fig. 7 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
At present, information data on a network is more and more, the updating speed is faster and more, different users can be interested in different information, or need to acquire related information in time. The related technology mainly screens the information on the network manually, screens out the information meeting the requirements of the user, and recommends the information to the matched client. The above mode is inefficient and cannot adapt to a network environment where information is expanded at present.
Referring to fig. 7, the components of the electronic device 1000 include, but are not limited to, a memory 1100 and a processor 1200. The processor 1200 is coupled to the memory 1100 via the bus 1300, and the database 1600 is used to store data.
The electronic device 1000 also includes an access device 1400, the access device 1400 enabling the electronic device 1000 to communicate via one or more networks 1500. Examples of such networks include the public switched telephone network (PST N), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 1400 may include one or more of any type of network interface, e.g., a Network Interface Card (NIC), wired or wireless, such as an IEEE802.11 wireless local area network (wlan) wireless interface, a global microwave interconnect access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In some embodiments of the invention, the above-mentioned components of the electronic device 1000 and other components not shown in fig. 7 may be connected to each other, for example, by a bus. It should be understood that the block diagram of the electronic device shown in fig. 7 is for exemplary purposes only and is not intended to limit the scope of the present invention. Those skilled in the art may add or replace other components as desired. The computing device may be any type of mobile computing device, such as a smartphone, a smart tablet, and the like.
Among other things, the processor 1200 may perform the steps in the information recommendation method shown in fig. 1. Fig. 1 shows a flowchart of an information recommendation method according to an embodiment of the present invention, and with reference to fig. 1 and 2, includes steps S100 to S500.
Step S100: and acquiring a first information text, and performing keyword matching on the first information text to obtain matching data.
Referring to fig. 3, specifically, a word segmentation operation is performed on the acquired first information text to obtain a word list, and then the word list is queried according to the keyword condition to obtain matching data. For example, keywords based on artificial knowledge are matched, and the keywords are | (or), & (and), |! And (not), the matching mode is keyword operation, parentheses are used as operation priority symbols, the condition source of the keywords is expert knowledge of historical precipitation, and the keywords are calculated and distributed in SPARK STREAMING real-time flow. Keyword condition examples, such as: (Shenzhen & landslide & Guangming) | (landslide & 2020). The text sentence is input text information, the keyword condition is shown in the example above, the information is subjected to jieba word segmentation to obtain a word list, then the keyword condition is subjected to bracket analysis, the operation sequence is bracket > non-operation > and operation > or operation, the operation mode is to inquire whether the word exists in the word list, the inquiry mode is polling, and finally a keyword matching result is obtained.
Step S200: and obtaining a first semantic vector by the matching data through a BERT model.
Referring to fig. 4, matching data is input into a BERT model, and a first semantic vector corresponding to the matching data output by the BERT model is received. For example, building a BERT service, using the BERT _ as _ service module, inputting text, calling a CLS vector as a semantic vector for the text.
Step S300: and acquiring a second information text, and obtaining a second semantic vector from the second information text through a BERT model.
Referring to fig. 5 and 6, acquiring a second information text, including performing similarity deduplication on the first information text to obtain deduplication text information; and carrying out time deduplication on the deduplication text information to obtain a second information text. Specifically, similarity duplication elimination is carried out on a first information text to obtain duplication elimination text information, wherein the duplication elimination text information comprises all historical semantic vectors in a preset time period; cosine similarity comparison is carried out on the first semantic vector and the historical semantic vector to obtain a comparison difference value of the two numerical values; and carrying out duplication elimination processing on the first semantic vector with the comparison difference value larger than the first preset value to obtain duplication elimination text information. Carrying out time deduplication on the deduplication text information to obtain a second information text, wherein the time data of the first information text is extracted; comparing the time data with the current time to obtain a time difference value; and carrying out deduplication processing on the first information text with the time difference value exceeding a second preset value.
For example, the specific repeatability and repeatability of information, and the repeated pushing of the same similar information can be one of the troublesome problems of machine real-time recommendation, in the embodiment of the invention, the semantic vector of news is used for carrying out similarity calculation with a news semantic vector library which is successfully pushed to clients within one year, if the similarity value is more than or equal to 0.9, the similarity is judged, the channel is manually confirmed, and if the similarity value is less than 0.9, the similarity is judged, and the duplicate removal is not carried out. Extracting the regular pattern through specific time, extracting the time of information occurrence, comparing with the current time, judging the information to be old if the time exceeds one year, and otherwise, passing the information; time extraction technology: extracting the regular pattern at a specific time: ([1-2] [0-9] {3}) [ year' - -/] ([0-1 ]; or, if the regular extraction is not available, the time normalization extraction is carried out by combining the TimeNormalizer module. In addition, in the embodiment of the invention, the second information text can be stored into the mysql database.
Step S400: and comparing the similarity of the first semantic vector and the second semantic vector to obtain comparison data.
Specifically, all historical semantic vectors are obtained, the average value of all historical semantic vectors is calculated, and the average value is used as a second semantic vector; and respectively analyzing the cosine similarity of the first semantic vector and the second semantic vector to obtain the cosine similarity of the first semantic vector and the second semantic vector. And comparing the cosine similarity value with a preset cosine similarity threshold value to obtain comparison data of the magnitude of the cosine similarity value and the preset cosine similarity threshold value.
For example, the cosine similarity between the first semantic vector and the second semantic vector is calculated, and if the value is greater than or equal to 0.7 or more, the enterprise is interested in public sentiment, otherwise, the enterprise is not interested in public sentiment.
Cosine similarity calculation (i.e., the similarity value calculation formula is supplemented):
given two attribute vectors, A and B, the remaining chord similarity θ is given by the dot product and the vector length, as follows:
in the embodiment of the present invention, a and B respectively refer to information vector and enterprise public opinion vector (in the formula, both are symmetric), Ai and Bi refer to the value of each dimension vector in the vector, and in the embodiment of the present invention, the dimension data is consistent with the CLS dimension number in BERT, which is 768 dimensions.
Step S500: and distributing the corresponding first information text to the terminal matched with the first information text according to the comparison data.
For example, public opinions which are recognized by the robot and are concerned by an enterprise are directly pushed to a communication program account of the enterprise through web connection, end-to-end recommendation is achieved, and the real-time and efficient effects are achieved. And issuing through a WEB interface provided by the robot of the communication program.
In addition, in the embodiment of the invention, a search library can be further arranged, and if the text is judged not to be the information text concerned by the user, the search library is stored in the ES database for manual search.
According to the embodiment of the invention, the first information text is obtained, and the keyword matching is carried out on the first information text to obtain the matching data. Then, obtaining a first semantic vector by the matching data through a BERT model; acquiring a second information text, obtaining a second semantic vector from the second information text through the BERT model, comparing the similarity of the first semantic vector and the second semantic vector to obtain comparison data, and distributing the corresponding first information text to a terminal matched with the first information text according to the comparison data. In summary, in the embodiments of the present invention, a first semantic vector and a second semantic vector are obtained through a BERT model, and the first semantic vector and the second semantic vector are compared with each other in terms of similarity, so as to finally obtain an information text meeting the user requirement, and the information text is pushed to a user terminal. Compared with the current information text distribution mode needing manual participation, the information recommendation and distribution method and the information recommendation and distribution device can effectively improve the information recommendation and distribution efficiency.
The embodiment of the present invention further provides an electronic device, which includes at least one memory, at least one processor, and at least one program, where the program is stored in the memory, and the processor executes the at least one program to implement the steps of the information recommendation method described above.
The embodiment of the invention also provides an illustrative scheme of a computer-readable storage medium. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the information recommendation method, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the information recommendation method.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. An information recommendation method, characterized by comprising the steps of:
acquiring a first information text, and performing keyword matching on the first information text to obtain matching data;
obtaining a first semantic vector from the matching data through a BERT model;
acquiring a second information text, and obtaining a second semantic vector from the second information text through the BERT model;
comparing the similarity of the first semantic vector and the second semantic vector to obtain comparison data;
and distributing the corresponding first information text to a terminal matched with the first information text according to the comparison data.
2. The information recommendation method according to claim 1, wherein said obtaining a second information text comprises:
carrying out similarity duplication elimination on the first information text to obtain duplication elimination text information;
and carrying out time deduplication on the deduplication text information to obtain the second information text.
3. The information recommendation method according to claim 2, wherein said similarity de-duplication of said first information text to obtain de-duplicated text information comprises the steps of:
acquiring all historical semantic vectors in a preset time period;
comparing the cosine similarity of the first semantic vector with the historical semantic vector to obtain a comparison difference value of the values of the first semantic vector and the historical semantic vector;
and carrying out duplication elimination processing on the first semantic vector with the comparison difference value larger than a first preset value to obtain duplication elimination text information.
4. The information recommendation method according to claim 3, wherein said time-deduplicating the deduplicating text information to obtain the second information text comprises:
extracting time data of the first information text;
comparing the time data with the current time to obtain a time difference value;
and carrying out deduplication processing on the first information text with the time difference value exceeding a second preset value.
5. The information recommendation method according to claim 1, wherein the obtaining of the first information text and the keyword matching of the first information text to obtain the matching data comprises the following steps:
acquiring the first information text;
performing word segmentation operation on the acquired first information text to obtain a word list;
and querying the word list according to the keyword condition to obtain the matching data.
6. The information recommendation method according to claim 1, wherein the step of obtaining the first semantic vector from the matching data through a BERT model comprises the following steps:
inputting the matching data into the BERT model;
and receiving a first semantic vector which is output by the BERT model and corresponds to the matching data.
7. The information recommendation method according to claim 1, wherein the comparing according to the similarity of the first semantic vector and the second semantic vector to obtain comparison data comprises:
acquiring all historical semantic vectors, calculating the average value of all the historical semantic vectors, and taking the average value as the second semantic vector;
and respectively analyzing the cosine similarity of the first semantic vector and the second semantic vector to obtain the cosine similarity of the first semantic vector and the second semantic vector.
8. The information recommendation method according to claim 7, wherein the comparing according to the similarity of the first semantic vector and the second semantic vector to obtain comparison data further comprises:
and comparing the cosine similarity value with a preset cosine similarity threshold value to obtain comparison data of the magnitude of the cosine similarity value and the preset cosine similarity threshold value.
9. An electronic device, comprising:
at least one memory;
at least one processor;
at least one program;
the programs are stored in the memory, and the processor executes the at least one program to implement the information recommendation method according to any one of claims 1 to 8.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the information recommendation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010676201.9A CN111966784A (en) | 2020-07-14 | 2020-07-14 | Information recommendation method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010676201.9A CN111966784A (en) | 2020-07-14 | 2020-07-14 | Information recommendation method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111966784A true CN111966784A (en) | 2020-11-20 |
Family
ID=73361673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010676201.9A Pending CN111966784A (en) | 2020-07-14 | 2020-07-14 | Information recommendation method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111966784A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| CN107463679A (en) * | 2017-08-07 | 2017-12-12 | 石林星 | A kind of information recommendation method and device |
| CN109871491A (en) * | 2019-03-20 | 2019-06-11 | 江苏满运软件科技有限公司 | Forum postings recommended method, system, equipment and storage medium |
| US20190243900A1 (en) * | 2017-03-03 | 2019-08-08 | Tencent Technology (Shenzhen) Company Limited | Automatic questioning and answering processing method and automatic questioning and answering system |
| CN111241381A (en) * | 2018-11-28 | 2020-06-05 | 北京奇虎科技有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
-
2020
- 2020-07-14 CN CN202010676201.9A patent/CN111966784A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| US20190243900A1 (en) * | 2017-03-03 | 2019-08-08 | Tencent Technology (Shenzhen) Company Limited | Automatic questioning and answering processing method and automatic questioning and answering system |
| CN107463679A (en) * | 2017-08-07 | 2017-12-12 | 石林星 | A kind of information recommendation method and device |
| CN111241381A (en) * | 2018-11-28 | 2020-06-05 | 北京奇虎科技有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
| CN109871491A (en) * | 2019-03-20 | 2019-06-11 | 江苏满运软件科技有限公司 | Forum postings recommended method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033387B (en) | Internet of things searching system and method fusing multi-source data and storage medium | |
| CN109271512B (en) | Emotion analysis method, device and storage medium for public opinion comment information | |
| CN106897428B (en) | Text classification feature extraction method and text classification method and device | |
| CN104573054B (en) | A kind of information-pushing method and equipment | |
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| US20190163742A1 (en) | Method and apparatus for generating information | |
| CN105608179B (en) | The method and apparatus for determining the relevance of user identifier | |
| CN106844407B (en) | Tag network generation method and system based on data set correlation | |
| CN110909222B (en) | User portrait establishing method and device based on clustering, medium and electronic equipment | |
| CN103248677B (en) | The Internet behavioural analysis system and method for work thereof | |
| CN107392259B (en) | Method and device for constructing unbalanced sample classification model | |
| CN110659436A (en) | Network public opinion monitoring method, device and equipment | |
| CN104657437A (en) | Monitoring method and monitoring device for promotion status data | |
| CN107133268B (en) | Collaborative filtering method for Web service recommendation | |
| WO2015165230A1 (en) | Social contact message monitoring method and device | |
| CN111930949B (en) | Search string processing method and device, computer readable medium and electronic equipment | |
| CN110704699A (en) | Data image construction method and device, computer equipment and storage medium | |
| CN112214770B (en) | Malicious sample identification method, device, computing equipment and medium | |
| CN111782970B (en) | Data analysis method and device | |
| CN105512270B (en) | Method and device for determining related objects | |
| WO2021056734A1 (en) | Friendship chain matching method and system, computer device, and readable storage medium | |
| CN111966784A (en) | Information recommendation method, electronic device and storage medium | |
| CN116094907A (en) | Complaint information processing method, complaint information processing device and storage medium | |
| CN113869904B (en) | Suspicious data identification method, device, electronic equipment, medium and computer program | |
| CN110852078A (en) | Method and device for generating title |
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 |