CN114528371A - Text recommendation method based on human-computer interaction, storage medium and electronic device - Google Patents
Text recommendation method based on human-computer interaction, storage medium and electronic device Download PDFInfo
- Publication number
- CN114528371A CN114528371A CN202210036732.0A CN202210036732A CN114528371A CN 114528371 A CN114528371 A CN 114528371A CN 202210036732 A CN202210036732 A CN 202210036732A CN 114528371 A CN114528371 A CN 114528371A
- Authority
- CN
- China
- Prior art keywords
- recommendation
- preset
- human
- text
- matching
- 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
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a text recommendation method based on human-computer interaction, a storage medium and electronic equipment, wherein the text recommendation method based on human-computer interaction comprises the following steps: based on different preset recommendation modes, acquiring matching judgment data formed by a user aiming at each preset recommendation mode; adjusting the recommendation weight of each preset recommendation mode by using the matching judgment data; determining the recommendation contribution degree of each preset recommendation mode according to the recommendation weight; and updating the text recommendation modes according to the recommendation contribution degrees of all preset recommendation modes. In the human-computer interaction process, the invention dynamically adjusts the weight of each algorithm in the algorithm pool in real time according to the matching condition selected by the user, thereby being suitable for the generalized text matching scene.
Description
Technical Field
The invention belongs to the technical field of text matching, relates to a text recommendation method, and particularly relates to a text recommendation method based on human-computer interaction, a storage medium and an electronic device.
Background
In the field of medical informatization, data governance is an extremely important task. And establishing a mapping relation from source information (data before treatment) to target information (data after treatment) is an important link. Wherein, the establishment of the mapping relation is based on the matching of the text information.
In order to successfully complete the production work of matching a large amount of texts, two main ways are currently available: pure manual comparison and use of tools such as regular expressions or algorithms such as natural language processing.
Pure manual comparison refers to manually comparing source data with target data and filling a suitable target into a source data table, and has the problems that the overall task difficulty is increased along with the product of the source data scale and the target data scale, the pure manual work workload is large, the efficiency is low, if 300 pieces of source data are required to be matched with the target data, 500 pieces of candidate target data are required, the mapping relation of 300 × 500 to 150,000 needs to be checked by pure manual work, and the historical matching result is not fully utilized. Therefore, it is inefficient in service implementation.
The use of tools such as regular expressions or algorithms such as natural language processing means that rules are manually established, and the use of tool matching results or algorithm recommendation results has the problems that the information has high requirements on the accuracy of work, the tools or algorithms are difficult to achieve, and the risk is high. The application scenes are numerous, and the cost of independently developing the algorithm in each scene are very high. If the recommendation is not clearly judged to be correct, the user still needs to manually search for a large number of possible options. The historical matching result is not fully utilized, and the efficiency in service implementation is low.
Therefore, how to provide a text recommendation method, a storage medium and an electronic device based on human-computer interaction to solve the defects that the prior art cannot ensure recommendation accuracy while reducing human input and cost input becomes a technical problem to be urgently solved by technical staff in the field.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide a text recommendation method, a storage medium, and an electronic device based on human-computer interaction, which are used to solve the problem that the prior art cannot ensure recommendation accuracy while reducing human input and cost input.
In order to achieve the above and other related objects, an aspect of the present invention provides a text recommendation method based on human-computer interaction, where the text recommendation method based on human-computer interaction includes: based on different preset recommendation modes, acquiring matching judgment data formed by a user aiming at each preset recommendation mode; adjusting the recommendation weight of each preset recommendation mode by using the matching judgment data; determining the recommendation contribution degree of each preset recommendation mode according to the recommendation weight; and updating the text recommendation modes according to the recommendation contribution degrees of all preset recommendation modes.
In an embodiment of the present invention, the step of obtaining matching judgment data formed by the user for each of the preset recommendation manners based on different preset recommendation manners includes: determining a recommendation result given by each preset recommendation mode; and acquiring operation data which are judged to be matched or unmatched by the user according to the recommendation result.
In an embodiment of the present invention, the step of determining the recommendation result given by each of the preset recommendation manners includes: setting a matching degree threshold value; and taking the content with the matching degree higher than the threshold value of the matching degree recommended by each preset recommendation mode as the recommendation result.
In an embodiment of the invention, the step of adjusting the recommendation weight of each of the predetermined recommendation methods by using the matching determination data includes: analyzing the number of the recommendation results which are judged to be matched in the matching judgment data; and adjusting the recommendation weight of each preset recommendation mode according to the matching quantity.
In an embodiment of the present invention, the step of adjusting the recommendation weight of each of the preset recommendation manners according to the matching number includes: increasing the recommendation weight aiming at the preset recommendation modes with the matching number higher than or equal to the preset number; and aiming at the preset recommendation modes with the matching number lower than the preset number, the recommendation weight is reduced.
In an embodiment of the invention, before the adjusting of the recommendation weight, each of the predetermined recommendation modes is set as the same recommendation weight.
In an embodiment of the present invention, after the step of updating the text recommendation modes according to the recommendation contribution degrees of all preset recommendation modes, the text recommendation method based on human-computer interaction further includes: based on the updated text recommendation mode, acquiring the matching judgment data formed by the user; and iteratively updating the text recommendation mode through the continuously accumulated matching judgment data.
In an embodiment of the present invention, after the step of iteratively updating the text recommendation method, the text recommendation method based on human-computer interaction further includes: and in response to the accumulation times reaching the preset times, performing customized design aiming at the text recommendation mode of iterative update.
To achieve the above and other related objects, another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the text recommendation method based on human-computer interaction.
To achieve the above and other related objects, a final aspect of the present invention provides an electronic device, comprising: a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored by the memory so as to enable the electronic equipment to execute the text recommendation method based on human-computer interaction.
As described above, the text recommendation method, the storage medium, and the electronic device based on human-computer interaction according to the present invention have the following advantages:
(1) aiming at the problems of large workload and low efficiency of pure manual comparison, the algorithm is used for recommending the items to be matched, so that the search time wasted in the inferior matching items manually is reduced; and for auxiliary information such as recommendation degree, highlight of similar fields and the like provided during manual check, the decision cost is reduced.
(2) Aiming at the problem that historical matching results are not fully utilized, the method and the device fully utilize the existing matching data and dynamically adjust the weight of each algorithm in the algorithm pool in real time, so that the recommendation precision is improved.
(3) Aiming at the problems that the accuracy requirement is high and a pure algorithm or other tools are difficult to achieve, the method and the system ensure the final accuracy by human judgment by utilizing human-computer interaction.
(4) Aiming at the problems that a plurality of scenes are provided, and the cost of a tool and an algorithm for independently developing each scene is high, the invention provides a customized similarity recommendation algorithm for customized scenes; and for an un-customized scene, a reusable general algorithm and a front-back end component are abstracted, and the expansion efficiency is improved. The general algorithm means that each scene is multiplexed with a set of calculation flow. If the algorithm is not general, the preprocessing components required by the algorithm A and the algorithm B are different, and the front-end presentation forms are also different. The invention can reuse the calculation process, thereby correspondingly improving the expansion efficiency or the development efficiency.
Drawings
Fig. 1 is a schematic flow chart illustrating a text recommendation method based on human-computer interaction according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating an application of the text recommendation method based on human-computer interaction according to an embodiment of the present invention.
Fig. 3 is a schematic diagram illustrating department matching in an embodiment of the text recommendation method based on human-computer interaction according to the present invention.
Fig. 4 is a schematic diagram illustrating human interaction of the text recommendation method based on human-computer interaction according to an embodiment of the invention.
FIG. 5 is a schematic diagram of laboratory test terms according to an embodiment of the human-computer interaction based text recommendation method of the present invention.
Fig. 6 is a schematic diagram illustrating a database schema mapping of the human-computer interaction based text recommendation method in an embodiment of the invention.
Fig. 7 is a schematic structural connection diagram of an electronic device according to an embodiment of the invention.
Description of the element reference numerals
7 electronic device
71 processor
72 memory
S11-S14
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of each component in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.
The text recommendation method based on human-computer interaction, the storage medium and the electronic equipment dynamically adjust the weight of each algorithm in the algorithm pool in real time according to the matching condition selected by the user in the human-computer interaction process, so that the text recommendation method based on human-computer interaction, the storage medium and the electronic equipment are suitable for a generalized text matching scene.
The principle and implementation of the text recommendation method, the storage medium and the electronic device based on human-computer interaction according to the present embodiment will be described in detail below with reference to fig. 1 to 7, so that those skilled in the art can understand the text recommendation method, the storage medium and the electronic device based on human-computer interaction without creative work.
Please refer to fig. 1, which is a schematic flowchart illustrating a text recommendation method based on human-computer interaction according to an embodiment of the present invention.
As shown in fig. 1, the text recommendation method based on human-computer interaction specifically includes the following steps:
and S11, acquiring matching judgment data formed by the user aiming at each preset recommendation mode based on different preset recommendation modes.
Please refer to fig. 2, which is a flowchart illustrating an application of the text recommendation method based on human-computer interaction according to an embodiment of the present invention. As shown in fig. 2, the initial predetermined recommendation method means that at the beginning of use, since there is not too much matched data as support, a set of predetermined general recommendation algorithms, such as general a, general B, and general C in fig. 2, are provided in the algorithm pool of the system. The set of preset general recommendation algorithms comprises a plurality of recommendation algorithms. In practical application, the general recommendation algorithm refers to various existing text similarity algorithms which can calculate the similarity between two sections of texts according to the literal meanings of the two sections of texts. The text similarity algorithms do not need to rely on a large amount of linguistic data, and are suitable for being used as a bottom-preserving algorithm in a cold start stage due to high universality and generalization. For example, a text similarity algorithm based on an edit distance, a text similarity algorithm based on a cosine distance, and a text similarity algorithm based on an open source common word vector, the three algorithms are different in implementation method, and the accuracy of each algorithm is different under different scenes.
In one embodiment, S11 specifically includes the following steps:
(1) and determining a recommendation result given by each preset recommendation mode.
Specifically, a matching degree threshold value is set; and taking the content with the matching degree higher than the threshold value of the matching degree recommended by each preset recommendation mode as the recommendation result.
(2) And acquiring operation data which are judged to be matched or unmatched by the user according to the recommendation result.
Please refer to fig. 3, which is a diagram illustrating department matching in an embodiment of the text recommendation method based on human-computer interaction according to the present invention. As shown in fig. 3, in the matching application scenario of the department, the old architecture is: the clinic of the department of cardiology, coronary heart disease and the clinic of the oncology are mapped to the cardiovascular medical center and the clinic of the oncology is mapped to the clinical oncology center in the specific mapping process.
Please refer to fig. 4, which is a schematic diagram illustrating human interaction in an embodiment of a text recommendation method based on human-computer interaction according to the present invention. As shown in fig. 4, in the initial stage, the system may preset a weight for each recommendation algorithm, and finally recommend a plurality of matching options for the user to refer to, and the recommended number may be freely defined by the user. The user picks the matching item within the recommendation provided by the algorithm. As in fig. 4, text matching the cardiovascular medical center is presented, including a cardiology clinic with a match of 0.9, a coronary heart disease clinic with a match of 0.7, and an angiography center with a match of 0.6. And for each recommendation result, a check box is arranged behind the recommendation result, if the user considers that the presented recommendation item is matched with the cardiovascular medicine center, the check box checks the matching in the first box, and if the user considers that the presented recommendation item is not matched with the cardiovascular medicine center, the check box checks the non-matching in the second box.
And S12, adjusting the recommendation weight of each preset recommendation mode by using the matching judgment data.
In one embodiment, S12 specifically includes the following steps:
(1) and analyzing the number of the recommendation results which are judged to be matched in the matching judgment data.
Assuming that there are currently three algorithms, A, B, C, their initial weights are 1: 1: 1, three text results are recommended for each algorithm, whereby a total of 9 are recommended. Over time, statistical findings: the user selects more recommended texts, namely the number of matched texts selected by the user aiming at the texts recommended by the algorithm A is more; the text recommended by the user for selecting C is fewer, namely the number of the matched text recommended by the algorithm C is larger.
(2) And adjusting the recommendation weight of each preset recommendation mode according to the matching quantity.
Specifically, for a preset recommendation mode in which the matching number is higher than or equal to a preset number, the recommendation weight is increased; and aiming at the preset recommendation modes with the matching number lower than the preset number, the recommendation weight is reduced.
According to the three algorithms described above, A, B, C, the weights of algorithm a, algorithm B, and algorithm C may be adjusted to 5: 3: 1. therefore, according to the weight ratio, when A recommends 5 text results, B recommends 3 text results, and C recommends 1 text result.
Further, before the recommendation weight is adjusted, each of the preset recommendation manners is set to be the same recommendation weight. In different embodiments, each of the predetermined recommendation manners may be set as a different recommendation weight. The developer will use some test texts during development, and preset according to the effect of each algorithm on the test texts. The well-developed algorithm weights will also be high.
And S13, determining the recommendation contribution degree of each preset recommendation mode according to the recommendation weight.
Specifically, according to the three algorithms, A, B, C, the text recommended by the user selection a is more, and the text recommended by the user selection C is less, that is, the recommendation contribution degree of the preset recommendation method algorithm a is higher than that of the preset recommendation method algorithm C.
And S14, updating the text recommendation modes according to the recommendation contribution degrees of all the preset recommendation modes.
In an embodiment, after step S14, the method for text recommendation based on human-computer interaction further includes:
based on the updated text recommendation mode, acquiring the matching judgment data formed by the user; and iteratively updating the text recommendation mode through the continuously accumulated matching judgment data.
In an embodiment, after the step of iteratively updating the text recommendation method, the text recommendation method based on human-computer interaction further includes: and in response to the accumulated times reaching the preset times, performing customized design on the iteratively updated text recommendation mode.
Specifically, after the matching data is accumulated to a certain extent, a developer of the system customizes and develops a recommendation algorithm according to a certain scene, and then adds the recommendation algorithm into the system where the whole recommendation method is located, so that the recommendation matching precision is improved. Continuing with FIG. 2, the custom algorithm is generated in the algorithm pool: custom A, custom B, and custom C.
In practical applications, the user's choice of whether the text matches is accumulated, for example, the user selects "match" between "sepsis" and "mismatch" between "hypertension" and "hyperlipidemia". When the data accumulation amount of the match and the mismatch is enough for the developer to model the machine learning algorithm, for example, the number is larger than 1000 or other number threshold designed according to the actual application scenario. For some scenes, the contained texts cannot be well matched by using universal literal similarity, for example, in a checking scene, the 'white band' and the 'vaginal secretion' have the same meaning, but the high similarity is difficult to achieve by simply looking at the literal, so that the matching of the texts needs to be customized by means of medical term normalization and the like, and a corresponding algorithm is customized.
Please refer to fig. 5, which is a schematic diagram of laboratory test terms according to an embodiment of the human-computer interaction based text recommendation method of the present invention. As shown in FIG. 5, the human-machine interaction based text recommendation method of the present invention is applied to the control of laboratory test terms. Item name item _ name "25 hydroxyvitamin D3 measurement" -sample name sample _ name "venous blood" -numerical value type value _ type "num" and item name item _ name "25 hydroxyvitamin D3 measurement" -sample name sample _ name "peripheral blood" -numerical value type value _ type "num", all mapped to the same "serum 25-hydroxyvitamin D3 measurement quantification" according to the higher degree of matching. In practical applications, matching for multiple fields of the item name item _ name, the sample name sample _ name and the value type value _ type may be divided into multiple single field matches, and mapping is performed by using the matching degree obtained by each field, so that a one-to-many situation occurs. And checking the mapping of the two data through human-computer interaction, and further adjusting the recommendation weight of each preset recommendation mode in a comparison scene of laboratory test terms according to matching judgment data of a user.
Please refer to fig. 6, which is a schematic diagram illustrating a database schema mapping of the human-computer interaction based text recommendation method according to an embodiment of the invention. As shown in fig. 6, the last name "-type" string "of the column name" family _ name "-annotation" patient and the first name "-type" string "of the column name" -annotation "patient are both mapped and matched to the name" -type "string" of the same column name "patient _ name" -annotation "patient according to a higher matching degree; the column name "age" -annotation "patient age" -type "integer", is mapped and matched to a column name "patient _ age" -annotation "age" -type "integer" according to a higher degree of matching; column name "sx _ kssj" -annotating "operation start time" -type "time" and column name "sx _ jssj" -annotating "operation end time" -type "time", according to the higher matching degree, all mapping and matching to the same column name "operation _ duration" -annotation "operation time length, and determining" -type "time" by operation start time and operation end time interval. In practical applications, matching for multiple fields of column names, comments and types can be divided into multiple single field matching, and the matching degree obtained by each field is used for mapping, so that a one-to-many situation occurs. And checking the mapping of the two data through human-computer interaction, and further judging the recommendation weight of each preset recommendation mode in the mapping scene when the data is adjusted in the database according to the matching of the user.
The protection scope of the text recommendation method based on human-computer interaction according to the present invention is not limited to the execution sequence of the steps listed in this embodiment, and all the schemes of adding, subtracting, and replacing the steps in the prior art according to the principle of the present invention are included in the protection scope of the present invention.
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the human-computer interaction based text recommendation method.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned computer-readable storage media comprise: various computer storage media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Please refer to fig. 7, which is a schematic structural connection diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 7, the present embodiment provides an electronic device 7, which specifically includes: a processor 71 and a memory 72; the memory 72 is configured to store a computer program, and the processor 71 is configured to execute the computer program stored in the memory 72, so as to enable the electronic device 7 to execute the steps of the human-computer interaction based text recommendation method.
The Processor 71 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be 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, discrete hardware component.
The Memory 72 may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
In practical applications, the electronic device may be a computer including all or a portion of the components of memory, a memory controller, one or more processing units (CPUs), peripheral interfaces, RF circuits, audio circuits, speakers, microphones, input/output (I/O) subsystems, a display screen, other output or control devices, and external ports; the computer includes, but is not limited to, Personal computers such as desktop computers, notebook computers, tablet computers, smart phones, Personal Digital Assistants (PDAs), and the like. In other embodiments, the electronic device may also be a server, where the server may be arranged on one or more entity servers according to various factors such as functions and loads, or may be a cloud server formed by a distributed or centralized server cluster, which is not limited in this embodiment.
In summary, the text recommendation method, the storage medium and the electronic device based on human-computer interaction provided by the invention aim at the problems of large workload and low efficiency of pure manual comparison, and the method and the device provided by the invention are used for recommending the item to be matched by using an algorithm, so that the search time wasted in the poor-quality matching item by manual work is reduced; and for auxiliary information such as recommendation degree, highlight of similar fields and the like provided during manual check, the decision cost is reduced. Aiming at the problem that historical matching results are not fully utilized, the method and the device fully utilize the existing matching data and dynamically adjust the weight of each algorithm in the algorithm pool in real time, so that the recommendation precision is improved. Aiming at the problems that the accuracy requirement is high and a pure algorithm or other tools are difficult to achieve, the method and the system ensure the final accuracy by human judgment by utilizing human-computer interaction. Aiming at the problems that a plurality of scenes are provided, and the cost of a tool and an algorithm for independently developing each scene is high, the invention provides a customized similarity recommendation algorithm for customized scenes; and for an un-customized scene, a reusable general algorithm and a front-back end component are abstracted, and the expansion efficiency is improved. The invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A text recommendation method based on human-computer interaction is characterized by comprising the following steps:
based on different preset recommendation modes, acquiring matching judgment data formed by a user aiming at each preset recommendation mode;
adjusting the recommendation weight of each preset recommendation mode by using the matching judgment data;
determining the recommendation contribution degree of each preset recommendation mode according to the recommendation weight;
and updating the text recommendation modes according to the recommendation contribution degrees of all preset recommendation modes.
2. The human-computer interaction based text recommendation method according to claim 1, wherein the step of obtaining matching judgment data formed by the user for each preset recommendation mode based on different preset recommendation modes comprises:
determining a recommendation result given by each preset recommendation mode;
and acquiring operation data which are judged to be matched or unmatched by the user according to the recommendation result.
3. The human-computer interaction based text recommendation method according to claim 2, wherein the step of determining the recommendation result given by each of the preset recommendation modes comprises:
setting a matching degree threshold value;
and taking the content with the matching degree higher than the threshold value of the matching degree recommended by each preset recommendation mode as the recommendation result.
4. The human-computer interaction based text recommendation method according to claim 2, wherein the step of adjusting the recommendation weight of each of the preset recommendation modes by using the matching decision data comprises:
analyzing the number of the recommendation results which are judged to be matched in the matching judgment data;
and adjusting the recommendation weight of each preset recommendation mode according to the matching quantity.
5. The human-computer interaction based text recommendation method according to claim 4, wherein the step of adjusting the recommendation weight of each of the preset recommendation modes according to the matching number comprises:
increasing the recommendation weight aiming at the preset recommendation modes with the matching number higher than or equal to the preset number;
and aiming at the preset recommendation modes with the matching number lower than the preset number, the recommendation weight is reduced.
6. The human-computer interaction based text recommendation method according to claim 1, wherein:
before the recommendation weight is adjusted, setting each preset recommendation mode as the same recommendation weight.
7. The human-computer interaction based text recommendation method according to claim 1, wherein after the step of updating the text recommendation modes according to the recommendation contribution degrees of all the preset recommendation modes, the human-computer interaction based text recommendation method further comprises:
based on the updated text recommendation mode, acquiring the matching judgment data formed by the user;
and iteratively updating the text recommendation mode through the continuously accumulated matching judgment data.
8. The human-computer interaction based text recommendation method according to claim 7, wherein after the step of iteratively updating the text recommendation manner, the human-computer interaction based text recommendation method further comprises:
and in response to the accumulated times reaching the preset times, performing customized design on the iteratively updated text recommendation mode.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the human-computer-interaction-based text recommendation method according to any one of claims 1 to 8.
10. An electronic device, comprising: a processor and a memory;
the memory is used for storing a computer program, and the processor is used for executing the computer program stored by the memory to enable the electronic equipment to execute the text recommendation method based on human-computer interaction according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210036732.0A CN114528371A (en) | 2022-01-13 | 2022-01-13 | Text recommendation method based on human-computer interaction, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210036732.0A CN114528371A (en) | 2022-01-13 | 2022-01-13 | Text recommendation method based on human-computer interaction, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114528371A true CN114528371A (en) | 2022-05-24 |
Family
ID=81620138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210036732.0A Pending CN114528371A (en) | 2022-01-13 | 2022-01-13 | Text recommendation method based on human-computer interaction, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114528371A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090893A (en) * | 2013-12-13 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method, device and system for optimizing recommendation algorithms |
| US20160162974A1 (en) * | 2014-12-08 | 2016-06-09 | Lg Cns Co., Ltd. | Personalized recommendation method and system, and computer-readable record medium |
| CN105913286A (en) * | 2016-05-16 | 2016-08-31 | 达而观信息科技（上海）有限公司 | Method for automatically integrating various kinds of personalized recommendation models |
| KR20170090562A (en) * | 2016-01-28 | 2017-08-08 | 주식회사 대구닷컴 | Personalized recommendation system and its method using multiple algorithms and self-learning function |
| CN107133836A (en) * | 2017-03-22 | 2017-09-05 | 无锡中科富农物联科技有限公司 | A kind of adaptive weighting combined recommendation algorithm |
| CN112633321A (en) * | 2020-11-26 | 2021-04-09 | 北京瑞友科技股份有限公司 | Artificial intelligence recommendation system and method |
-
2022
- 2022-01-13 CN CN202210036732.0A patent/CN114528371A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090893A (en) * | 2013-12-13 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method, device and system for optimizing recommendation algorithms |
| US20160162974A1 (en) * | 2014-12-08 | 2016-06-09 | Lg Cns Co., Ltd. | Personalized recommendation method and system, and computer-readable record medium |
| KR20170090562A (en) * | 2016-01-28 | 2017-08-08 | 주식회사 대구닷컴 | Personalized recommendation system and its method using multiple algorithms and self-learning function |
| CN105913286A (en) * | 2016-05-16 | 2016-08-31 | 达而观信息科技（上海）有限公司 | Method for automatically integrating various kinds of personalized recommendation models |
| CN107133836A (en) * | 2017-03-22 | 2017-09-05 | 无锡中科富农物联科技有限公司 | A kind of adaptive weighting combined recommendation algorithm |
| CN112633321A (en) * | 2020-11-26 | 2021-04-09 | 北京瑞友科技股份有限公司 | Artificial intelligence recommendation system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177231A (en) | Report generation method and report generation device | |
| CN110517785A (en) | Lookup method, device and the equipment of similar case | |
| CN108701250A (en) | Data fixed point method and apparatus | |
| US20180107654A1 (en) | Method and apparatus for managing synonymous items based on similarity analysis | |
| US20210056129A1 (en) | Mapping of Topics within a Domain Based on Terms Associated with the Topics | |
| CN109918394A (en) | Data query method, system, computer installation and computer readable storage medium | |
| US11262898B2 (en) | Visual context in dataflows | |
| US20100325125A1 (en) | Media recommendations | |
| WO2019123703A1 (en) | Data analysis assistance device, data analysis assistance method, and data analysis assistance program | |
| US10572881B2 (en) | Applying entity search techniques to expedite entitlement resolution in support services | |
| US20140324839A1 (en) | Determining candidate scripts from a catalog of scripts | |
| CN116168848A (en) | Drug information matching method and device based on Faiss algorithm | |
| CN113254673B (en) | Data management method, system, equipment and medium based on knowledge graph | |
| US20220335315A1 (en) | Application of local interpretable model-agnostic explanations on decision systems without training data | |
| CN104461558B (en) | A kind of personalized task recommendation method of the software-oriented modification based on association's related subject model | |
| US10353932B2 (en) | Text processing method, system and computer program | |
| KR102153259B1 (en) | Data domain recommendation method and method for constructing integrated data repository management system using recommended domain | |
| CN114528371A (en) | Text recommendation method based on human-computer interaction, storage medium and electronic device | |
| CN109871540A (en) | A kind of calculation method and relevant device of text similarity | |
| US20210357372A1 (en) | Data analysis assistance device, data analysis assistance method, and data analysis assistance program | |
| US11042706B2 (en) | Natural language skill generation for digital assistants | |
| US8712995B2 (en) | Scoring records for sorting by user-specific weights based on relative importance | |
| CN114661751B (en) | Data production method, device, system, equipment and medium based on SQL (structured query language) knowledge base | |
| WO2019236338A1 (en) | Computerized relevance scoring engine for identifying potential investors for a new business entity | |
| CN114547085B (en) | Data processing method and device, electronic 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 |