CN114676306A - Computer information sieving mechanism based on artificial intelligence - Google Patents
Computer information sieving mechanism based on artificial intelligence Download PDFInfo
- Publication number
- CN114676306A CN114676306A CN202210311618.4A CN202210311618A CN114676306A CN 114676306 A CN114676306 A CN 114676306A CN 202210311618 A CN202210311618 A CN 202210311618A CN 114676306 A CN114676306 A CN 114676306A
- Authority
- CN
- China
- Prior art keywords
- search
- module
- array
- entry
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 238000007873 sieving Methods 0.000 title description 2
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000012216 screening Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 239000012634 fragment Substances 0.000 description 8
- 238000000034 method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- 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
- G06F16/9538—Presentation of query results
-
- 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
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a computer information screening device based on artificial intelligence, which comprises a processor, wherein a processing system runs on the processor, and the processing system comprises: the device comprises a search segment acquisition module, a search segment disassembly module, a word disassembly qualitative module, a search mode determination module and a search execution module. The invention decomposes the words, obtains the actual meanings of the words according to the arrangement and combination structure of the words, matches the corresponding entries according to the actual meanings, and finally displays the corresponding entries to the user according to the association degree, so that when the user searches, the displayed entries are the entries which meet the requirements of the user and are not irrelevant to the search segments of the user, when the word combination is arranged, the arranged word combination structure is numbered according to the parts of speech and the categories of the words, and when the word combination is optimized, the caching mode is optimized according to the experience of the user.
Description
Technical Field
The invention relates to the field of computer data processing, in particular to a computer information screening device based on artificial intelligence.
Background
In the internet era, people can acquire information more conveniently and quickly, and more software helps people enjoy convenient life brought by the internet. In many internet software, the most used is a search engine, and when people want to search for contents they want, they can complete the search only by filling the searched contents in a search box and using a search instruction.
In the current search engine, the characters in the search box are received during searching, the characters in the search box are decomposed to obtain search terms, the search terms are sequentially arranged according to the key and then are sequentially searched, and finally, terms obtained through searching are sequentially displayed according to the association degree, so that the search of the segment characters is completed. Although the method can complete the search of the segment characters, the obtained search terms are often far from the expectations of the user because only the characters are decomposed, thereby resulting in poor user experience.
Disclosure of Invention
The invention aims to overcome the problems in the prior art and provide a computer information screening device based on artificial intelligence, which obtains the actual meanings of words according to the arrangement and combination structure of the words after the words are decomposed, matches the corresponding entries according to the actual meanings and finally displays the corresponding entries to users according to the association degree.
Therefore, the invention provides a computer information screening device based on artificial intelligence, which comprises a processor, wherein a processing system runs on the processor, and the processing system comprises:
the search segment acquisition module is used for acquiring the search segment in the search box after the user types;
a search segment disassembling module, configured to disassemble the obtained search segment using a pause word list to obtain various disassembled words of the search segment, and sequentially arrange each disassembled word according to the sequence of the disassembled word in the search segment;
the disassembled word qualitative module is used for acquiring the part of speech of each disassembled word, expressing the part of speech of the disassembled word by using a unified corresponding number, and sequentially arranging the number corresponding to each disassembled word according to the arrangement sequence of the numbers to obtain a semantic array;
the search mode determining module is used for inputting the semantic array into a trained learning model, outputting the semantic array to obtain a search array, carrying out normalization processing on the search array and outputting the search array, sequentially obtaining corresponding search behaviors according to the arrangement sequence of all numerical values in the search array, comprehensively obtaining a search mode and outputting the search mode;
and the search execution module is used for completing search in the Internet according to the search mode and displaying the searched entries to the user.
Further, the search fragment acquisition module includes:
the recording monitoring module is used for monitoring the recording operation of the user in the search box;
the logging timing module is used for receiving the starting time and the ending time of the operation logging;
the state judgment module is used for calculating a time interval between the ending time of the former and the starting time of the latter in two adjacent input operations, judging whether the time interval is in the range of a set time interval range, if so, skipping to execute the input monitoring module, and if not, skipping to execute the segment output module;
and the segment output module is used for acquiring and outputting the characters in the current search box as the search segments.
Further, the search execution module, when displaying the searched entry to the user, includes the following steps:
respectively acquiring the link content of each searched entry, and converting the link content of each entry into a text format;
extracting entry topics from the linked content in the text format by using a topic extraction technology;
disassembling the entry theme by using a pause word list to obtain each topic word of the entry theme, and sequentially arranging each topic word according to the sequence of the topic word in the entry theme;
acquiring the part of speech of each subject word, expressing the part of speech of the subject word by using a unified corresponding number, and sequentially arranging the number corresponding to each subject word according to the arrangement sequence of the numbers to obtain a term array;
respectively carrying out similarity matching on each entry array and the semantic array to obtain a matching degree value, and arranging each entry in sequence according to the size of the corresponding matching degree value;
and sequentially displaying the arranged entries to a user according to the sequence of a display interface from top to bottom.
Further, when similarity matching is performed, the method comprises the following steps:
respectively establishing two matching chains, wherein each matching chain is respectively composed of a plurality of comparison areas which are sequentially arranged;
sequentially filling each numerical value in the entry array and the semantic array into the matching chains, wherein each matching chain is filled with an array;
sequentially comparing the difference value of the numerical values in the comparison areas in the corresponding sequence in the two matching chains, and obtaining the association degree numerical value of the numerical values in the two comparison areas according to the difference value;
and sequentially solving the association degree values corresponding to each corresponding two comparison areas, and calculating each association degree value in a weighting mode to obtain the matching degree value.
Further, the learning model in the search mode determination module is stored in a local cache.
Further, when training the learning model, the obtaining of the output of the learning model comprises the following steps:
s1: after the entries are displayed to the user, monitoring the access times and the access time of the user to each entry;
s2: carrying out numerical calculation on the access times and the access time of each entry by the user according to the set weight weighting to obtain access values corresponding to the entries;
s3: arranging each entry in sequence according to the corresponding access value;
s4: and adjusting the search array until the searched entries displayed to the user entry are the same as the sequence of the searched entries in the step S3.
Further, the weight set in step S2 is such that the ratio of the number of accesses to the access time is 1: 9.
The computer information screening device based on artificial intelligence provided by the invention has the following beneficial effects:
according to the invention, after words are decomposed, the actual meanings of the words are obtained according to the arrangement and combination structure of the words, corresponding entries are matched according to the actual meanings, and finally the corresponding entries are displayed to a user according to the association degree, so that when the user searches, the displayed entries are the entries which are in line with the user requirements and are not irrelevant to the search segments of the user;
when the word combination is arranged, the arranged word combination structure is numbered according to the part of speech and the category of the word, and the corresponding number and the corresponding searching mode are stored in the cache, so that the search can be optimized in a local cache mode during storage, and meanwhile, the cache mode is optimized according to the experience of a user during optimization.
Drawings
FIG. 1 is a schematic block diagram of a system connection of a processing system of the present invention;
FIG. 2 is a schematic block diagram of a system connection of a search segment acquisition module of the present invention;
FIG. 3 is a schematic block diagram of the process of the search execution module of the present invention in displaying the searched terms to the user;
fig. 4 is a schematic block diagram of a process of performing similarity matching according to the present invention.
Detailed Description
An embodiment of the present invention will be described in detail below with reference to the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the embodiment.
In the present application, the type and structure of components that are not specified are all the prior art known to those skilled in the art, and those skilled in the art can set the components according to the needs of the actual situation, and the embodiments of the present application are not specifically limited.
Specifically, as shown in fig. 1 to 4, an embodiment of the present invention provides an artificial intelligence-based computer information screening apparatus, including a processor, on which a processing system runs, where the processing system includes: the device comprises a search segment acquisition module, a search segment disassembly module, a word disassembly qualitative module, a search mode determination module and a search execution module. The following is a detailed description of the various modules.
The search segment acquisition module is used for acquiring the search segment in the search box after the user types; the module is used for acquiring characters, and acquiring the characters in a search box when a user finishes inputting, namely the search fragment of the invention.
A search segment disassembling module, configured to disassemble the obtained search segment using a pause word list to obtain various disassembled words of the search segment, and sequentially arrange each disassembled word according to the sequence of the disassembled word in the search segment; the module disassembles the search segments, namely disassembles the whole text segment to obtain each word forming the text segment, namely the disassembled word of the invention.
The disassembled word qualitative module is used for acquiring the part of speech of each disassembled word, expressing the part of speech of the disassembled word by using a unified corresponding number, and sequentially arranging the number corresponding to each disassembled word according to the arrangement sequence of the numbers to obtain a semantic array; the module analyzes each obtained disassembled word to obtain the part of speech of the disassembled word, and uses numbers to represent the part of speech of each disassembled word for convenient subsequent processing, and arranges the numerical values corresponding to the parts of speech according to the sequence of the disassembled words to obtain a semantic array, so that the semantic trend of the text can be clear, and the subsequent searching mode can be determined.
The search mode determining module is used for inputting the semantic array into a trained learning model, outputting the semantic array to obtain a search array, carrying out normalization processing on the search array and outputting the search array, sequentially obtaining corresponding search behaviors according to the arrangement sequence of all numerical values in the search array, comprehensively obtaining a search mode and outputting the search mode; the module obtains a corresponding search mode according to the semantic array, generally, the invention uses a mode of multiple accumulation retrieval, and finally obtains intersection.
The search execution module is used for completing search in the Internet according to the search mode and displaying searched entries to a user; the module is a corresponding execution unit, executes the above-mentioned operations, and displays the search result to the user.
According to the invention, through the coordination of the modules, after words are decomposed, the actual meanings of the words are obtained according to the arrangement and combination structure of the words, the corresponding entries are matched according to the actual meanings, and finally the corresponding entries are displayed to the user according to the association degree, so that when the user searches, the displayed entries are the entries which meet the requirements of the user, and the entries which are irrelevant to the search segments of the user cannot be generated.
In the present invention, the search fragment acquisition module includes: the device comprises an input monitoring module, an input timing module, a state judgment module and a fragment output module. The following is a detailed operational description of the various functional modules.
The recording monitoring module is used for monitoring the recording operation of the user in the search box; the module is a monitoring module and is mainly used for monitoring the operation state of a user.
The logging timing module is used for receiving the starting time and the ending time of the operation logging; the module is used for carrying out preliminary analysis on the monitored condition, and the time of user operation is obtained in a time using mode during analysis.
The state judgment module is used for calculating a time interval between the ending time of the former and the starting time of the latter in two adjacent input operations, judging whether the time interval is in the range of a set time interval range, if so, skipping to execute the input monitoring module, and if not, skipping to execute the segment output module; the module judges whether the user operation is finished or not by acquiring the interval between the user operations.
The segment output module is used for acquiring and outputting the characters in the current search box as the search segments; this module is the function of acquisition and output.
Through the combined action of the input monitoring module, the input timing module, the state judgment module and the fragment output module, the invention can acquire the complete search fragment input by the user and then carry out the search process, so that the used search mode is the same as the originally used search mode when the search fragment is analyzed.
In order to display the relative height of the viewed entries in front of the user and improve the search result experience of the user, the search execution module comprises the following steps when displaying the searched entries to the user:
respectively acquiring the link content of each searched entry, and converting the link content of each entry into a text format;
(II) extracting an entry topic from the linked content in the text format by using a topic extraction technology;
thirdly, the entry theme is disassembled by using a pause word list to obtain each theme word of the entry theme, and each theme word is sequentially arranged according to the sequence of the theme word in the entry theme;
fourthly, the part of speech of each topic word is obtained, the part of speech of the topic word is represented by the number corresponding to the unity, and the number corresponding to each topic word is sequentially arranged according to the arrangement sequence of the number to obtain an entry array;
(V) respectively carrying out similarity matching on each entry array and the semantic array to obtain a matching degree value, and arranging each entry in sequence according to the size of the corresponding matching degree value;
and sixthly, sequentially displaying the arranged entries to a user according to the sequence of a display interface from top to bottom.
The method comprises the steps of (a) sequentially performing the steps to (six) according to a logic sequence, and sequentially displaying the entries according to the searched relevancy, starting from the content of the entries, obtaining the subject of the entries, obtaining the content and the semantics displayed by the entries according to the subject of the entries, namely, the entry numerical values described in the invention, representing the semantics of the entries, and performing similarity matching on the entry array and the semantic array, so that the entries with high similarity are the entries with high relevance, and the relevance degree of each entry and the search fragment can be obtained, so that when the entries are displayed to a user, the user can preferentially see the entries with high relevance degree, and the user experience is improved.
When the word combination is arranged, the arranged word combination structure is numbered according to the part of speech and the category of the word, and the corresponding number and the corresponding searching mode are stored in the cache, so that the search can be optimized in a local cache mode during storage, and meanwhile, the cache mode is optimized according to the experience of a user during optimization.
Meanwhile, in the invention, when the similarity matching is carried out, the method comprises the following steps:
(1) respectively establishing two matching chains, wherein each matching chain is respectively composed of a plurality of comparison areas which are sequentially arranged;
(2) filling the entry array and each numerical value in the semantic array into the matching chains in sequence, wherein each matching chain is filled with an array;
(3) sequentially comparing the difference value of the numerical values in the comparison areas in the corresponding sequence in the two matching chains, and obtaining the association degree numerical value of the numerical values in the two comparison areas according to the difference value;
(4) and sequentially solving the association degree values corresponding to each corresponding two comparison areas, and calculating each association degree value in a weighting mode to obtain the matching degree value.
In the technical scheme, the steps (1) - (4) are sequentially performed according to a logic sequence, the matching degree values of two arrays are obtained in a digital two-matching mode, in the invention, the corresponding values of two identical positions are compared to obtain a difference, a final matching degree value is obtained according to the difference and corresponding weighting, the matching degree value is generally expressed in a percentage mode, and the larger the general matching degree value is, the higher the matching degree is. And during weighting, setting the weight according to the condition of the voice array, wherein each semantic array has the weight of each position numerical value which is uniquely corresponding.
In the invention, the learning model in the searching mode determining module is stored in a local cache. Therefore, the called data can be quickly imported when the data is called.
Meanwhile, in the present invention, when training a learning model, the obtaining of the output of the learning model includes the following steps:
s1: after the entries are displayed to the user, monitoring the access times and the access time of the user to each entry;
s2: carrying out numerical calculation on the access times and the access time of each entry by the user according to the set weight weighting to obtain access values corresponding to the entries;
s3: arranging each entry in sequence according to the corresponding access value;
s4: and adjusting the search array until the searched entries displayed to the user entry are the same as the sequence of the searched entries in the step S3.
The invention judges the correlation degree of the entries and the user requirements according to the browsing condition of the user on the entries in the learning model training process, and generally, the correlation degree is larger due to long visiting time, the visiting times are more, and the correlation degree is larger. In the present invention, the weight set in step S2 is such that the ratio of the number of accesses to the access time is 1: 9.
The above disclosure is only for a few specific embodiments of the present invention, however, the present invention is not limited to the above embodiments, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present invention.
Claims (7)
1. An artificial intelligence based computer information screening device, comprising a processor, wherein a processing system runs on the processor, and the processing system comprises:
the search segment acquisition module is used for acquiring the search segment in the search box after the user types;
a search segment disassembling module, configured to disassemble the obtained search segment using a pause word list to obtain various disassembled words of the search segment, and sequentially arrange each disassembled word according to the sequence of the disassembled word in the search segment;
the disassembled word qualitative module is used for acquiring the part of speech of each disassembled word, expressing the part of speech of the disassembled word by using a unified corresponding number, and sequentially arranging the number corresponding to each disassembled word according to the arrangement sequence of the numbers to obtain a semantic array;
the search mode determining module is used for inputting the semantic array into a trained learning model, outputting the semantic array to obtain a search array, carrying out normalization processing on the search array and outputting the search array, sequentially obtaining corresponding search behaviors according to the arrangement sequence of all numerical values in the search array, comprehensively obtaining a search mode and outputting the search mode;
and the search execution module is used for completing search in the Internet according to the search mode and displaying the searched entries to the user.
2. The artificial intelligence based computer information screening apparatus of claim 1, wherein the search segment obtaining module comprises:
the recording monitoring module is used for monitoring the recording operation of the user in the search box;
the logging timing module is used for receiving the starting time and the ending time of the operation logging;
the state judgment module is used for calculating a time interval between the ending time of the former and the starting time of the latter in two adjacent input operations, judging whether the time interval is in the range of a set time interval range, if so, skipping to execute the input monitoring module, and if not, skipping to execute the segment output module;
and the segment output module is used for acquiring and outputting the characters in the current search box as the search segments.
3. The artificial intelligence based computer information screening apparatus of claim 1, wherein the search execution module, when displaying the searched entry to the user, comprises the following steps:
respectively acquiring the link content of each searched entry, and converting the link content of each entry into a text format;
extracting entry topics from the linked content in the text format by using a topic extraction technology;
using a pause word list to disassemble the entry theme to obtain each theme word of the entry theme, and sequentially arranging each theme word according to the sequence of the theme word in the entry theme;
acquiring the part of speech of each subject word, expressing the part of speech of the subject word by using a unified corresponding number, and sequentially arranging the number corresponding to each subject word according to the arrangement sequence of the numbers to obtain a term array;
respectively carrying out similarity matching on each entry array and the semantic array to obtain a matching degree value, and arranging each entry in sequence according to the size of the corresponding matching degree value;
and sequentially displaying the arranged entries to a user according to the sequence of a display interface from top to bottom.
4. The artificial intelligence based computer information screening apparatus of claim 3, wherein when performing similarity matching, comprising the steps of:
respectively establishing two matching chains, wherein each matching chain is respectively composed of a plurality of comparison areas which are sequentially arranged;
sequentially filling each numerical value in the entry array and the semantic array into the matching chains, wherein each matching chain is filled with an array;
sequentially comparing the difference value of the numerical values in the comparison areas in the corresponding sequence in the two matching chains, and obtaining the association degree numerical value of the numerical values in the two comparison areas according to the difference value;
and sequentially solving the association degree values corresponding to each corresponding two comparison areas, and calculating each association degree value in a weighting mode to obtain the matching degree value.
5. The artificial intelligence based computer information screening apparatus of claim 1, wherein the learning model in the search mode determining module is stored in a local cache.
6. An artificial intelligence based computer information screening apparatus as claimed in claim 5, wherein the obtaining of the output of the learning model when training the learning model comprises the steps of:
s1: after the entries are displayed to the user, monitoring the access times and the access time of the user to each entry;
s2: carrying out numerical calculation on the access times and the access time of each entry by the user according to the set weight weighting to obtain access values corresponding to the entries;
s3: arranging each entry in sequence according to the corresponding access value;
s4: and adjusting the search array until the searched entries displayed to the user entry are the same as the sequence of the searched entries in the step S3.
7. The artificial intelligence based computer information filtering apparatus of claim 6, wherein the weight set in the step S2 is that the ratio of the number of access times to the access time is 1: 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210311618.4A CN114676306A (en) | 2022-03-28 | 2022-03-28 | Computer information sieving mechanism based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210311618.4A CN114676306A (en) | 2022-03-28 | 2022-03-28 | Computer information sieving mechanism based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114676306A true CN114676306A (en) | 2022-06-28 |
Family
ID=82075232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210311618.4A Pending CN114676306A (en) | 2022-03-28 | 2022-03-28 | Computer information sieving mechanism based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114676306A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105677924A (en) * | 2016-03-29 | 2016-06-15 | 努比亚技术有限公司 | Data searching device and method |
| CN110363617A (en) * | 2019-06-03 | 2019-10-22 | 北京三快在线科技有限公司 | A kind of recommended method, device, electronic equipment and readable storage medium storing program for executing |
| CN111291168A (en) * | 2018-12-07 | 2020-06-16 | 北大方正集团有限公司 | Book retrieval method and device and readable storage medium |
| CN112434220A (en) * | 2020-11-25 | 2021-03-02 | 浙江兴士烨新材料科技有限公司 | Product pushing system and method based on Internet |
| CN113255343A (en) * | 2021-06-21 | 2021-08-13 | 中国平安人寿保险股份有限公司 | Semantic identification method and device for label data, computer equipment and storage medium |
| CN113535936A (en) * | 2021-06-21 | 2021-10-22 | 杭州初灵数据科技有限公司 | Deep learning-based regulation and regulation retrieval method and system |
-
2022
- 2022-03-28 CN CN202210311618.4A patent/CN114676306A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105677924A (en) * | 2016-03-29 | 2016-06-15 | 努比亚技术有限公司 | Data searching device and method |
| CN111291168A (en) * | 2018-12-07 | 2020-06-16 | 北大方正集团有限公司 | Book retrieval method and device and readable storage medium |
| CN110363617A (en) * | 2019-06-03 | 2019-10-22 | 北京三快在线科技有限公司 | A kind of recommended method, device, electronic equipment and readable storage medium storing program for executing |
| CN112434220A (en) * | 2020-11-25 | 2021-03-02 | 浙江兴士烨新材料科技有限公司 | Product pushing system and method based on Internet |
| CN113255343A (en) * | 2021-06-21 | 2021-08-13 | 中国平安人寿保险股份有限公司 | Semantic identification method and device for label data, computer equipment and storage medium |
| CN113535936A (en) * | 2021-06-21 | 2021-10-22 | 杭州初灵数据科技有限公司 | Deep learning-based regulation and regulation retrieval method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10896212B2 (en) | System and methods for automating trademark and service mark searches | |
| US10936821B2 (en) | Testing and training a question-answering system | |
| AU2019201531B2 (en) | An in-app conversational question answering assistant for product help | |
| CA2533605C (en) | Providing a user interface with search query broadening | |
| CN117033608A (en) | Knowledge graph generation type question-answering method and system based on large language model | |
| CN111859160B (en) | Session sequence recommendation method and system based on graph neural network | |
| CN111488137B (en) | Code searching method based on common attention characterization learning | |
| CN105979376A (en) | Recommendation method and device | |
| CN110364234A (en) | Electronic health record intelligent storage analyzing search system and method | |
| CN106708929B (en) | Video program searching method and device | |
| KR20050073429A (en) | Machine-learned approach to determining document relevance for search over large electronic collections of documents | |
| US20160063062A1 (en) | Code searching and ranking | |
| CN112749328B (en) | Searching method, searching device and computer equipment | |
| CN110851584A (en) | Accurate recommendation system and method for legal provision | |
| CN114254158A (en) | Video generation method and device, and neural network training method and device | |
| CN114239730A (en) | Cross-modal retrieval method based on neighbor sorting relation | |
| CN113918702A (en) | Semantic matching-based online legal automatic question-answering method and system | |
| CN114676306A (en) | Computer information sieving mechanism based on artificial intelligence | |
| US20210149900A1 (en) | Method, system and computer program for semantic triple-based knowledge extension | |
| CN116955591A (en) | Recommendation language generation method, related device and medium for content recommendation | |
| CN113761081A (en) | Method and system for carrying out multi-dimensional combined retrieval on enterprise information | |
| CN112527982A (en) | Equipment management system, method, equipment and storage medium | |
| CN113239274B (en) | Behavior big data automatic acquisition system | |
| CN113722608B (en) | Collaborative filtering method and device based on association relation learning under guidance of iterative auxiliary information | |
| CN112905884B (en) | Method, apparatus, medium and program product for generating sequence annotation model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220628 |