CN113010640A - Service execution method and device - Google Patents
Service execution method and device Download PDFInfo
- Publication number
- CN113010640A CN113010640A CN202110239446.XA CN202110239446A CN113010640A CN 113010640 A CN113010640 A CN 113010640A CN 202110239446 A CN202110239446 A CN 202110239446A CN 113010640 A CN113010640 A CN 113010640A
- Authority
- CN
- China
- Prior art keywords
- statement
- user
- service
- guide
- information
- 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.)
- Granted
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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Acoustics & Sound (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present specification discloses a method and an apparatus for executing a service, wherein after receiving a current service request of a user, a service platform can obtain service related information corresponding to the user, determine a service tag related to the user according to the service related information, and determine a service guide statement template matched with the service tag related to the user from pre-constructed service guide statement templates as a target guide statement template. Finally, the service platform can determine at least one piece of filling information corresponding to the target guide statement template according to the search information type corresponding to the position to be filled in the target guide statement template and the determined service word set corresponding to the user, fill the position to be filled according to the at least one piece of filling information to generate a guide statement, and display the guide statement to the user, so that the user performs service execution according to the guide statement, and can perform accurate service guide on the user to a certain extent.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for executing a service.
Background
In practical application, a user may search for a service required by the user through a service platform for execution, for example, the user may search for the service required by the user through a voice input form in the service platform, or may input search information in a text form for query.
No matter how the user searches the required service, the service platform can provide some information for the user to refer to when the user inquires, and guide the user to search, so that the user can search according to the information. In the prior art, when a user needs to search information in a voice form, a service platform can extract keywords from information browsed by the user in history and information searched by the user and recommend the keywords to the user, so that the user can refer to the keywords to perform voice input.
However, in the prior art, keywords may not accurately represent the intention of the user, so how to accurately display information guiding the user to search for the user is a problem to be solved.
Disclosure of Invention
The present specification provides a method and an apparatus for service execution, so as to partially solve the above problems in the prior art.
The technical scheme adopted by the specification is as follows:
the present specification provides a method for service execution, including:
responding to a current service request of a user, and acquiring service related information corresponding to the user, wherein the service related information comprises: at least one of user information of the user, a current geographic position of the user, current corresponding time information of the user and historical behavior records of the user;
determining a service label related to the user according to the service related information;
determining a business guide statement template matched with a business label related to the user from all pre-constructed business guide statement templates to serve as a target guide statement template, and determining at least one piece of filling information corresponding to the target guide statement template according to a search information type corresponding to a position to be filled in the target guide statement template and the determined business word set corresponding to the user;
and filling the position to be filled according to the at least one piece of filling information to obtain a guide statement, and displaying the guide statement to the user so that the user performs service execution according to the guide statement.
Optionally, determining a service tag related to the user according to the service related information specifically includes:
for each service label, inputting the relevant information and the label identification of the service label into a first pre-trained prediction model, and determining the correlation degree between the service label and the user;
and sequencing the service labels according to the relevance from large to small, and taking the service label before the set ranking as the service label related to the user.
Optionally, determining at least one piece of filling information corresponding to the target guide statement template according to the search information type corresponding to the position to be filled in the target guide statement template and the determined service word set corresponding to the user, specifically including:
and aiming at each position to be filled of the target guide statement template, determining a service word which is matched with the search information type corresponding to the position to be filled and meets the subordination relation between filling information corresponding to other positions to be filled in the target guide statement template from the service word set, and taking the service word as the filling information corresponding to the position to be filled.
Optionally, constructing each service guide statement template specifically includes:
acquiring each historical search statement;
for each historical search statement, determining a specified word from the historical search statement;
taking the position of the specified word in the historical search statement as a position to be filled corresponding to the historical search statement, determining a basic statement corresponding to the historical search statement according to partial statements except the position to be filled in the historical search statement, and determining a search information type corresponding to the historical search statement according to the search information type corresponding to the specified word;
and constructing each business guide statement template according to the position to be filled corresponding to each historical search statement, the basic statement corresponding to each historical search statement and the search information type corresponding to each historical search statement.
Optionally, determining a basic sentence corresponding to the historical search sentence according to a part of sentences except for the position to be filled in the historical search sentence specifically includes:
for each historical search statement, determining the similarity between partial statements except the position to be filled in other historical search statements and partial statements except the position to be filled in the historical search statement;
determining at least one other historical search statement meeting set conditions from the other historical search statements with the similarity greater than the set similarity;
and determining a basic sentence corresponding to the historical search sentence according to the partial sentences except the positions to be filled in the at least one other historical search sentence which meets the set conditions and the partial sentences except the positions to be filled in the historical search sentence.
Optionally, in the at least one other history search statement that satisfies the set condition, a sum of historical search times of each other history search statement is not less than the set search time.
Optionally, according to the at least one piece of filling information, filling the to-be-filled position to obtain a guide statement, specifically including:
filling the position to be filled according to the at least one piece of filling information to obtain at least one candidate guide statement;
for each candidate guide statement, determining feature information corresponding to the candidate guide statement according to template information corresponding to the candidate guide statement, related information of the candidate guide statement and the service related information, wherein the template information comprises: at least one of a template identifier of a target guide statement template corresponding to the candidate guide statement, a search information type corresponding to a position to be filled in the target guide statement template corresponding to the candidate guide statement, and a service tag of the target guide statement template corresponding to the candidate guide statement, where relevant information of the candidate guide statement includes: at least one of the length of the candidate guide statement and filling information in a position to be filled in the candidate guide statement;
inputting the characteristic information corresponding to the candidate guide statement into a pre-trained second prediction model to obtain the correlation degree between the candidate guide statement and the user as the correlation degree corresponding to the candidate guide statement;
and determining the guide sentences displayed for the user according to the corresponding correlation degree of each candidate guide sentence.
Optionally, training the first prediction model specifically includes:
for each service label, taking a historical search statement which is historically related to the service label as a first historical search statement, and constructing a positive sample according to service related information corresponding to a user which historically sends the first historical search statement;
taking a historical search statement which is not related to the service tag historically as a second historical search statement, determining users who send the historical search statement related to the service tag historically less than a set number of times among users who send the second historical search statement as target users, and constructing a negative sample according to service related information corresponding to the target users;
and training the first prediction model according to the positive samples and the negative samples.
Optionally, training the second prediction model specifically includes:
acquiring historical guide sentences historically recommended to each user;
for each historical guide statement, determining whether each user sends an execution result of voice search information after looking up the historical guide statement historically according to the historical behavior record of each user, wherein the execution result is used as the corresponding annotation information of the historical guide statement;
inputting the characteristic information corresponding to the historical guide statement into a second prediction model to obtain a prediction result corresponding to the historical guide statement, wherein the prediction result indicates whether a user sends voice search information after checking the historical guide statement;
and training the second prediction model by taking the minimized deviation between the prediction result and the labeled information as an optimization target.
The present specification provides a service execution apparatus, including:
an obtaining module, configured to respond to a current service request of a user, and obtain service-related information corresponding to the user, where the service-related information includes: at least one of user information of the user, a current geographic position of the user, current corresponding time information of the user and historical behavior records of the user;
a first determining module, configured to determine, according to the service-related information, a service tag related to the user;
a second determining module, configured to determine, from pre-constructed business guide statement templates, a business guide statement template that matches a business label related to the user, as a target guide statement template, and determine at least one piece of filling information corresponding to the target guide statement template according to a search information type corresponding to a position to be filled in the target guide statement template and the determined business word set corresponding to the user;
and the display module is used for filling the position to be filled according to the at least one piece of filling information to obtain a guide statement and displaying the guide statement to the user so that the user performs service execution according to the guide statement.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the method of service execution described above.
The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of service execution when executing the program.
The technical scheme adopted by the specification can achieve the following beneficial effects:
in the method and apparatus for service execution provided in this specification, after receiving a current service request of a user, a service platform may obtain service related information corresponding to the user, where the service related information may include at least one of user information of the user, a current geographic location of the user, current corresponding time information of the user, and a historical behavior record of the user. Then, the service platform can determine the service label related to the user according to the service related information, and determine a service guide statement template matched with the service label related to the user from the pre-constructed service guide statement templates as a target guide statement template. And finally, the service platform can determine at least one piece of filling information corresponding to the target guide statement template according to the search information type corresponding to the position to be filled in the target guide statement template and the determined service word set corresponding to the user, fill the position to be filled according to the at least one piece of filling information to generate a guide statement, and display the guide statement to the user so that the user performs service execution according to the guide statement.
The method can be seen that the business platform can automatically generate a guide statement for business guide for a user when the user needs to search information, and the guide statement is determined by a business guide statement template matched with a business label related to the user, and the guide statement can be matched with the user intention to a certain extent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
fig. 1 is a schematic flow chart of a method for executing a service in the present specification;
FIG. 2 is a schematic diagram of determining a business guide statement template through a historical search statement provided in the present specification;
fig. 3 is a schematic diagram of a service execution apparatus in the present specification;
fig. 4 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for executing a service in this specification, which specifically includes the following steps:
s101: responding to a current service request of a user, and acquiring service related information corresponding to the user, wherein the service related information comprises: at least one of user information of the user, a current geographic location of the user, current corresponding time information of the user, and historical behavior records of the user.
S102: and determining a service label related to the user according to the service related information.
In some service scenarios, in order to facilitate the user to perform service execution, the service platform may present information for guiding the user to perform service execution to the user. For example, in a voice search scenario, a user may input voice information through a service platform to perform information search, before the user performs information search, the service platform may display information for guiding the user to perform voice input to the user, where the information is information that the user may want to search and is determined by the service platform, and of course, the user may input voice according to the information displayed by the service platform, or may input voice according to his own idea to perform information search.
Of course, in other service scenarios, the service platform may also present similar information for guiding the user, for example, in a text search scenario, the service platform may also provide information for guiding the user to perform service execution, that is, the service platform provides search information that the user may want to input to guide the user to perform information search.
Based on this, the service platform may respond to the current service request of the user to obtain service related information corresponding to the user, where the service request mentioned here may refer to a service request sent when the user needs to perform a voice search, a service request sent when the user needs to perform a text search, and the like, and the service related information may include user information of the user, a current geographical location of the user, current corresponding time information of the user, a historical behavior record of the user, and the like. The service platform may determine the service label corresponding to the user according to the service related information corresponding to the user.
The user information of the user may refer to the age, sex, etc. of the user. The historical behavior record of the user may include: the number of times that the search information input when the user has historically performed information search is related to each service tag, the number of times that the user has historically performed services related to each service tag, and the like. The above-mentioned service tags may be used to indicate which services the user is related to, for example, service tags may include dining, hotels, traveling, finding merchants, finding coupons, and the like. If the service tags related to the user determined by the service platform are two service tags, namely, a restaurant and a merchant, it can be determined that the user may need to query merchants of the restaurant class, and then according to the predicted intention of the user, related guide sentences can be displayed for the user to guide the user to perform voice search.
In this specification, the service platform may determine the service label associated with the user through a pre-trained first prediction model. Specifically, the service platform may input, for each service label, a label identifier corresponding to the service label and service-related information of the user into a pre-trained first prediction model, so as to determine a correlation degree between the service label and the user, and after sorting the service labels according to the correlation degree from large to small, the service platform may use the service label before setting the ranking as the service label related to the user.
Specifically, the service platform may obtain the training sample according to a service execution result of information search performed in the service platform by each user historically. For each business label, taking a historical search statement historically related to the business label as a first historical search statement, constructing a positive sample according to business related information corresponding to a user historically sending the first historical search statement, taking a historical search statement historically unrelated to the business label as a second historical search statement, determining users who send the second historical search statement, wherein the number of times of historically sending the historical search statement related to the business label is less than a set number of times, and using the users as target users.
Therefore, when the negative sample is determined, after the historical search statement irrelevant to the service tag is determined, the user with the lower historical search frequency for the service tag can be selected to construct the negative sample, and therefore, the relevance between the user and the service tag in the negative sample is lower.
S103: determining a business guide statement template matched with a business label related to the user from all pre-constructed business guide statement templates to serve as a target guide statement template, and determining at least one piece of filling information corresponding to the target guide statement template according to a search information type corresponding to a position to be filled in the target guide statement template and the determined business word set corresponding to the user.
After determining each service tag related to the user, the service platform may determine, from pre-constructed service guide statement templates, a service guide statement template matched with the service tag related to the user as a target guide statement template, and determine at least one piece of filling information corresponding to the target guide statement template according to a search information type corresponding to a position to be filled in the target guide statement model and the determined service word set corresponding to the user.
The service guide statement template mentioned here is used for a service platform to generate a guide statement, for a service guide statement template, the service guide statement template includes a position to be filled and a partial statement except the position to be filled, the position to be filled is a vacant position in the service guide statement template, and after it is determined that filling information fills the position to be filled, the filling information and the partial statement except the position to be filled can form a complete statement as the guide statement.
Each business guide statement template can correspond to a plurality of business tags, and if the quantity of the business tags corresponding to one business guide statement template, which is consistent with the business tags related to the user, is not less than a set quantity, the business guide statement template can be used as a target guide statement template.
For example, if the service tag determined by the service platform to be related to the user is catering and a dealer, the target guidance statement template may be "i want to eat" _ "of the" _ ", where the" _ "part is a position to be filled, and each position to be filled corresponds to a search information type, that is, filling information of the search information type corresponding to the position to be filled can be filled in the position to be filled, and assuming that in this example, the search information type corresponding to the first position to be filled in the target guidance statement template is a name of a dealer and the search information type corresponding to the second position to be filled is a name of a dish, the service platform may fill the target guidance statement template according to the service word set corresponding to the user. If the business word set corresponding to the user contains restaurant A and spicy hot pot, the business platform can fill restaurant A and spicy hot pot in the target guide statement template to obtain the guide statement: if the user searches the information according to the guide statement, the service platform can show the relevant information of the restaurant A to the user.
As can be seen from the above example of the target guide statement template, a plurality of positions to be filled may exist in the target guide statement template, and after the positions to be filled in the target guide statement template are filled, a guide statement can be obtained. In order to finally obtain a correct guide statement, when a target guide statement template is filled, a service platform needs to determine, from a service word set, a service word, which is matched with the type of search information corresponding to a position to be filled and satisfies the dependency relationship between filling information corresponding to other positions to be filled in the target guide statement template, for each position to be filled of the target guide statement template, as filling information corresponding to the position to be filled.
The dependency referred to herein may mean that the filling information in different positions to be filled needs to satisfy a certain dependency. Continuing to take the previous example, in the previous example, the target guidance statement template is "i want to eat" _ ", where the search information type corresponding to the first to-be-filled location is a name of a merchant, and the search information type corresponding to the second to-be-filled location is a name of a dish, and when filling is performed, the filling information corresponding to the second to-be-filled location needs to satisfy the dependency relationship with the first to-be-filled location, that is, the name of the dish in the second to-be-filled location should coincide with the name of the restaurant in the first to-be-filled location, that is, after filling is performed, the dish corresponding to the name of the dish in the guidance statement should exist in the restaurant corresponding to the name of the restaurant.
Assuming that the service word set corresponding to the user comprises restaurant A, restaurant B, spicy pot and fish filets, the service platform combines the service words in the service word set to obtain 4 guide sentences, however, the restaurant A has a spicy pot and no fish is boiled in water, the restaurant B has a spicy pot and no fish is boiled in water, when the target guide sentence template is filled, if restaurant a is filled in the target guide sentence template, when filling another position to be filled, the spicy incense pot meeting the subordination relation needs to be filled in the target guide statement template, if the obtained guide sentence is the spicy incense pot which the restaurant A wants to eat, if the restaurant B is filled with the target guide sentence template, when another position to be filled is filled, the boiled fish meeting the dependency relationship needs to be filled in the target guide sentence template, and the obtained guide sentence is the boiled fish which I wants to eat the restaurant B.
S104: and filling the position to be filled according to the at least one piece of filling information to generate a guide statement, and displaying the guide statement to the user so that the user performs service execution according to the guide statement.
After the business platform determines at least one piece of filling information, filling positions to be filled in the target guide statement template according to the filling information to generate a guide statement, and displaying the guide statement to the user so that the user performs business execution according to the guide statement displayed to the user. The business platform can determine various filling information and various target guide statement templates, fill the various target guide statement templates through the various filling information, obtain a plurality of candidate guide statements, and select the guide statements displayed for the user from the candidate guide statements.
Specifically, for each candidate guidance statement, the service platform may determine, according to the template information corresponding to the candidate guidance statement, the relevant information of the candidate guidance statement, and the service relevant information of the user, the feature information corresponding to the candidate guidance statement. The service platform may input the feature information corresponding to the candidate guide sentence into a pre-trained second prediction model, obtain a degree of correlation between the candidate guide sentence and the user as a degree of correlation corresponding to the candidate guide sentence, and according to the degree of correlation corresponding to each candidate guide sentence, the service platform may determine the guide sentence displayed to the user from each candidate guide sentence.
For example, the service platform may determine a candidate guidance statement with a higher relevance than the set relevance as the guidance statement to be presented to the user. For another example, the service platform may sort the candidate guide statements according to the relevance from large to small, and use the candidate guide statement before the set ranking as the guide statement to be presented to the user.
The template information may include a template identifier of a target guide statement template corresponding to the candidate guide statement, a search information type corresponding to a to-be-filled position in the target guide statement template corresponding to the candidate guide statement, a service tag of the target guide statement template corresponding to the candidate guide statement, and the like, and the related information of the candidate guide statement may include a length of the candidate guide statement, filling information in the to-be-filled position in the candidate guide statement, and the like.
The second prediction model also needs to be supervised and trained in advance, specifically, the service platform can acquire historical guide sentences historically recommended to each user, and for each historical guide sentence, after determining that each user has historically viewed the historical guidance statement according to the historical behavior record of each user, whether to send the execution result of the voice search information is used as the marking information corresponding to the historical guide statement, the characteristic information corresponding to the historical guide statement is input into the second prediction model to obtain the prediction result corresponding to the historical guide statement, the prediction result indicates whether the user sends voice search information after the history guide statement is checked, and the service platform can train the second prediction model by taking the deviation between the minimized prediction result and the labeled information of the history guide statement as an optimization target.
That is, the second prediction model is trained for the purpose of performing voice search according to the guide sentence after the user sees the guide sentence shown to the second prediction model, and for the purpose of performing more reasonable service guide on the user by the guide sentence shown to the user, the service platform may train another third prediction model similar to the second prediction model, and when the third prediction model is trained, the difference between the training sample and the training sample of the second prediction model is that the annotation information corresponding to the training sample is used to indicate whether the user will send voice search information and whether the voice search information sent by the user is similar to the history guide sentence after the history guide sentence is seen, and if the annotation information indicates that the user will send voice search information and the voice search information sent by the user is similar to the history guide sentence after the history guide sentence is seen, then such training samples are positive samples, otherwise, the training samples are negative samples. That is, the third prediction model aims at enabling a user to perform information search in accordance with a guide sentence.
The service platform may also obtain the correlation between the user and the candidate guide sentences determined by the third prediction model, perform weighted summation on the correlations determined by the second prediction model and the third prediction model, respectively (weights may be preset for the correlations determined by the second prediction model and the third prediction model, respectively), obtain a total score for the candidate guide sentences, and select the guide sentences displayed to the user according to the total scores corresponding to the candidate guide sentences.
It should be noted that, each service guide statement template needs to be pre-constructed by the service platform, so that after the service tag related to the user is determined, the target guide statement template can be determined for the user through the service tags, and the guide statement displayed for the user is determined.
The business platform can build each business guide statement template in a manual mode, and can also search statements sent by each user in history through collected history. To build a business guide statement template.
Specifically, the service platform may obtain each historical search statement, determine a specified term from the historical search statement for each historical search statement, use a position of the specified term in the historical search statement as a to-be-filled position corresponding to the historical search statement, determine a basic statement corresponding to the historical search statement according to a part of the historical search statement except for the to-be-filled position, and determine a search information type corresponding to the historical search statement according to the search information type corresponding to the specified term. The business platform can construct each business guide statement template according to the position to be filled corresponding to each historical search statement, the basic statement corresponding to each historical search statement and the search information type corresponding to each historical search statement.
That is, the service platform converts the history search sentence into the service guide sentence template by the specified word determined in the history search sentence. The manner of determining the designated word may be various, for example, the service platform may determine a set of the designated word in advance, so as to determine the designated word in the historical search sentence, and of course, the service platform may also determine the designated word through a machine learning model. When each user searches information historically, sent historical search sentences may have similarities, the service platform may merge the similar historical search sentences, and if the historical search sentences of each user are used with high utilization rate historically, the service guide sentence template may be determined through the historical search sentences.
Therefore, the service platform can also determine, for each historical search statement, the similarity between the partial statement except the to-be-filled position in the other historical search statements and the partial statement except the to-be-filled position in the historical search statement, and determine at least one other historical search statement meeting the set condition from the other historical search statements with the similarity greater than the set similarity. The service platform can determine the basic sentence corresponding to the historical search sentence according to the partial sentence except the position to be filled in at least one other historical search sentence which meets the set condition and the partial sentence except the position to be filled in the historical search sentence.
The setting conditions mentioned above may be various, for example, if the sum of the historical search times of each of the at least one other historical search term is not less than the setting search time, the at least one other historical search term satisfies the setting conditions. For another example, if the historical search times of each of the at least one other historical search statement are not less than the set search times, the at least one other historical search statement all satisfies the set condition.
This is illustrated below by some historical search statements, as shown in FIG. 2.
Fig. 2 is a schematic diagram of determining a business guide statement template through a historical search statement provided in this specification.
The historical search statement 1 is which boiled fish is sold, the service platform can determine the specified word of the boiled fish from the historical search statement 1, the position of the word of the boiled fish in the historical search statement 1 is used as the position to be filled corresponding to the historical search statement 1, which selling is the partial statement except the position to be filled in the historical search statement 1, the type of the search information corresponding to the word of the boiled fish is the name of the dish, and if the historical search statement is converted into a service guide statement template, the service guide statement template is which selling is sold, wherein the type of the search information corresponding to the position to be filled is the name of the dish.
Where the historical search statement 2 is provided with the spicy dip, where the historical search statement 3 is provided with the hot pot, the service platform identifies the 'spicy dip' from the historical search statement 2, identifies the 'hot pot' from the historical search statement 3, the basic statements corresponding to the three historical search statements are 'where to sell', 'where to have' and 'where to have', the total number of times of searching the three historical search statements in the history of each user is 1000, and the set number of times is 500, so that the service platform can construct a service guide statement template according to the three historical search statements. Of course, the service platform may select a basic sentence corresponding to the historical search sentence from the historical search sentences to determine the service guide sentence template, or all of the 3 sentences may be used as the service guide sentence templates. For example, the service guide sentence template may be "which is sold/where is" _"," _ "corresponding to the search information type is the name of the dish.
The method can be seen in that the business platform can determine the guide sentences displayed to the user through the target guide sentence templates matched with the user when the user needs to search information, and the target guide sentence templates determined by the business platform are determined through the business labels related to the user, so that the guide sentences determined by the target guide sentence templates can be matched with the intention of the user to a certain extent.
Moreover, each business guide statement template can be used for summarizing and determining the historical search statements of each user for the business platform, so that the guide statements determined by the business guide statement template accord with the daily language habits of people, and compared with the prior art, the method can accurately guide the business of the user through the statements according with the language habits, and can improve the business execution efficiency of the user to a certain extent.
Based on the same idea, the present specification further provides a device for performing a service, as shown in fig. 3.
Fig. 3 is a schematic diagram of a service execution apparatus provided in this specification, which specifically includes:
an obtaining module 301, configured to respond to a current service request of a user, and obtain service-related information corresponding to the user, where the service-related information includes: at least one of user information of the user, a current geographic position of the user, current corresponding time information of the user and historical behavior records of the user;
a first determining module 302, configured to determine a service tag related to the user according to the service-related information;
a second determining module 303, configured to determine, from pre-constructed business guide statement templates, a business guide statement template that matches a business label related to the user, as a target guide statement template, and determine at least one piece of filling information corresponding to the target guide statement template according to a search information type corresponding to a position to be filled in the target guide statement template and the determined business word set corresponding to the user;
a display module 304, configured to fill the position to be filled according to the at least one piece of filling information to obtain a guide statement, and display the guide statement to the user, so that the user performs service execution according to the guide statement.
Optionally, the first determining module 302 is specifically configured to, for each service tag, input the relevant information and a tag identifier of the service tag into a first pre-trained prediction model, and determine a degree of correlation between the service tag and the user; and sequencing the service labels according to the relevance from large to small, and taking the service label before the set ranking as the service label related to the user.
Optionally, the second determining module 303 is specifically configured to, for each to-be-filled position of the target guidance statement template, determine, from the service word set, a service word that matches the search information type corresponding to the to-be-filled position and satisfies a dependency relationship between filling information corresponding to other to-be-filled positions in the target guidance statement template, as the filling information corresponding to the to-be-filled position.
Optionally, the apparatus further comprises:
a building module 305, configured to obtain each historical search statement; for each historical search statement, determining a specified word from the historical search statement; taking the position of the specified word in the historical search statement as a position to be filled corresponding to the historical search statement, determining a basic statement corresponding to the historical search statement according to partial statements except the position to be filled in the historical search statement, and determining a search information type corresponding to the historical search statement according to the search information type corresponding to the specified word; and constructing each business guide statement template according to the position to be filled corresponding to each historical search statement, the basic statement corresponding to each historical search statement and the search information type corresponding to each historical search statement.
Optionally, the building module 305 is specifically configured to, for each historical search statement, determine a similarity between a partial statement in the other historical search statements except for the to-be-filled position and a partial statement in the historical search statement except for the to-be-filled position; determining at least one other historical search statement meeting set conditions from the other historical search statements with the similarity greater than the set similarity; and determining a basic sentence corresponding to the historical search sentence according to the partial sentences except the positions to be filled in the at least one other historical search sentence which meets the set conditions and the partial sentences except the positions to be filled in the historical search sentence.
Optionally, in the at least one other history search statement that satisfies the set condition, a sum of historical search times of each other history search statement is not less than the set search time.
Optionally, the presentation module 304 is specifically configured to, according to the at least one filling information, fill the to-be-filled position to obtain at least one candidate guidance statement; for each candidate guide statement, determining feature information corresponding to the candidate guide statement according to template information corresponding to the candidate guide statement, related information of the candidate guide statement and the service related information, wherein the template information comprises: at least one of a template identifier of a target guide statement template corresponding to the candidate guide statement, a search information type corresponding to a position to be filled in the target guide statement template corresponding to the candidate guide statement, and a service tag of the target guide statement template corresponding to the candidate guide statement, where relevant information of the candidate guide statement includes: at least one of the length of the candidate guide statement and filling information in a position to be filled in the candidate guide statement; inputting the characteristic information corresponding to the candidate guide statement into a pre-trained second prediction model to obtain the correlation degree between the candidate guide statement and the user as the correlation degree corresponding to the candidate guide statement; and determining the guide sentences displayed for the user according to the corresponding correlation degree of each candidate guide sentence.
Optionally, the apparatus further comprises:
a training module 306, configured to, for each service tag, use a historical search statement historically related to the service tag as a first historical search statement, and construct a positive sample according to service-related information corresponding to a user historically sending the first historical search statement; taking a historical search statement which is not related to the service tag historically as a second historical search statement, determining users who send the historical search statement related to the service tag historically less than a set number of times among users who send the second historical search statement as target users, and constructing a negative sample according to service related information corresponding to the target users; and training the first prediction model according to the positive samples and the negative samples.
Optionally, the training module 306 is further configured to obtain historical guidance statements historically recommended to each user; for each historical guide statement, determining whether each user sends an execution result of voice search information after looking up the historical guide statement historically according to the historical behavior record of each user, wherein the execution result is used as the corresponding annotation information of the historical guide statement; inputting the characteristic information corresponding to the historical guide statement into a second prediction model to obtain a prediction result corresponding to the historical guide statement, wherein the prediction result indicates whether a user sends voice search information after checking the historical guide statement; and training the second prediction model by taking the minimized deviation between the prediction result and the labeled information as an optimization target.
The present specification also provides a computer-readable storage medium storing a computer program, which is operable to execute the method of service execution shown in fig. 1.
This specification also provides a schematic block diagram of the electronic device shown in fig. 4. As shown in fig. 4, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the method for executing the service described in fig. 1. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (12)
1. A method of service execution, comprising:
responding to a current service request of a user, and acquiring service related information corresponding to the user, wherein the service related information comprises: at least one of user information of the user, a current geographic position of the user, current corresponding time information of the user and historical behavior records of the user;
determining a service label related to the user according to the service related information;
determining a business guide statement template matched with a business label related to the user from all pre-constructed business guide statement templates to serve as a target guide statement template, and determining at least one piece of filling information corresponding to the target guide statement template according to a search information type corresponding to a position to be filled in the target guide statement template and the determined business word set corresponding to the user;
and filling the position to be filled according to the at least one piece of filling information to obtain a guide statement, and displaying the guide statement to the user so that the user performs service execution according to the guide statement.
2. The method of claim 1, wherein determining the service label associated with the user according to the service-related information specifically comprises:
for each service label, inputting the relevant information and the label identification of the service label into a first pre-trained prediction model, and determining the correlation degree between the service label and the user;
and sequencing the service labels according to the relevance from large to small, and taking the service label before the set ranking as the service label related to the user.
3. The method according to claim 1, wherein determining at least one piece of filling information corresponding to the target guide statement template according to the search information type corresponding to the position to be filled in the target guide statement template and the determined service word set corresponding to the user specifically includes:
and aiming at each position to be filled of the target guide statement template, determining a service word which is matched with the search information type corresponding to the position to be filled and meets the subordination relation between filling information corresponding to other positions to be filled in the target guide statement template from the service word set, and taking the service word as the filling information corresponding to the position to be filled.
4. The method of claim 1, wherein constructing each business guide statement template specifically comprises:
acquiring each historical search statement;
for each historical search statement, determining a specified word from the historical search statement;
taking the position of the specified word in the historical search statement as a position to be filled corresponding to the historical search statement, determining a basic statement corresponding to the historical search statement according to partial statements except the position to be filled in the historical search statement, and determining a search information type corresponding to the historical search statement according to the search information type corresponding to the specified word;
and constructing each business guide statement template according to the position to be filled corresponding to each historical search statement, the basic statement corresponding to each historical search statement and the search information type corresponding to each historical search statement.
5. The method of claim 4, wherein determining the basic sentence corresponding to the historical search sentence according to the partial sentences except the positions to be filled in the historical search sentence specifically comprises:
for each historical search statement, determining the similarity between partial statements except the position to be filled in other historical search statements and partial statements except the position to be filled in the historical search statement;
determining at least one other historical search statement meeting set conditions from the other historical search statements with the similarity greater than the set similarity;
and determining a basic sentence corresponding to the historical search sentence according to the partial sentences except the positions to be filled in the at least one other historical search sentence which meets the set conditions and the partial sentences except the positions to be filled in the historical search sentence.
6. The method according to claim 5, wherein, in the at least one other history search sentence satisfying the set condition, a sum value of the number of searches in the history of each other history search sentence is not less than the set number of searches.
7. The method according to claim 1, wherein the filling the to-be-filled location according to the at least one filling information to obtain a guide statement specifically includes:
filling the position to be filled according to the at least one piece of filling information to obtain at least one candidate guide statement;
for each candidate guide statement, determining feature information corresponding to the candidate guide statement according to template information corresponding to the candidate guide statement, related information of the candidate guide statement and the service related information, wherein the template information comprises: at least one of a template identifier of a target guide statement template corresponding to the candidate guide statement, a search information type corresponding to a position to be filled in the target guide statement template corresponding to the candidate guide statement, and a service tag of the target guide statement template corresponding to the candidate guide statement, where relevant information of the candidate guide statement includes: at least one of the length of the candidate guide statement and filling information in a position to be filled in the candidate guide statement;
inputting the characteristic information corresponding to the candidate guide statement into a pre-trained second prediction model to obtain the correlation degree between the candidate guide statement and the user as the correlation degree corresponding to the candidate guide statement;
and determining the guide sentences displayed for the user according to the corresponding correlation degree of each candidate guide sentence.
8. The method of claim 2, wherein training the first predictive model comprises:
for each service label, taking a historical search statement which is historically related to the service label as a first historical search statement, and constructing a positive sample according to service related information corresponding to a user which historically sends the first historical search statement;
taking a historical search statement which is not related to the service tag historically as a second historical search statement, determining users who send the historical search statement related to the service tag historically less than a set number of times among users who send the second historical search statement as target users, and constructing a negative sample according to service related information corresponding to the target users;
and training the first prediction model according to the positive samples and the negative samples.
9. The method of claim 7, wherein training the second predictive model comprises:
acquiring historical guide sentences historically recommended to each user;
for each historical guide statement, determining whether each user sends an execution result of voice search information after looking up the historical guide statement historically according to the historical behavior record of each user, wherein the execution result is used as the corresponding annotation information of the historical guide statement;
inputting the characteristic information corresponding to the historical guide statement into a second prediction model to obtain a prediction result corresponding to the historical guide statement, wherein the prediction result indicates whether a user sends voice search information after checking the historical guide statement;
and training the second prediction model by taking the minimized deviation between the prediction result and the labeled information as an optimization target.
10. An apparatus for service execution, comprising:
an obtaining module, configured to respond to a current service request of a user, and obtain service-related information corresponding to the user, where the service-related information includes: at least one of user information of the user, a current geographic position of the user, current corresponding time information of the user and historical behavior records of the user;
a first determining module, configured to determine, according to the service-related information, a service tag related to the user;
a second determining module, configured to determine, from pre-constructed business guide statement templates, a business guide statement template that matches a business label related to the user, as a target guide statement template, and determine at least one piece of filling information corresponding to the target guide statement template according to a search information type corresponding to a position to be filled in the target guide statement template and the determined business word set corresponding to the user;
and the display module is used for filling the position to be filled according to the at least one piece of filling information to obtain a guide statement and displaying the guide statement to the user so that the user performs service execution according to the guide statement.
11. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 9.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 9 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110239446.XA CN113010640B (en) | 2021-03-04 | 2021-03-04 | Service execution method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110239446.XA CN113010640B (en) | 2021-03-04 | 2021-03-04 | Service execution method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113010640A true CN113010640A (en) | 2021-06-22 |
| CN113010640B CN113010640B (en) | 2022-07-15 |
Family
ID=76405018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110239446.XA Active CN113010640B (en) | 2021-03-04 | 2021-03-04 | Service execution method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113010640B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114611497A (en) * | 2022-05-10 | 2022-06-10 | 北京世纪好未来教育科技有限公司 | Training method of language diagnosis model, language diagnosis method, device and equipment |
| CN115545002A (en) * | 2022-11-29 | 2022-12-30 | 支付宝(杭州)信息技术有限公司 | Method, device, storage medium and equipment for model training and business processing |
| CN117033801A (en) * | 2023-10-08 | 2023-11-10 | 太平金融科技服务（上海）有限公司 | Service recommendation method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140351682A1 (en) * | 2003-12-12 | 2014-11-27 | Knapp Investment Company Limited | Dynamic generation of target files from template files and tracking of the processing of target files |
| CN109325097A (en) * | 2018-07-13 | 2019-02-12 | 海信集团有限公司 | A kind of voice guide method and device, electronic equipment, storage medium |
| CN110717536A (en) * | 2019-09-30 | 2020-01-21 | 北京三快在线科技有限公司 | Method and device for generating training sample |
| CN111368049A (en) * | 2020-02-26 | 2020-07-03 | 京东方科技集团股份有限公司 | Information acquisition method and device, electronic equipment and computer readable storage medium |
| CN111782947A (en) * | 2020-06-29 | 2020-10-16 | 北京达佳互联信息技术有限公司 | Search content display method and device, electronic equipment and storage medium |
-
2021
- 2021-03-04 CN CN202110239446.XA patent/CN113010640B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140351682A1 (en) * | 2003-12-12 | 2014-11-27 | Knapp Investment Company Limited | Dynamic generation of target files from template files and tracking of the processing of target files |
| CN109325097A (en) * | 2018-07-13 | 2019-02-12 | 海信集团有限公司 | A kind of voice guide method and device, electronic equipment, storage medium |
| CN110717536A (en) * | 2019-09-30 | 2020-01-21 | 北京三快在线科技有限公司 | Method and device for generating training sample |
| CN111368049A (en) * | 2020-02-26 | 2020-07-03 | 京东方科技集团股份有限公司 | Information acquisition method and device, electronic equipment and computer readable storage medium |
| CN111782947A (en) * | 2020-06-29 | 2020-10-16 | 北京达佳互联信息技术有限公司 | Search content display method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| HEIKO LUDWIG ET AL.: "Template-Based Automated Service Provisioning–Supporting the Agreement-Driven Service Life-Cycle", 《ICSOC：INTERNATIONAL CONFERENCE ON SERVICE-ORIENTED COMPUTING》 * |
| 陈宏希等: "基于Jess的银行大厅自助引导服务系统设计开发", 《自动化与仪器仪表》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114611497A (en) * | 2022-05-10 | 2022-06-10 | 北京世纪好未来教育科技有限公司 | Training method of language diagnosis model, language diagnosis method, device and equipment |
| CN114611497B (en) * | 2022-05-10 | 2022-08-16 | 北京世纪好未来教育科技有限公司 | Training method of language diagnosis model, language diagnosis method, device and equipment |
| CN115545002A (en) * | 2022-11-29 | 2022-12-30 | 支付宝(杭州)信息技术有限公司 | Method, device, storage medium and equipment for model training and business processing |
| CN115545002B (en) * | 2022-11-29 | 2023-03-31 | 支付宝(杭州)信息技术有限公司 | Model training and business processing method, device, storage medium and equipment |
| CN117033801A (en) * | 2023-10-08 | 2023-11-10 | 太平金融科技服务（上海）有限公司 | Service recommendation method, device, equipment and storage medium |
| CN117033801B (en) * | 2023-10-08 | 2023-12-22 | 太平金融科技服务（上海）有限公司 | Service recommendation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113010640B (en) | 2022-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113010640B (en) | Service execution method and device | |
| CN113837804A (en) | Information recommendation method, device and equipment | |
| CN111488426A (en) | Query intention determining method and device and processing equipment | |
| US11774264B2 (en) | Method and system for providing information to a user relating to a point-of-interest | |
| CN113688313A (en) | Training method of prediction model, information pushing method and device | |
| CN112733024A (en) | Information recommendation method and device | |
| CN113344098A (en) | Model training method and device | |
| CN113641896A (en) | Model training and recommendation probability prediction method and device | |
| JP2018504686A (en) | Method and apparatus for processing search data | |
| CN113343095A (en) | Model training and information recommendation method and device | |
| CN116737915B (en) | Semantic retrieval method, device, equipment and storage medium based on knowledge graph | |
| CN107577660B (en) | Category information identification method and device and server | |
| CN113641894A (en) | Information recommendation method and device | |
| CN112699307A (en) | Information generation method and device | |
| CN111639269A (en) | Site recommendation method and device | |
| CN113343132B (en) | Model training method, information display method and device | |
| CN116662657A (en) | Model training and information recommending method, device, storage medium and equipment | |
| CN113344078B (en) | Model training method and device | |
| CN114117028A (en) | Information recommendation method and device, storage medium and electronic equipment | |
| CN114116816A (en) | Recommendation method and device | |
| CN114861043A (en) | Model training and recommended position determining method and device | |
| CN114331602A (en) | Model training method based on transfer learning, information recommendation method and device | |
| CN113407689A (en) | Method and device for model training and business execution | |
| CN112905913A (en) | Public opinion display method, device and equipment | |
| CN112613320A (en) | Method and device for acquiring similar sentences, storage medium and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |