CN113297254A - Conceptualization query method and device - Google Patents
Conceptualization query method and device Download PDFInfo
- Publication number
- CN113297254A CN113297254A CN202110683675.0A CN202110683675A CN113297254A CN 113297254 A CN113297254 A CN 113297254A CN 202110683675 A CN202110683675 A CN 202110683675A CN 113297254 A CN113297254 A CN 113297254A
- Authority
- CN
- China
- Prior art keywords
- level
- low
- concept
- level concept
- concepts
- 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 46
- 238000013139 quantization Methods 0.000 claims abstract description 69
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 7
- 238000007477 logistic regression Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000008878 coupling Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229910052697 platinum Inorganic materials 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013598 vector Substances 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2433—Query languages
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a conceptualization query method and a conceptualization query device, wherein the method comprises the following steps: obtaining a query statement, wherein the query statement comprises a high-level concept; determining a plurality of lower-level concepts associated with the higher-level concept, each higher-level concept data being a weighted sum of the associated plurality of lower-level concept data, the weight of each lower-level concept being adjustable according to user feedback; obtaining at least one quantization interval of each low-level concept in a plurality of low-level concepts associated with the high-level concept and a score corresponding to each quantization interval, wherein the quantization interval corresponding to each low-level concept can be adjusted according to user feedback; calculating the score of each product corresponding to the high-level concept according to the quantization intervals of each product in the plurality of products corresponding to the low-level concepts and the score corresponding to each quantization interval and the weight of the plurality of low-level concepts; and obtaining one or more target products to be recommended according to the size relation of scores corresponding to the high-level concepts of the products. Therefore, the query precision is improved.
Description
Technical Field
The present application relates to the field of computer technology, and more particularly, to a conceptualized query method and apparatus.
Background
Aiming at the knowledge in a specific field, a knowledge base can be established to facilitate the user to search and obtain a corresponding result. When a user queries knowledge meeting self requirements, the user tends to use some high-level concepts of ambiguity and uncertainty due to the fact that knowledge structures and contents are not known.
In the prior art, the high-level concepts can be subjected to multi-level conceptualization processing to obtain quantifiable low-level concepts, and the low-level concepts and the high-level concepts are stored, so that a user can find the low-level concepts related to the high-level concepts when querying the corresponding high-level concepts, and a query result is obtained. However, in business scenarios such as knowledge retrieval and product query, higher requirements are placed on the accuracy of quantizing the high-level concept to the low-level concept, so that a conceptualized query method which is more efficient, accurate, maintainable and highly applicable is required, and the query accuracy is improved to meet the query requirements of users.
Disclosure of Invention
The embodiment of the application provides a conceptualization query method, so that the query precision is improved.
In a first aspect, the present application provides a conceptualized query method, including: obtaining a query statement, wherein the query statement comprises a high-level concept; determining a plurality of lower-level concepts associated with the higher-level concept, each higher-level concept being a weighted sum of the associated plurality of lower-level concepts, the weight of each lower-level concept being adjustable according to user feedback; obtaining at least one quantization interval of each low-level concept in a plurality of low-level concepts associated with the high-level concept and a score corresponding to each quantization interval, wherein the quantization interval corresponding to each low-level concept can be adjusted according to user feedback; calculating the score corresponding to each product in the high-level concepts according to the quantization intervals corresponding to the low-level concepts of each product in the plurality of products, the score corresponding to each quantization interval and the weights of the low-level concepts; and obtaining one or more target products to be recommended according to the size relation of the scores of the products corresponding to the high-level concepts.
Based on the scheme, the query information with certain ambiguity and uncertainty input by the user can be converted into the quantifiable weighted sum of the low-level concepts by quantifying the high-level concepts into the weighted sum of the associated low-level concepts, and the weights in the query information can be adjusted according to the satisfaction degree fed back by the user, so that the real expectation of the user of the obtained conceptualized query result is closer, the query precision is improved, and the query requirement of the user is met.
Optionally, the determining a plurality of low-level concepts associated with the high-level concept comprises: and searching a plurality of low-level concepts related to the high-level concept in a conceptualized hierarchical database, wherein the conceptualized hierarchical database is prestored with the plurality of high-level concepts and the related low-level concepts.
Optionally, the weight of each low-level concept and the quantization interval corresponding to each low-level concept are adjusted according to user feedback.
Optionally, the adjusting, according to the user feedback, the weight of each low-level concept and the quantization interval corresponding to each low-level concept includes: and taking the concept set containing the plurality of low-level concepts and the satisfaction degree of the corresponding user feedback as a training sample, training the model by enabling the predicted satisfaction degree of the user feedback obtained by the model to be close to the satisfaction degree of the real user feedback, and automatically adjusting the weight of each low-level concept and the quantization interval corresponding to each low-level concept so as to obtain the weight of each low-level concept and the quantization interval corresponding to each low-level concept.
Optionally, the query statement is a Structured Query Language (SQL) statement.
Optionally, the model includes eXtreme gradient boosting (XGBoost) and Logistic Regression (LR) algorithms.
In a second aspect, a conceptualized query apparatus is provided, including a module or a unit for implementing the conceptualized query method described in any one of the first aspect and the first aspect. It should be understood that the respective modules or units may implement the respective functions by executing the computer program.
In a third aspect, a conceptualized query apparatus is provided, including a processor configured to execute the conceptualized query method of any one of the first aspect and the first aspect.
The apparatus may also include a memory to store instructions and data. The memory is coupled to the processor, and the processor, when executing the instructions stored in the memory, may implement the method described in the first aspect above. The apparatus may also include a communication interface for the apparatus to communicate with other devices, which may be, for example, a transceiver, circuit, bus, module, or other type of communication interface.
In a fourth aspect, a chip system is provided, which comprises at least one processor configured to support the implementation of the functionality referred to in the first aspect as well as any one of the possible implementations of the first aspect, e.g. to receive or process data and/or information referred to in the above method.
In one possible design, the system-on-chip further includes a memory to hold program instructions and data, the memory being located within the processor or external to the processor.
In a fifth aspect, there is provided a computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to carry out the method of any one of the first aspect and the first aspect.
In a sixth aspect, there is provided a computer program product comprising: a computer program (also referred to as code, or instructions), which when executed, causes a computer to perform the method of any of the first aspect and the first aspect.
It should be understood that the second aspect to the sixth aspect of the present application correspond to the technical solutions of the first aspect of the present application, and the beneficial effects achieved by the aspects and the corresponding possible implementations are similar and will not be described again.
Drawings
FIG. 1 is a schematic flow chart diagram of a conceptualized query method provided by an embodiment of the present application;
FIG. 2 is a schematic block diagram of a conceptualized query device provided by an embodiment of the present application;
fig. 3 is another schematic block diagram of a conceptualized query device provided by an embodiment of the present application.
Detailed Description
The technical solution in the present application will be described below with reference to the accompanying drawings.
For ease of understanding, some terms referred to in the present application are explained first below.
Conceptualization query: aiming at the query requirements which are provided by a user and contain some ambiguity and uncertainty concepts, the system carries out conceptualization processing on the ambiguity and uncertainty concepts to provide a query result.
For example, in the problem of 'which product has high cost performance' proposed by the user, the high cost performance is a fuzzy concept, and can be further quantized into a plurality of quantifiable concepts such as low cost, good quality and the like, and then the system gives a query result according to two attributes of price and quality.
And (3) query statement: a machine query language facilitates a machine to query data from a database itself. For example, SQL may be used.
SQL: is a special purpose programming language, a database query and programming language, used to access data and query, update and manage relational database systems.
High-level concept: are some concepts of ambiguity, uncertainty. Can be quantized from the low-level concept. In particular, a high-level concept may be quantized as a weighted sum of low-level concepts contained within the high-level concept.
Low-level concept: the concept of properties can be quantified.
The following exemplarily illustrates the relationship of the low-level concepts to the high-level concepts. For example, "cost performance is high" belonging to the high-level concepts of "good quality" and "low price," and "bank card" belongs to the high-level concepts of "debit card" and "platinum card".
Conceptualized hierarchical database: a database is pre-stored with a plurality of high-level concepts and their associated low-level concepts.
XGboost: an optimized distributed gradient enhancement library efficiently and flexibly solves the problem of data science through parallel computing, approximate tree building, sparse data processing and memory use optimization. In the embodiment of the present application, the method may be specifically used to construct a relationship tree of a high-level concept and a low-level concept, so as to calculate the score of each product according to the relationship tree at a later stage, thereby obtaining a query result.
LR: and predicting the probability of the future result occurrence through the performance of the historical data items. In the embodiment of the application, the weight of each low-layer concept and the quantization interval corresponding to each low-layer concept are adjusted in combination with XGboost.
Aiming at the knowledge in a specific field, a knowledge base can be established to facilitate the user to search and obtain a corresponding result. When a user queries knowledge meeting self requirements, some high-level concepts with certain ambiguity and uncertainty tend to be used due to the fact that knowledge structures and contents are not known.
In the prior art, multi-level conceptualization processing can be performed on the high-level concepts to obtain quantitative low-level concepts, and the low-level concepts and the high-level concepts are stored, so that a user can find the low-level concepts related to the high-level concepts when inquiring the corresponding high-level concepts, and a query result is obtained. However, in business scenarios such as knowledge retrieval and product query, higher requirements are placed on the accuracy of quantizing the high-level concept to the low-level concept, so that a conceptualized query method which is more efficient, accurate, maintainable and highly applicable is required, and the query accuracy is improved to meet the query requirements of users.
Therefore, the embodiment of the application provides a conceptualization query method, based on the method, conceptualization query conditions with certain ambiguity and uncertainty input by a user can be accurately converted into some quantifiable conceptualization attributes, a query result is obtained by calculating scores of a plurality of corresponding conceptualization attributes in each conceptualization query condition and then weighting and summing the scores, and the weight can be adjusted according to the satisfaction fed back by the user, so that the query result is closer to the requirements of the user.
The embodiment of the application also provides a conceptualized query device, which can be a server configured with a conceptualized hierarchical database (hereinafter referred to as a database).
The technical solution in the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a conceptual query method 100 according to an embodiment of the present disclosure. The method 100 includes steps 110 through 150, and the steps 110 through 150 are described in detail below.
In step 110, a query statement is obtained, the query statement including high-level concepts.
One possible scenario is that a user can provide a query requirement to a customer service staff by means of voice call, and the customer service staff can extract keywords according to the query requirement of the user and input the keywords into a query box of a value server. It will be appreciated that since users are looking for knowledge that meets their needs, they tend to use some high-level concepts including ambiguity and uncertainty due to the lack of knowledge structure and content. The keywords thus extracted also tend to include high-level concepts.
When the server searches the data desired by the user from the database according to the high-level concepts, the high-level concepts need to be converted into statements which can be understood by the machine, namely query statements, wherein the query statements can be SQL statements.
It should be understood that the above-listed scenarios are only examples and should not constitute any limitation on the embodiments of the present application. The user can also directly input the keywords in the query requirement into the query box of the value server, or the query requirement is sent to the server in a voice mode, and the server can extract the keywords by self. The server may further translate into a query statement based on high-level concepts in the keyword. Or, the server can also extract the high-level concepts according to the query requirement of the user, and then convert the high-level concepts into the query statement. The embodiment of the present application does not limit the manner of obtaining the query statement.
In step 120, a plurality of low-level concepts associated with the high-level concept is determined.
In embodiments of the present application, the high-level concepts and the low-level concepts may be quantized, for example, characterized by vectors. Each high-level concept can be quantized to a weighted sum of the associated plurality of low-level concepts, the weight of each low-level concept being adjustable according to user feedback. In other words, the weight used by each low-level concept when weighting a certain high-level concept is variable.
Wherein the lower-level concepts associated with each higher-level concept may be stored in a conceptual hierarchical database. After the server converts the high-level concepts into the query statement, the high-level concepts and the related low-level concepts can be directly obtained by querying from the conceptual hierarchical database according to the query statement.
Illustratively, Table 1 gives N (N ≧ 1 and an integer) lower-level concepts corresponding to one higher-level concept.
TABLE 1
| Numbering | Low level concept |
| 1 | Attribute 1 |
| 2 | Attribute 2 |
| 3 | Attribute 3 |
| ... | ... |
| N | Attribute N |
Wherein each low-level concept can also be understood as an attribute. As previously described, each high-level concept may be quantized to a weighted sum of the associated plurality of low-level concepts, and in Table 1, the weighted sum of attributes 1 through N may be used to characterize a high-level concept.
In step 130, at least one quantization interval of each low-level concept of the plurality of low-level concepts associated with the high-level concept and a score corresponding to each quantization interval are obtained.
Since there may be a large quantization range corresponding to each low-level concept, at least one quantization interval may also be set for each low-level concept, each quantization interval may correspond to one score. At least one quantization interval of each low-level concept and the score corresponding to each quantization interval can be stored in the database together with the low-level concept, so that after a plurality of low-level concepts associated with the high-level concept are obtained according to the query statement, at least one quantization interval of each low-level concept and the score corresponding to each quantization interval can also be obtained.
The initial values of the upper limit and the lower limit of the quantization interval can be set according to expert experience, and in order to provide a query result more accurately, the upper limit value and the lower limit value of the quantization interval can be adjusted in the later stage according to the satisfaction degree of the user on the query result.
For convenience of illustration, table 2 shows quantization intervals corresponding to a plurality of low-level concepts and scores corresponding to each quantization interval. The knowledge corresponding to the same knowledge number can be regarded as a rule for scoring the quantization interval corresponding to the same low-level concept. As an example, if knowledge 1 in Table 2 corresponds to low-level concept 1 in Table 1, knowledge 1 in Table 2 corresponds to two quantization intervals, interval 1 and interval 2, and the two intervals correspond to scores s respectively1And score s2Then it means that there are two quantities for the low-level attribute 1The interval, interval 1 and interval 2, the two intervals correspond to the score s respectively1And score s2. As yet another example, if knowledge 2 in Table 2 corresponds to low-level concept 2 in Table 1, knowledge 2 in Table 2 corresponds to two quantization intervals, interval 1 and interval 2, each corresponding to a score s3And score s4Then, it means that the low-level concept 2 has two quantization intervals, interval 1 and interval 2, and the two intervals correspond to the score s respectively3And score s4. It is to be understood that the intervals 1 and 2 of the low-level concept 1 and the low-level concept 2 in table 2 may be different quantization intervals. Other knowledge is similar, and for brevity, will not be described in detail.
TABLE 2
| Knowledge numbering | Quantization interval | Score corresponding to each interval |
| Knowledge 1 | Interval 1 | Score s1 |
| Knowledge 1 | Interval 2 | Score s2 |
| Knowledge 2 | Interval 1 | Score s3 |
| Knowledge 2 | Interval 2 | Score s4 |
| Knowledge 3 | Interval 3 | Score s5 |
| ... | ... | ... |
| Knowledge M | Interval N | Score sK |
Wherein N is more than or equal to 1, N is more than or equal to M is more than or equal to 1, and N, M are integers.
For convenience of explanation, how to give the query result will be described below by taking the query question made by the user for the product as an example, and specifically, reference may be made to step 140 and step 150.
In step 140, a score corresponding to each product in the high-level concepts is calculated according to the quantization intervals corresponding to each product in the plurality of low-level concepts and the score corresponding to each quantization interval, and the weights of the plurality of low-level concepts.
The initial value of the weight of the low-level concept can be set according to expert experience, and in order to give a query result more accurately, the weight of the low-level concept can be adjusted in the later stage according to the satisfaction degree of the user on the query result.
It should be understood that each product corresponds to a plurality of attributes, that is, corresponds to a plurality of low-level concepts, and as can be seen from table 2, each knowledge corresponds to a rule that a quantization interval corresponding to one low-level concept corresponds to a score, each low-level concept corresponds to one or more quantization intervals, and each quantization interval corresponds to a score.
One possible implementation is: when the score of a high-level concept corresponding to a product is judged, the score can be obtained by calculating the weighted sum of the scores of the quantization intervals corresponding to a plurality of low-level concepts corresponding to the high-level concept of each product.
Illustratively, a high-level concept corresponding to a product has two attributes, attribute 1 and attribute 2, which correspond to knowledge 1 and knowledge 2, respectively, the quantization interval of attribute 1 of the product is quantization interval 1 corresponding to knowledge 1, the quantization interval of attribute 2 of the product is quantization interval 2 corresponding to knowledge 2, and the scores corresponding to attribute 1 and attribute 2 of the product are scores s1And score s4The weights corresponding to the attribute 1 and the attribute 2 are a1And a2Then the score corresponding to the high-level concept of the product is a1*s1+a2*s4. Similarly, the score for each of the other products can be calculated in the same manner as described above.
In step 150, one or more target products to be recommended are obtained according to the scored magnitude relationship corresponding to the high-level concept of the plurality of products.
As shown in step 140, the score of each product can be obtained by calculating the weighted sum of the scores corresponding to the multiple low-level concepts corresponding to the high-level concept of each product, after the score is obtained, the scores can be ranked according to the descending order of the multiple products, and one or more products ranked in the top are recommended to the user.
It should be understood that after one or more products are recommended to the user, the satisfaction degree fed back by the user can be collected and used for adjusting the upper limit value and the lower limit value of the quantization interval corresponding to each attribute and the weight of each attribute.
One possible implementation is: the method comprises the steps of taking a concept set containing a plurality of low-level concepts and the satisfaction degree of corresponding user feedback as training samples, training a model by enabling the predicted satisfaction degree of the user feedback obtained by the model to be close to the satisfaction degree of real user feedback, and automatically adjusting the weight of each low-level concept and the quantization interval corresponding to each low-level concept so as to obtain the weight of each low-level concept and the quantization interval corresponding to each low-level concept.
The model may be implemented using, for example, XGBoost and LR algorithms.
It should be understood that other algorithms may be used in the model, and the same functions as those in the embodiments of the present application may be implemented, which is not limited by the embodiments of the present application.
Based on the technical scheme, the query information with certain ambiguity and uncertainty input by the user can be converted into the quantifiable weighted sum of the low-level concepts by quantifying the high-level concepts into the weighted sum of the associated low-level concepts, and the weights in the query information can be adjusted according to the satisfaction degree fed back by the user, so that the real expectation of the obtained conceptualized query result to the user is closer, the query precision is improved, and the query requirement of the user is met.
Fig. 2 is a schematic block diagram of a conceptualized query device provided in an embodiment of the present application. As shown in fig. 2, the apparatus 200 may include: an acquisition module 210 and a processing module 220. The obtaining module 210 may be configured to obtain a query statement, where the query statement includes a high-level concept; the processing module 220 may be configured to determine a plurality of low-level concepts associated with the high-level concept, each high-level concept being a weighted sum of the associated plurality of low-level concepts, the weight of each low-level concept being adjustable based on user feedback; obtaining at least one quantization interval of each low-level concept in a plurality of low-level concepts associated with the high-level concept and a score corresponding to each quantization interval, wherein the quantization interval corresponding to each low-level concept can be adjusted according to user feedback; calculating the score corresponding to each product in the high-level concepts according to the quantization intervals corresponding to the low-level concepts of each product in the plurality of products, the score corresponding to each quantization interval and the weights of the low-level concepts; and obtaining one or more target products to be recommended according to the size relation of the scores of the products corresponding to the high-level concepts.
Optionally, the processing module 220 may be further configured to search a conceptualized hierarchical database, in which a plurality of high-level concepts and their associated low-level concepts are pre-stored, for the plurality of low-level concepts associated with the high-level concept.
Optionally, the processing module 220 may be further configured to adjust the weight of each low-level concept and the quantization interval corresponding to each low-level concept according to the user feedback.
Optionally, the processing module 220 may be further configured to use a concept set including the plurality of low-level concepts and the satisfaction degree of the user feedback corresponding to the concept set as a training sample, train the model by making the predicted satisfaction degree of the user feedback obtained by the model approach the satisfaction degree of the real user feedback, and automatically adjust the weight of each low-level concept and the quantization interval corresponding to each low-level concept, so as to obtain the weight of each low-level concept and the quantization interval corresponding to each low-level concept.
It should be understood that the division of the modules in the embodiments of the present application is illustrative, and is only one logical function division, and there may be other division manners in actual implementation. In addition, functional modules in the embodiments of the present application may be integrated into one processor, may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
Fig. 3 is another schematic block diagram of a conceptualized query device provided by an embodiment of the present application. The device can be used for realizing the function of the conceptualized inquiry device in the method. Wherein the apparatus may be a system-on-a-chip. In the embodiment of the present application, the chip system may be composed of a chip, and may also include a chip and other discrete devices.
As shown in fig. 3, the apparatus 300 may include at least one processor 310 for implementing the functions of the conceptualized query apparatus in the method provided by the embodiment of the present application. Illustratively, the processor 310 may be operable to obtain a query statement, the query statement including a high-level concept; determining a plurality of lower-level concepts associated with the higher-level concept, each higher-level concept being a weighted sum of the associated plurality of lower-level concepts, the weight of each lower-level concept being adjustable according to user feedback; obtaining at least one quantization interval of each low-level concept in a plurality of low-level concepts associated with the high-level concept and a score corresponding to each quantization interval, wherein the quantization interval corresponding to each low-level concept can be adjusted according to user feedback; calculating the score corresponding to each product in the high-level concepts according to the quantization intervals corresponding to the low-level concepts of each product in the plurality of products, the score corresponding to each quantization interval and the weights of the low-level concepts; and obtaining one or more target products to be recommended according to the size relation of the scores of the products corresponding to the high-level concepts.
The apparatus 300 may also include at least one memory 320 for storing program instructions and/or data. The memory 320 is coupled to the processor 310. The coupling in the embodiments of the present application is an indirect coupling or a communication connection between devices, units or modules, and may be an electrical, mechanical or other form for information interaction between the devices, units or modules. The processor 310 may operate in conjunction with the memory 320. Processor 310 may execute program instructions stored in memory 320. At least one of the at least one memory may be included in the processor.
The apparatus 300 may also include a communication interface 330 for communicating with other devices over a transmission medium so that the apparatus used in the apparatus 300 may communicate with other devices. Illustratively, the communication interface 330 may be, for example, a transceiver, an interface, a bus, a circuit, or a device capable of performing a transceiving function. The processor 310 may utilize the communication interface 330 to send and receive data and/or information and to implement the methods performed by the conceptualized query device described in the corresponding embodiment of fig. 1.
The specific connection medium between the processor 310, the memory 320 and the communication interface 330 is not limited in the embodiments of the present application. In fig. 3, the processor 310, the memory 320, and the communication interface 330 are connected by a bus 340. The bus 340 is represented by a thick line in fig. 3, and the connection manner between other components is merely illustrative and not limited thereto. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 3, but this does not mean only one bus or one type of bus.
The present application further provides a computer program product, the computer program product comprising: a computer program (also referred to as code, or instructions), which when executed, causes a computer to perform the method of the embodiment shown in fig. 1.
The present application also provides a computer-readable storage medium having stored thereon a computer program (also referred to as code, or instructions). When executed, the computer program causes a computer to perform the method of the embodiment shown in fig. 1.
It should be understood that the processor in the embodiments of the present application may be an integrated circuit chip having signal processing capability. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
It will also be appreciated that the memory in the embodiments of the subject application can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. The non-volatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), double data rate SDRAM, enhanced SDRAM, SLDRAM, Synchronous Link DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
As used in this specification, the terms "unit," "module," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution.
Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps (step) described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application. In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
In the above embodiments, the functions of the functional units may be fully or partially implemented by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). The procedures or functions described in accordance with the embodiments of the present application are generated in whole or in part when the computer program instructions (programs) are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A conceptualized query method, comprising:
obtaining a query statement, wherein the query statement comprises a high-level concept;
determining a plurality of lower-level concepts associated with the higher-level concept, each higher-level concept being a weighted sum of the associated plurality of lower-level concepts, the weight of each lower-level concept being adjustable according to user feedback;
obtaining at least one quantization interval of each low-level concept in a plurality of low-level concepts associated with the high-level concept and a score corresponding to each quantization interval, wherein the quantization interval corresponding to each low-level concept can be adjusted according to user feedback;
calculating the score corresponding to each product in the high-level concepts according to the quantization intervals corresponding to the low-level concepts of each product in the plurality of products, the score corresponding to each quantization interval and the weights of the low-level concepts;
and obtaining one or more target products to be recommended according to the size relation of the scores of the products corresponding to the high-level concepts.
2. The method of claim 1, wherein the determining a plurality of lower-level concepts associated with the higher-level concept comprises:
and searching a plurality of low-level concepts related to the high-level concept in a conceptualized hierarchical database, wherein the conceptualized hierarchical database is prestored with the plurality of high-level concepts and the related low-level concepts.
3. The method of claim 1, wherein the weight of each low-level concept and the quantization interval to which each low-level concept corresponds are adjusted based on user feedback.
4. The method of claim 3, wherein the adjusting the weight of each low-level concept and the quantization interval to which each low-level concept corresponds according to the user feedback comprises:
and taking the concept set containing the plurality of low-level concepts and the satisfaction degree of the corresponding user feedback as a training sample, training the model by enabling the predicted satisfaction degree of the user feedback obtained by the model to be close to the satisfaction degree of the real user feedback, and automatically adjusting the weight of each low-level concept and the quantization interval corresponding to each low-level concept so as to obtain the weight of each low-level concept and the quantization interval corresponding to each low-level concept.
5. The method of claim 1, wherein the query statement is an SQL statement.
6. The method of claim 4, wherein the model comprises an extreme gradient boosting algorithm and a logistic regression algorithm.
7. A conceptualized query apparatus comprising means for implementing the method of any of claims 1-6.
8. A conceptualized query device comprising a processor and a memory; wherein,
the memory for storing program code;
the processor, configured to call the program code stored in the memory, and execute the method of any one of claims 1 to 6.
9. A computer-readable storage medium having stored therein instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 6.
10. A computer program product, comprising a computer program which, when run by a computer, causes the computer to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110683675.0A CN113297254A (en) | 2021-06-21 | 2021-06-21 | Conceptualization query method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110683675.0A CN113297254A (en) | 2021-06-21 | 2021-06-21 | Conceptualization query method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113297254A true CN113297254A (en) | 2021-08-24 |
Family
ID=77328868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110683675.0A Pending CN113297254A (en) | 2021-06-21 | 2021-06-21 | Conceptualization query method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113297254A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20240095283A1 (en) * | 2022-09-15 | 2024-03-21 | Relativity Oda Llc | Systems and methods for conceptual highlighting of document search results |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060015486A1 (en) * | 2004-07-13 | 2006-01-19 | International Business Machines Corporation | Document data retrieval and reporting |
| CN101067807A (en) * | 2007-05-24 | 2007-11-07 | 上海大学 | Text semantic visable representation and obtaining method |
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
| CN108228820A (en) * | 2017-12-30 | 2018-06-29 | 厦门太迪智能科技有限公司 | User's query intention understanding method, system and terminal |
-
2021
- 2021-06-21 CN CN202110683675.0A patent/CN113297254A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060015486A1 (en) * | 2004-07-13 | 2006-01-19 | International Business Machines Corporation | Document data retrieval and reporting |
| CN101067807A (en) * | 2007-05-24 | 2007-11-07 | 上海大学 | Text semantic visable representation and obtaining method |
| CN101334796A (en) * | 2008-02-29 | 2008-12-31 | 浙江师范大学 | Personalized and synergistic integration network multimedia search and enquiry method |
| CN108228820A (en) * | 2017-12-30 | 2018-06-29 | 厦门太迪智能科技有限公司 | User's query intention understanding method, system and terminal |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20240095283A1 (en) * | 2022-09-15 | 2024-03-21 | Relativity Oda Llc | Systems and methods for conceptual highlighting of document search results |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11782915B2 (en) | Searchable index | |
| US20220075670A1 (en) | Systems and methods for replacing sensitive data | |
| CN107436875B (en) | Text classification method and device | |
| US8332434B2 (en) | Method and system for finding appropriate semantic web ontology terms from words | |
| CN102479239A (en) | Method and device for per-storing RDF ternary data | |
| CN110019474B (en) | Automatic synonymy data association method and device in heterogeneous database and electronic equipment | |
| US10901993B2 (en) | Performing cache update adaptation | |
| CN103714098A (en) | Method and system used for sectioning data base | |
| CN114756607A (en) | Parameter configuration method and device | |
| CN113297254A (en) | Conceptualization query method and device | |
| JP7213890B2 (en) | Accelerated large-scale similarity computation | |
| CN116362589A (en) | Quality work assessment and evaluation method | |
| CN116383340A (en) | Information searching method, device, electronic equipment and storage medium | |
| CN113535938B (en) | Standard data construction method, system, equipment and medium based on content identification | |
| CN111539208B (en) | Sentence processing method and device, electronic device and readable storage medium | |
| CN112069164B (en) | Data query method, device, electronic equipment and computer readable storage medium | |
| CN114519105B (en) | Concept word determining method and device, electronic equipment and storage medium | |
| CN113420550B (en) | Keyword extraction method and device | |
| US20230297572A1 (en) | Cache update adaptation | |
| JP2018180866A (en) | Determination method, determination program and determination device | |
| CN110019289B (en) | Data query method and device and electronic equipment | |
| CN117389994A (en) | Project database construction method, device, equipment and storage medium | |
| CN117787704A (en) | Object evaluation method, device and storage medium | |
| CN117609428A (en) | Information recall method and related equipment | |
| CN116662304A (en) | Data migration method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |