CN106095941B - Big data knowledge base-based solution recommendation method and system - Google Patents
Big data knowledge base-based solution recommendation method and system Download PDFInfo
- Publication number
- CN106095941B CN106095941B CN201610416286.0A CN201610416286A CN106095941B CN 106095941 B CN106095941 B CN 106095941B CN 201610416286 A CN201610416286 A CN 201610416286A CN 106095941 B CN106095941 B CN 106095941B
- Authority
- CN
- China
- Prior art keywords
- solution
- information
- problem information
- question information
- 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.)
- Active
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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a solution recommendation method, which comprises the following steps: acquiring problem information of a user, and taking the problem information of the user as first problem information; matching the first question information with each question information in a knowledge base, and determining second question information matched with the first question information; acquiring a solution corresponding to the second problem information; recommending the acquired solution to a user corresponding to the first problem information. The timeliness and the convenience of obtaining the solution corresponding to the problem information are achieved, and the recommended solution is more reliable because the method and the system do not depend on the subjective experience of an individual any more and are based on the objective historical data of the problem. In addition, a solution recommendation system is also provided.
Description
Technical Field
The invention relates to the field of computer processing, in particular to a solution recommendation method and system based on a big data knowledge base.
Background
At present, when people meet problems which cannot be solved by themselves in life, people generally consult through telephones or related persons who find experience face to face, but because personal knowledge and experience are often limited, if the people only depend on subjective experience and theoretical knowledge of the related persons, the problems of people cannot be solved effectively in many times, once the consulted related persons give wrong solutions due to personal cognition errors, the problems can be solved by people, and in addition, the problems are solved by people adversely affected, and a long-time waiting process is often needed when people consult the solutions. The conventional method therefore provides a solution with poor reliability and timeliness.
Disclosure of Invention
Based on the above, in order to solve the above problems, a reliable and fast solution recommendation method and system based on big data are provided.
A solution recommendation method, the method comprising: the method comprises the steps of obtaining problem information of a user, taking the problem information of the user as first problem information, matching the first problem information with each problem information in a knowledge base, determining second problem information matched with the first problem information, obtaining a solution corresponding to the second problem information, and recommending the obtained solution to the user corresponding to the first problem information.
In one embodiment, before the step of obtaining the question information of the user, the method further includes: establishing a knowledge base, wherein the knowledge base comprises a plurality of solution cases, and the solution cases comprise problem information and solution schemes and fractional values of solution effects corresponding to the problem information.
In one embodiment, the step of matching the first question information with each question information in a knowledge base and determining the second question information matching the first question information includes: matching the first problem information with each problem information in a knowledge base, obtaining a problem information set with the matching degree larger than a preset threshold value, searching a score value of a solving effect corresponding to each problem information in the problem information set, and taking the problem information corresponding to the solving effect with the largest score value as second problem information matched with the first problem information.
In one embodiment, the step of matching the first question information with each question information in a knowledge base and determining the second question information matching the first question information includes: matching the first problem information with each problem information in a knowledge base, acquiring a problem information set with the matching degree larger than a preset threshold value, searching a score value of a solving effect corresponding to each problem information in the problem information set, calculating the matching priority of each problem information according to the matching degree of each problem information in the problem information set and the score value of the solving effect corresponding to each problem information, taking the maximum matching priority obtained through calculation as a first matching priority, and taking the problem information corresponding to the first matching priority as second problem information matched with the first problem information.
In one embodiment, the method further comprises: obtaining feedback of a user on the solution, determining a score value of a solution effect corresponding to the solution according to the feedback, adding the first problem information, the recommended solution and the score value of the solution effect into the knowledge base as a solution case, and forming a big data knowledge base when the number of the solution cases in the knowledge base reaches a first preset threshold value.
A solution recommendation system, the system comprising: the system comprises a question information acquisition module, a question information processing module and a question information processing module, wherein the question information acquisition module is used for acquiring question information of a user and taking the question information of the user as first question information; the determining module is used for matching the first question information with each question information in a knowledge base and determining second question information matched with the first question information; a solution obtaining module, configured to obtain a solution corresponding to the second problem information; and the recommending module is used for recommending the acquired solution to the user corresponding to the first problem information.
In one embodiment, the system further comprises: the system comprises an establishing module and a judging module, wherein the establishing module is used for establishing a knowledge base, the knowledge base comprises a plurality of solution cases, and the solution cases comprise problem information, solutions corresponding to the problem information and fraction values of solution effects.
In one embodiment, the determining module comprises: the first acquisition unit is used for matching the first question information with each question information in a knowledge base and acquiring a question information set with the matching degree larger than a preset threshold value; the first searching unit is used for searching a score value of a solving effect corresponding to each problem information in the problem information set; and the first matching unit is used for taking the problem information corresponding to the solution effect with the maximum score value as the second problem information matched with the first problem information.
In one embodiment, the determining module comprises: the second acquisition unit is used for matching the first question information with each question information in a knowledge base and acquiring a question information set with the matching degree larger than a preset threshold value; the second searching unit is used for searching a score value of a solving effect corresponding to each problem information in the problem information set; a calculating unit, configured to calculate a matching priority of each piece of problem information according to the matching degree of each piece of problem information in the problem information set and a score value of a solution effect corresponding to each piece of problem information, and use a maximum matching priority obtained through calculation as a first matching priority; and the second matching unit is used for taking the question information corresponding to the first matching priority as second question information matched with the first question information.
In one embodiment, the system further comprises: the feedback module is used for acquiring feedback of a user on the solution and determining a score value of a solution effect corresponding to the solution according to the feedback; and the adding module is used for adding the first problem information, the recommended solutions and the score values of the solution effects into the knowledge base as a solution case, and when the number of the solution cases in the knowledge base reaches a first preset threshold value, a big data knowledge base is formed.
According to the solution recommendation method and system, the problem information of the user is firstly acquired and is used as the first problem information, then the first problem information is matched with each problem information in the knowledge base, the second problem information matched with the first problem information is determined, then the solution corresponding to the second problem information is acquired, and the acquired solution is recommended to the user. According to the solution recommending method and system, the problem information of the user is matched with the problem information in the knowledge base based on the big data, the solution which can solve the problem of the user most is determined by determining the second problem information matched with the first problem information, and then the found solution is recommended to the user, so that the timeliness and convenience of obtaining the solution corresponding to the problem information are achieved, and the method and the system do not depend on the subjective experience of the user any more but according to the objective historical data of the problem, so that the recommended solution is more reliable.
Drawings
FIG. 1 is a schematic flow chart diagram of a solution recommendation method in one embodiment;
FIG. 2 is a flow diagram illustrating a method for determining second issue information that matches first issue information, according to one embodiment;
FIG. 3 is a flowchart illustrating a method for determining second question information that matches the first question information in another embodiment;
FIG. 4 is a flowchart illustrating a solution recommendation method according to another embodiment;
FIG. 5 is a block diagram of the architecture of the solution recommendation system in one embodiment;
FIG. 6 is a block diagram showing the construction of a solution recommending system in another embodiment;
FIG. 7 is a block diagram of the structure of a determination module in one embodiment;
FIG. 8 is a block diagram of the structure of a determination module in another embodiment;
fig. 9 is a block diagram showing the structure of a solution recommendation system in still another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the following detailed description of the embodiments of the method and system for recommending a solution based on a knowledge base according to the present invention is provided by way of example and with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in FIG. 1, in one embodiment, a solution recommendation method is presented, the method comprising the steps of:
In this embodiment, the user question information may be obtained through the terminal, for example, the user question information may be input through the terminal. The terminal can be an electronic device capable of inputting problem information, such as a smart phone, a tablet computer, a notebook computer and wearable intelligent equipment. Specifically, a user problem management system can be operated on the terminal, and problem information of the user can be input through the system. The problem information that can be entered includes, but is not limited to, daily problems, professional problems, and the like.
And 104, matching the first question information with each question information in the knowledge base, and determining second question information matched with the first question information.
Specifically, the first question information is matched with each question information in the knowledge base, the matching degree of each question information and the first question information is calculated respectively, and the question information with the largest matching degree obtained through calculation can be used as the second question information matched with the first question information. In one embodiment, first, the matching degree of each problem information and the first problem information is calculated, then all the problem information with the matching degree larger than a preset threshold (for example, the threshold is set to be 0.8) are combined into a set, or the calculated matching degrees are smoothly arranged from large to small, then the problem information corresponding to the matching degrees arranged in the front (for example, the first 10) is selected to form a problem information set, then the score value of the solution effect corresponding to each problem information in the set is obtained, and the problem information corresponding to the solution effect with the largest score value is used as the second problem information matched with the first problem information. In another embodiment, first, a matching degree of each problem information and first problem information is calculated, then a problem information set with the matching degree larger than a preset threshold value is obtained, then a score value of a solution effect corresponding to each problem information in the problem information set is obtained, finally, a matching priority of each problem information is calculated according to the obtained matching degree of each problem information and the score value of the solution effect corresponding to each problem information, the calculated maximum matching priority is used as a first matching priority, and the problem information corresponding to the first matching priority is used as second problem information matched with the first problem information.
And 106, acquiring a solution corresponding to the second problem information.
Specifically, a large number of solution cases are pre-stored in the knowledge base, and each solution case includes problem information, and a solution and a score value of a solution effect corresponding to the problem information. Wherein, the score value of the solution reflects the quality of the solution, and the higher the score value is, the better the solution is. And after second problem information matched with the first problem information is obtained through calculation, a solution corresponding to the second problem information is obtained. If the first question information matches the second question information, indicating that the question information of both are similar or identical, then the solutions will be most similar or identical. Therefore, after the solution corresponding to the second problem information is obtained, the obtained solution is recommended to the user corresponding to the first problem information, and the user is further helped to answer questions.
And step 108, recommending the acquired solution to a user corresponding to the first problem information.
Specifically, the solution matching the acquired problem information of the user may be recommended to the user. The information of the solution can be pushed to the user through the network, can also be sent to a terminal corresponding to the user in a short message mode, and can also be sent to the user in a mail mode and the like. After the user receives the question information aiming at the user, namely the solution of the first problem information, the user can grade the solution according to the solution effect of the solution, the grade of the user is used as a score value of the solution effect corresponding to the solution, and then the first problem information, the solution recommended for the first problem information and the score value of the solution effect are used as a new solution case to be added into the knowledge base, so that the knowledge base is gradually improved.
In this embodiment, the problem information of the user is first obtained and used as first problem information, then the first problem information is matched with each problem information in the knowledge base, second problem information matched with the first problem information is determined, then a solution corresponding to the second problem information is obtained, and the obtained solution is recommended to the user. According to the solution recommending method, the problem information of the user is matched with the problem information in the knowledge base based on the big data, the second problem information matched with the first problem information is determined, so that the solution which can solve the problem of the user most can be determined, the found solution is recommended to the user, timeliness and convenience in obtaining the solution corresponding to the problem information are achieved, and the method and the system do not depend on personal subjective experience any more but are based on objective historical data of solving the problem, so that the recommended solution is more reliable.
In one embodiment, before the step of obtaining the question information of the user, the method further comprises: and establishing a knowledge base, wherein the knowledge base comprises a plurality of solution cases, and each solution case comprises the problem information and the solution and the fraction value of the solution effect corresponding to the problem information.
In this embodiment, a knowledge base is pre-established, the knowledge base is a big data knowledge base, it can be understood that a large number of solution cases exist in the knowledge base, each solution case includes problem information, a solution corresponding to the problem information, and a score value of a solution effect, the score value of the solution effect is used for reflecting the quality of the solution effect corresponding to the solution, the larger the score value is, the better the solution effect is, and conversely, the smaller the score value is, the worse the solution effect is. The score value is derived from the user's feedback on the solution, which can be achieved by scoring. The big data knowledge base in the embodiment of the invention is a big data knowledge base of the solution, the big data knowledge base of the solution is a structured, easy-to-operate, easy-to-use and fully organized knowledge cluster in knowledge engineering, and can adopt a professional knowledge representation mode to store, organize, manage and use interconnected knowledge slice sets in a computer memory according to the requirement of solving problems in the professional field. These pieces of knowledge include theoretical knowledge and factual data related to the field of expertise. For example, the relevant definition, theorems and operation rules, common sense knowledge, etc. in the professional field.
As shown in fig. 2, in one embodiment, matching the first question information with each question information in the knowledge base, and determining the second question information matching the first question information includes:
and 104a, matching the first question information with each question information in the knowledge base to obtain a question information set with the matching degree larger than a preset threshold value.
In this embodiment, the first problem information is matched with each problem information in the knowledge base one by one, the matching degree between each problem information in the knowledge base and the first problem information is calculated, then all the problem information larger than a preset threshold value is acquired according to the calculated matching degree, and all the acquired problem information is combined into a problem information set. There are various methods for calculating the matching degree, for example, matching may be performed according to keywords, and the number of successfully matched keywords is used as the matching degree. When matching the keywords, the keywords are used as character strings, and the precise matching of the character strings and the fuzzy matching of the character strings can be adopted. Specifically, keywords in the first question information are extracted as first keywords, and then the first keywords are used for matching with question information in a knowledge base, the more the number of matched keywords is, the greater the corresponding matching degree is, and all question information with the matching degree greater than a preset threshold (for example, 80%) is collected to form a question information set. In another embodiment, keywords are extracted from the acquired problem information of the user as first keywords, keywords are extracted from the problem information in the solution cases in the big data knowledge base as second keywords, the matching between the problem information of the user and each problem information in the knowledge base is actually the matching between the first keywords and the second keywords, and the ratio of the number of successfully matched keywords in the number of first keywords is used as the corresponding matching degree. For example, if the number of times of extracting the first keyword from the question information of the user is 10, if 7 keywords in a certain question information in the database are successfully matched with the first keyword, the matching degree of the question information and the first question information is 70%.
And 104b, searching a score value of a solution effect corresponding to each problem information in the problem information set.
In this embodiment, after the problem information set with the matching degree greater than the preset threshold is obtained, a score value of a solution effect corresponding to each problem information in the problem information set is further obtained, and the larger the score value is, the better the solution effect is. Specifically, for example, a problem information set with a matching degree greater than 90% is first obtained, problem information in the problem information set is basically similar to first problem information, and then a score value of a solution effect corresponding to each problem information in the problem information set needs to be obtained. The larger the score value is, the better the solution effect is, and the more the corresponding solution meets the requirements of the user.
And step 104c, using the problem information corresponding to the solution effect with the maximum score value as the second problem information matched with the first problem information.
In this embodiment, after the score value of the solution effect corresponding to each problem information in the problem information set is obtained, the score value of the solution effect of each problem information is compared, the problem information corresponding to the solution effect with the largest score value is used as the second problem information matched with the first problem information, and then the solution corresponding to the second problem information is obtained, and the solution is recommended to the user corresponding to the first problem information.
As shown in fig. 3, in one embodiment, matching the first question information with each question information in the knowledge base, and determining the second question information matching the first question information includes:
and 104A, matching the first question information with each question information in the knowledge base to obtain a question information set with the matching degree larger than a preset threshold value.
In this embodiment, the first problem information is matched with each problem information in the knowledge base one by one, the matching degree between each problem information in the knowledge base and the first problem information is calculated, then all the problem information larger than a preset threshold value is acquired according to the calculated matching degree, and all the acquired problem information is combined into a problem information set. The value range of the preset threshold value of the matching degree is between 0 and 1. There are various methods for calculating the matching degree, for example, matching may be performed according to keywords, and the number of successfully matched keywords is used as the matching degree. When matching the keywords, the keywords are used as character strings, and the precise matching of the character strings and the fuzzy matching of the character strings can be adopted. Specifically, keywords in the first question information are extracted as first keywords, and then the first keywords are used for matching with question information in a knowledge base, the more the number of matched keywords is, the greater the corresponding matching degree is, and all question information with the matching degree greater than a preset threshold (for example, 80%) is collected to form a question information set. In another embodiment, keywords are extracted from the acquired problem information of the user as first keywords, keywords are extracted from the problem information in the solution cases in the big data knowledge base as second keywords, the matching between the problem information of the user and each problem information in the knowledge base is actually the matching between the first keywords and the second keywords, and the ratio of the number of successfully matched keywords in the number of first keywords is used as the corresponding matching degree. For example, if the number of times of extracting the first keyword from the question information of the user is 10, if 7 keywords in a certain question information in the database are successfully matched with the first keyword, the matching degree of the question information and the first question information is 70%.
And step 104B, searching a score value of a solution effect corresponding to each problem information in the problem information set.
In this embodiment, after the problem information set with the matching degree greater than the preset threshold is obtained, a score value of a solution effect corresponding to each problem information in the problem information set is further obtained, and the larger the score value is, the better the solution effect is.
And step 104C, calculating the matching priority of each question information according to the matching degree of each question information and the first question information in the question information set and the score value of the solution effect corresponding to each question information, and taking the maximum matching priority obtained through calculation as the first matching priority.
In this embodiment, first, the matching degree of each problem information in the problem information set with the first problem information is obtained, and then the score value of the solution effect corresponding to each problem information in the problem information set is obtained. And calculating the matching priority of each question message in the question message set by adopting a weighted average method. Specifically, the matching degree of the problem information is set to P1, the score value of the solution effect corresponding to the problem information is set to P2, then the weight of the matching degree P1 is set to k1, and the weight of the score value P2 of the solution effect is set to k2, where k1+ k2 is 1, and k1 and k2 are numbers greater than 0 and less than 1. Then the matching priority of the corresponding question information is P1 × k1+ P2 × k 2. And then taking the maximum matching priority obtained by calculation as a first matching priority.
And step 104D, using the question information corresponding to the first matching priority as second question information matched with the first question information.
Specifically, the calculated maximum matching priority is used as a first matching priority, then the question information corresponding to the first matching priority is obtained, and the question information corresponding to the first matching priority is used as second question information matched with the first question information.
As shown in fig. 4, in an embodiment, the solution recommendation method further includes:
and 110, acquiring feedback of the user on the solution, and determining a score value of the solution effect corresponding to the solution according to the feedback.
In this embodiment, after a solution is recommended for the problem information of the user, feedback of the user on the recommended solution is acquired, and a score value of a solution effect corresponding to the solution is determined according to the feedback of the user. Specifically, the feedback of the user may be directly given a score in a form of, for example, a full score of 100, and the recommendation is correspondingly scored according to the solution effect, and then the score of the user is used as the score value of the solution effect. The method can also include the steps of obtaining the satisfaction degree of the user on the solution, converting the satisfaction degree of the user into corresponding scores and storing the scores, specifically, assuming that the satisfaction degrees are divided into five types, namely, very satisfactory degrees, general degrees, dissatisfaction degrees and very dissatisfaction degrees, presetting the score value corresponding to each satisfaction degree, for example, the score value corresponding to the very satisfactory degrees is 100 scores, the score value corresponding to the satisfactory degrees is 80 scores, the score value corresponding to the general degrees is 60 scores, the score value corresponding to the dissatisfaction degrees is 30 scores and the score corresponding to the very dissatisfaction degrees is 0 score. For example, if the user evaluates the solution as normal, the background automatically takes the corresponding score of 60 as the score value of the solution effect.
And 112, adding the first problem information, the recommended solutions and the score values of the solution effects into the knowledge base as a solution case, and forming a big data knowledge base when the number of the solution cases in the knowledge base reaches a first preset threshold value.
Specifically, after the score of the user on the recommended scheme is obtained, that is, the score value of the solution effect is obtained. The method is characterized in that the problem information of the previous user, namely the first problem information, the solution recommended for the first problem information and the score value of the solution effect are added into the knowledge base as a new solution case, and the knowledge base can be continuously improved through the method. When the number of the solution cases in the knowledge base is greater than a first preset threshold (for example, the first preset threshold is set to 1 ten thousand), a big data knowledge base is formed, and the greater the number of the solution cases in the big data knowledge base is, the greater the probability that the more matched problem information can be found is. Thus, the proposed solution will also become more and more reliable.
For better understanding and application of a solution recommendation method proposed by the present invention, the following examples are made, and it should be noted that the scope of protection of the present invention is not limited to the following examples.
In one embodiment, the obtained question information of the user is: how to do the computer crash the card machine. And searching second question information matched with the question information of the user in a pre-established big data knowledge base. Specifically, the problem information of the user is matched with the problem information in the big data knowledge base, then the matching degree of each problem information in the knowledge base and the problem information of the user is calculated, then a problem information set with the matching degree larger than 80% is obtained or the matching degrees are sorted from big to small, and then the problem information with the matching degree of the top 10 is selected. For example, one of the question information found from the acquired question information sets to match the question information of the user is "how the computer crashes the card machine. Further, a score value of a solution effect corresponding to each problem information in the problem information set is obtained, and then a solution corresponding to the solution effect with the largest score value is used as a recommended solution. For example, the solution to the problem information of "how to do the computer crashed the card machine" is: and starting the task manager by Ctrl + Alt + Delete, and then selecting to finish the corresponding program process, and the like. The point value of the solution is 99 points, and the solution with the highest point value is the best recommendation obtained.
As shown in FIG. 5, in one embodiment, a solution recommendation system includes:
a question information obtaining module 502, configured to obtain question information of a user, where the question information of the user is used as first question information;
a determining module 504, configured to match the first question information with each question information in a knowledge base, and determine second question information that matches the first question information;
a solution obtaining module 506, configured to obtain a solution corresponding to the second problem information;
a recommending module 508, configured to recommend the obtained solution to the user corresponding to the first problem information.
As shown in fig. 6, in an embodiment, the solution recommendation system further includes:
the establishing module 501 is configured to establish a knowledge base, where the knowledge base includes a plurality of solution cases, and the solution cases include problem information and solution solutions and score values of solution effects corresponding to the problem information.
As shown in fig. 7, in one embodiment, the determining module 504 includes:
a first obtaining unit 504a, configured to match the first question information with each question information in a knowledge base, and obtain a question information set of which a matching degree is greater than a preset threshold;
a first searching unit 504b, configured to search for a score value of a solution effect corresponding to each problem information in the problem information set;
a first matching unit 504c, configured to use the question information corresponding to the solution effect with the largest score value as the second question information matched with the first question information.
As shown in fig. 8, in one embodiment, the determining module 504 includes:
a second obtaining unit 504A, configured to match the first question information with each question information in a knowledge base, and obtain a question information set of which a matching degree is greater than a preset threshold.
The second searching unit 504B is configured to search for a score value of a solution effect corresponding to each problem information in the problem information set.
The calculating unit 504C is configured to calculate a matching priority of each question information according to the matching degree of each question information in the question information set and a score value of a solution effect corresponding to each question information, and use the calculated maximum matching priority as the first matching priority.
The second matching unit 504D is configured to use the question information corresponding to the first matching priority as the second question information matched with the first question information.
As shown in fig. 9, in one embodiment, the recommendation system for the solution further includes:
a feedback module 510, configured to obtain feedback of the solution from the user, and determine a score value of a solution effect corresponding to the solution according to the feedback.
The adding module 512 is configured to add the first problem information, the recommended solution, and the score value of the solution effect to the knowledge base as a solution case, and form a big data knowledge base when the number of solution cases in the knowledge base reaches a first preset threshold.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A solution recommendation method, the method comprising:
acquiring problem information of a user, and taking the problem information of the user as first problem information;
matching the first question information with each question information in a knowledge base to determine second question information matched with the first question information;
acquiring a solution corresponding to the second problem information;
recommending the acquired solution to a user corresponding to the first problem information;
the step of matching the first question information with each question information in a knowledge base and determining second question information matched with the first question information comprises:
converting the keywords into character strings according to the first question information and keywords of each question information in a knowledge base, performing character string matching according to the character strings, taking the number of the successfully matched character strings as matching degree, and acquiring a question information set with the matching degree larger than a preset threshold value;
searching a score value of a solution effect corresponding to each problem information in the problem information set;
and taking the problem information corresponding to the solution effect with the maximum score value as second problem information matched with the first problem information.
2. The method of claim 1, further comprising, prior to the step of obtaining the question information of the user: establishing a knowledge base, wherein the knowledge base comprises a plurality of solution cases, and the solution cases comprise problem information and solution schemes and fractional values of solution effects corresponding to the problem information.
3. The method of claim 2, wherein matching the first question information to respective question information in a knowledge base, and wherein determining second question information that matches the first question information further comprises:
matching the first question information with each question information in a knowledge base to obtain a question information set with the matching degree larger than a preset threshold value;
searching a score value of a solution effect corresponding to each problem information in the problem information set;
calculating the matching priority of each problem information according to the matching degree of each problem information in the problem information set and the score value of the solution effect corresponding to each problem information, and taking the maximum matching priority obtained by calculation as a first matching priority;
and taking the question information corresponding to the first matching priority as second question information matched with the first question information.
4. The method of claim 1, further comprising:
obtaining feedback of a user on the solution, and determining a score value of a solution effect corresponding to the solution according to the feedback;
and adding the first problem information, the recommended solutions and the score values of the solution effects into the knowledge base as a solution case, and forming a big data knowledge base when the number of the solution cases in the knowledge base reaches a first preset threshold value.
5. A solution recommendation system, characterized in that the system comprises:
the system comprises a question information acquisition module, a question information processing module and a question information processing module, wherein the question information acquisition module is used for acquiring question information of a user and taking the question information of the user as first question information;
the determining module is used for matching the first question information with each question information in a knowledge base and determining second question information matched with the first question information;
a solution obtaining module, configured to obtain a solution corresponding to the second problem information;
the recommending module is used for recommending the acquired solution to a user corresponding to the first problem information;
the determining module comprises:
the first acquisition unit is used for extracting the first question information and keywords of each question information in a knowledge base, converting the keywords into character strings, matching the character strings according to the character strings, taking the number of the successfully matched character strings as the matching degree, and acquiring a question information set with the matching degree larger than a preset threshold value;
the first searching unit is used for searching a score value of a solving effect corresponding to each problem information in the problem information set;
and the first matching unit is used for taking the problem information corresponding to the solution effect with the largest score value as the second problem information matched with the first problem information.
6. The system of claim 5, further comprising:
the system comprises an establishing module and a judging module, wherein the establishing module is used for establishing a knowledge base, the knowledge base comprises a plurality of solution cases, and the solution cases comprise problem information, solutions corresponding to the problem information and fraction values of solution effects.
7. The system of claim 6, wherein the determination module further comprises:
the second acquisition unit is used for matching the first question information with each question information in a knowledge base and acquiring a question information set with the matching degree larger than a preset threshold value;
the second searching unit is used for searching a score value of a solving effect corresponding to each problem information in the problem information set;
a calculating unit, configured to calculate a matching priority of each piece of problem information according to the matching degree of each piece of problem information in the problem information set and a score value of a solution effect corresponding to each piece of problem information, and use a maximum matching priority obtained through calculation as a first matching priority;
and the second matching unit is used for taking the question information corresponding to the first matching priority as second question information matched with the first question information.
8. The system of claim 5, further comprising:
the feedback module is used for acquiring feedback of a user on the solution and determining a score value of a solution effect corresponding to the solution according to the feedback;
and the adding module is used for adding the first problem information, the recommended solutions and the score values of the solution effects into the knowledge base as a solution case, and when the number of the solution cases in the knowledge base reaches a first preset threshold value, a big data knowledge base is formed.
9. A storage medium on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the solution recommendation method according to any one of claims 1-4.
10. A terminal device comprising a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, the processor implementing the solution recommendation method according to any one of claims 1-4 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610416286.0A CN106095941B (en) | 2016-06-14 | 2016-06-14 | Big data knowledge base-based solution recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610416286.0A CN106095941B (en) | 2016-06-14 | 2016-06-14 | Big data knowledge base-based solution recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106095941A CN106095941A (en) | 2016-11-09 |
| CN106095941B true CN106095941B (en) | 2020-03-20 |
Family
ID=57846697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610416286.0A Active CN106095941B (en) | 2016-06-14 | 2016-06-14 | Big data knowledge base-based solution recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106095941B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875014B (en) * | 2018-06-20 | 2021-11-02 | 大国创新智能科技(东莞)有限公司 | Precise project recommendation method based on big data and artificial intelligence and robot system |
| CN109299224B (en) * | 2018-10-23 | 2020-12-01 | 广州九一乐维信息科技有限公司 | Zabbix-based solution query method and device and computer equipment |
| CN111507550A (en) * | 2019-01-30 | 2020-08-07 | 广州泰迪智能科技有限公司 | Automatic recommendation method for optimal solution of work order problem |
| CN110471961A (en) * | 2019-08-22 | 2019-11-19 | 北京锐安科技有限公司 | A kind of product demand acquisition methods, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236677A (en) * | 2010-04-28 | 2011-11-09 | 北京大学深圳研究生院 | Question answering system-based information matching method and system |
| CN103853842A (en) * | 2014-03-20 | 2014-06-11 | 百度在线网络技术（北京）有限公司 | Automatic question and answer method and system |
| CN104133817A (en) * | 2013-05-02 | 2014-11-05 | 深圳市世纪光速信息技术有限公司 | Online community interaction method and device and online community platform |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
-
2016
- 2016-06-14 CN CN201610416286.0A patent/CN106095941B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236677A (en) * | 2010-04-28 | 2011-11-09 | 北京大学深圳研究生院 | Question answering system-based information matching method and system |
| CN104133817A (en) * | 2013-05-02 | 2014-11-05 | 深圳市世纪光速信息技术有限公司 | Online community interaction method and device and online community platform |
| CN103853842A (en) * | 2014-03-20 | 2014-06-11 | 百度在线网络技术（北京）有限公司 | Automatic question and answer method and system |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106095941A (en) | 2016-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020073534A1 (en) | Pushing method and apparatus based on re-clustering, and computer device and storage medium | |
| CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
| CN106095941B (en) | Big data knowledge base-based solution recommendation method and system | |
| EP2933770A1 (en) | Method and system for pushing mobile application | |
| CN112800170A (en) | Question matching method and device and question reply method and device | |
| WO2019223552A1 (en) | Article recommendation method and apparatus, and computer device and storage medium | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| EP3367258A1 (en) | Playlist list determining method, device, electronic device and storage medium | |
| CN107943910B (en) | Personalized book recommendation method based on combined algorithm | |
| CN116455861B (en) | Big data-based computer network security monitoring system and method | |
| WO2018058118A1 (en) | Method, apparatus and client of processing information recommendation | |
| WO2020073526A1 (en) | Trust network-based push method, apparatus, computer device, and storage medium | |
| CN109492085A (en) | Method, apparatus, terminal and storage medium are determined based on the answer of data processing | |
| CN111160699A (en) | Expert recommendation method and system | |
| CN109543002B (en) | Method, device and equipment for restoring abbreviated characters and storage medium | |
| CN116628142B (en) | Knowledge retrieval method, device, equipment and readable storage medium | |
| CN117495485A (en) | Product recommendation method, device and readable storage medium | |
| CN112597292A (en) | Question reply recommendation method and device, computer equipment and storage medium | |
| CN110162535B (en) | Search method, apparatus, device and storage medium for performing personalization | |
| CN112528046A (en) | New knowledge graph construction method and device and information retrieval method and device | |
| CN112559769A (en) | Method and device for generating question-answer database | |
| CN108170665B (en) | Keyword expansion method and device based on comprehensive similarity | |
| US20220108071A1 (en) | Information processing device, information processing system, and non-transitory computer readable medium | |
| CN109213937B (en) | Intelligent search method and device | |
| CN113849518A (en) | Assisted search query |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |