CN111310445B - Method and device for generating file information of online service entity - Google Patents

Method and device for generating file information of online service entity Download PDF

Info

Publication number
CN111310445B
CN111310445B CN202010087233.5A CN202010087233A CN111310445B CN 111310445 B CN111310445 B CN 111310445B CN 202010087233 A CN202010087233 A CN 202010087233A CN 111310445 B CN111310445 B CN 111310445B
Authority
CN
China
Prior art keywords
information
online service
evaluation
service entity
participles
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
Application number
CN202010087233.5A
Other languages
Chinese (zh)
Other versions
CN111310445A (en
Inventor
殷晓明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Koubei Shanghai Information Technology Co Ltd
Original Assignee
Koubei Shanghai Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Koubei Shanghai Information Technology Co Ltd filed Critical Koubei Shanghai Information Technology Co Ltd
Priority to CN202010087233.5A priority Critical patent/CN111310445B/en
Publication of CN111310445A publication Critical patent/CN111310445A/en
Application granted granted Critical
Publication of CN111310445B publication Critical patent/CN111310445B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a method and a device for generating file and case information of an online service entity, wherein the method comprises the following steps: acquiring description information of a plurality of preset dimensions of an online service entity to be displayed; extracting key participles from the description information of each dimension, inquiring the key participles in the established dictionary, and constructing the description vector of the online service entity to be displayed according to the inquiry result; and inputting the description vector into a trained pattern prediction model, and generating the pattern information of the online service entity to be displayed according to the pattern vector output by the pattern prediction model. According to the scheme, the description vector is constructed according to the description information of the online service object to be displayed, the file information of the service object to be displayed is generated, and the file information can be rapidly and accurately generated and displayed.

Description

Method and device for generating file information of online service entity
Technical Field
The invention relates to the technical field of internet, in particular to a method and a device for generating file information of an online service entity.
Background
In recent years, with the development of internet technology, it has become more common to rely on online platforms to meet daily needs, such as shopping using shopping platforms, ordering using local life applications, reservation services, and the like. At the same time, these platforms distinguish the entity characteristics of different entities by assigning corresponding tags to the entities on the platforms.
In the prior art, a feature with a certain dimension is usually selected as a label of an entity, for example, a user evaluation feature is selected as a label of a store, which can distinguish entity features of different entities to some extent, but the label is too single, and especially for some entities with more feature dimensions, the feature of the entity cannot be fully embodied at all.
Disclosure of Invention
In view of the above problems, embodiments of the present invention are provided to provide a method and an apparatus for generating pattern information of an online service entity, which overcome or at least partially solve the above problems.
According to an aspect of the embodiments of the present invention, a method for generating document information of an online service entity is provided, including:
acquiring description information of a plurality of preset dimensions of an online service entity to be displayed;
extracting key participles from the description information of each dimension, inquiring the key participles in the established dictionary, and constructing the description vector of the online service entity to be displayed according to the inquiry result;
and inputting the description vector into a trained pattern prediction model, and generating the pattern information of the online service entity to be displayed according to the pattern vector output by the pattern prediction model.
Optionally, the dictionary is established by the following steps:
acquiring description information of a plurality of preset dimensions of a plurality of online service entities;
counting a plurality of words and word frequencies thereof contained in the description information of a plurality of preset dimensions of the plurality of online service entities;
and sequencing the words according to the sequence of the word frequencies of the words from high to low, and establishing a dictionary containing the words and sequencing numbers thereof according to a sequencing result.
Optionally, the querying the keyword in the established dictionary, and constructing the description vector of the online service entity according to the query result further includes:
and inquiring the key participles in the dictionary, and constructing the description vector of the online service entity according to the sequence numbers of the key participles in the dictionary.
Optionally, the multiple preset dimensions include an evaluation information dimension, and the method further includes:
acquiring description information of evaluation information dimensions of a plurality of online service entities, and performing word segmentation processing on the description information of the evaluation information dimensions of the plurality of online service entities; filtering the stop words in the obtained multiple participles, and determining multiple evaluation participles according to the filtering result;
counting the occurrence frequency of a plurality of evaluation word segments in the description information of the evaluation information dimensionality of the plurality of online service entities;
selecting a preset number of candidate participles from the plurality of evaluation participles according to the sequence of the occurrence frequency from high to low, and forming an evaluation hot word candidate set;
the extracting key word segmentation from the description information of each dimension further comprises:
and splitting a plurality of evaluation participles to be selected from the description information of the evaluation information dimension of the online service entity to be displayed, matching the plurality of evaluation participles to be selected with the candidate participles in the evaluation hot word candidate set, and screening out key participles from the plurality of evaluation participles to be selected according to the matching result.
Optionally, the plurality of preset dimensions include an entry store information dimension;
the collecting the description information of a plurality of preset dimensions of the online service entity to be displayed further comprises:
matching an entrance shop of the online service entity to be displayed with a brand shop base, and if the entrance shop is contained in the brand shop base, acquiring brand information of the entrance shop; and if the entrance shop is not contained in the brand shop base, acquiring the identification information and the geographic position information of the entrance shop.
Optionally, the preset dimensions include an entity attribute information dimension;
the collecting the description information of a plurality of preset dimensions of the online service entity to be displayed further comprises:
acquiring the working time information, training lead information, role information and/or certificate information of the online service entity to be displayed.
Optionally, the preset dimensions further include an activity information dimension.
Optionally, the pattern prediction model is obtained by training through the following steps:
determining a plurality of online service entity samples; obtaining a plurality of description information samples with preset dimensionalities of each online service entity sample, extracting key word segmentation samples from the description information samples with the dimensionalities, inquiring the key word segmentation samples in an established dictionary, constructing description vector samples of the online service entity samples according to inquiry results, and taking the description vector samples as training input data;
performing word segmentation on the configured case information of each online service entity sample to obtain a plurality of case word segmentation samples, inquiring the plurality of case word segmentation samples in the established dictionary, constructing case vector samples of the online service entity samples according to the inquiry result, and taking the case vector samples as training output data;
and training a neural network model by using the training input data and the training output data, and obtaining a pattern prediction model according to a training result.
According to another aspect of the embodiments of the present invention, there is provided an apparatus for generating document information of an online service entity, including:
the acquisition module is suitable for acquiring the description information of a plurality of preset dimensions of the online service entity to be displayed;
the construction module is suitable for extracting key participles from the description information of each dimension, inquiring the key participles in the established dictionary, and constructing the description vector of the online service entity to be displayed according to the inquiry result;
and the generation module is suitable for inputting the description vector into a trained case prediction model and generating the case information of the online service entity to be displayed according to the case vector output by the case prediction model.
Optionally, the apparatus further comprises:
a dictionary establishment module adapted to: acquiring description information of a plurality of preset dimensions of a plurality of online service entities; counting a plurality of words and word frequencies thereof contained in the description information of a plurality of preset dimensions of the plurality of online service entities; and sequencing the words according to the sequence of the word frequencies of the words from high to low, and establishing a dictionary containing the words and sequencing numbers thereof according to a sequencing result.
Optionally, the building module is further adapted to:
and inquiring the key participles in the dictionary, and constructing the description vector of the online service entity according to the sequence numbers of the key participles in the dictionary.
Optionally, the multiple preset dimensions include an evaluation information dimension, and the apparatus further includes:
the evaluation hot word screening module is suitable for acquiring the description information of the evaluation information dimensions of a plurality of online service entities and performing word segmentation processing on the description information of the evaluation information dimensions of the plurality of online service entities; filtering the stop words in the obtained multiple participles, and determining multiple evaluation participles according to the filtering result; counting the occurrence frequency of a plurality of evaluation word segments in the description information of the evaluation information dimensionality of the plurality of online service entities; selecting a preset number of candidate participles from the plurality of evaluation participles according to the sequence of the occurrence frequency from high to low, and forming an evaluation hot word candidate set;
the building module is further adapted to:
and splitting a plurality of evaluation participles to be selected from the description information of the evaluation information dimension of the online service entity to be displayed, matching the plurality of evaluation participles to be selected with the candidate participles in the evaluation hot word candidate set, and screening out key participles from the plurality of evaluation participles to be selected according to the matching result.
Optionally, the plurality of preset dimensions include an entry store information dimension;
the acquisition module is further adapted to:
matching an entrance shop of the online service entity to be displayed with a brand shop base, and if the entrance shop is contained in the brand shop base, acquiring brand information of the entrance shop; and if the entrance shop is not contained in the brand shop base, acquiring the identification information and the geographic position information of the entrance shop.
Optionally, the preset dimensions include an entity attribute information dimension;
the acquisition module is further adapted to: acquiring the working time information, training lead information, role information and/or certificate information of the online service entity to be displayed.
Optionally, the preset dimensions further include an activity information dimension.
Optionally, the apparatus further comprises: a training module adapted to determine a plurality of online service entity samples; obtaining a plurality of description information samples with preset dimensionalities of each online service entity sample, extracting key word segmentation samples from the description information samples with the dimensionalities, inquiring the key word segmentation samples in an established dictionary, constructing description vector samples of the online service entity samples according to inquiry results, and taking the description vector samples as training input data;
performing word segmentation on the configured case information of each online service entity sample to obtain a plurality of case word segmentation samples, inquiring the plurality of case word segmentation samples in the established dictionary, constructing case vector samples of the online service entity samples according to the inquiry result, and taking the case vector samples as training output data;
and training a neural network model by using the training input data and the training output data, and obtaining a pattern prediction model according to a training result.
According to still another aspect of an embodiment of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the file information generation method of the online service entity.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium, in which at least one executable instruction is stored, and the executable instruction causes a processor to perform operations corresponding to the above method for generating document information of an online service entity.
According to the method and the device for generating the file information of the online service entity, provided by the embodiment of the invention, the key participles are extracted from the description information of a plurality of preset dimensions and a description vector is constructed by acquiring the description information of the plurality of preset dimensions of the online service entity to be displayed, and the element values of a plurality of elements in the description vector can represent the core characteristics of the plurality of preset dimensions of the online service entity to be displayed; then, the description vector is input into the pattern prediction model, so that a pattern vector can be obtained through prediction, pattern information is generated through the pattern vector, and the pattern information can comprehensively represent the scattered characteristics of a plurality of preset dimensions in the input description vector. Therefore, according to the scheme of the embodiment, the reasonable file information can be generated by the characteristics of the plurality of preset dimensions of the online service entity to be displayed, and the file information can logically and hierarchically reflect the comprehensive characteristics of the online service entity to be displayed.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the embodiments of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the embodiments of the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a method for generating document information of an online service entity according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a document information generating method of an online service entity according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram illustrating a document information generating apparatus of an online service entity according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computing device provided in an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flowchart of a method for generating document information of an online service entity according to an embodiment of the present invention. The method for generating the document information of the online service entity provided by the embodiment can be applied to service platforms of various industries, for example, a local life service platform, an online e-commerce platform, a take-out platform, and the like. The method for generating the document information of the online service entity provided by the embodiment may be executed by a computing device with corresponding computing capability, and the embodiment does not limit the specific type of the computing device.
As shown in fig. 1, the method comprises the steps of:
step S110: the method comprises the steps of collecting description information of a plurality of preset dimensions of an online service entity to be displayed.
The online service entity refers to an entity providing services, for example, a stylist providing a styling design; and the online service entity to be displayed refers to the online service entity which needs to be displayed in the list.
Specifically, for each online service entity, collecting description information from a plurality of preset dimensions, where the plurality of preset dimensions include any dimension that can reflect entity characteristics of the service entity, for example, the preset dimensions include a dimension that reflects an age of the service entity; correspondingly, the description information of each preset dimension refers to the entity characteristics of the dimension.
Step S120: extracting key participles from the description information of each dimension, inquiring the key participles in the established dictionary, and constructing the description vector of the online service entity to be displayed according to the inquiry result.
Specifically, key participles are extracted from the description information of each dimension, the key participles of each dimension are core words of the entity features of the dimension, the key participles are extracted from the description information of a plurality of preset dimensions, and a plurality of key participles corresponding to the plurality of preset dimensions are obtained, wherein each dimension has one or more key participles. Then, each key participle is inquired from a dictionary, a large number of hot words and the number of the hot words are recorded in the dictionary, and a description vector is constructed according to the number of each key participle in the dictionary.
Step S130: inputting the description vector into a trained case prediction model, and generating case information of the online service entity to be displayed according to the case vector output by the case prediction model.
The pattern prediction model can predict and obtain the pattern vector of the online service entity to be displayed according to the input description vector.
Specifically, the description vector is input into the case prediction model, and the case vector can be obtained through prediction, wherein each element in the case vector represents a participle forming the case information, and the case information can be obtained by restoring the element values of a plurality of elements in the case vector to the participle.
According to the method for generating the language and pattern information of the online service entity provided by the embodiment, by acquiring the description information of a plurality of preset dimensions of the online service entity to be displayed, extracting key participles from the description information of the plurality of preset dimensions and constructing a description vector, wherein element values of a plurality of elements in the description vector can represent core features of the plurality of preset dimensions of the online service entity to be displayed; then, the description vector is input into the pattern prediction model, so that a pattern vector can be obtained through prediction, pattern information is generated through the pattern vector, and the pattern information can comprehensively represent the scattered characteristics of a plurality of preset dimensions in the input description vector. Therefore, according to the scheme of the embodiment, the reasonable file information can be generated by the characteristics of the plurality of preset dimensions of the online service entity to be displayed, and the file information can logically and hierarchically reflect the comprehensive characteristics of the online service entity to be displayed.
Fig. 2 is a flowchart illustrating a document information generating method of an online service entity according to another embodiment of the present invention. The method for generating the pattern information of the online service entity provided in this embodiment is directed to further optimization of the method for generating the pattern information of the online service entity in the embodiment. As shown in fig. 2, the method comprises the steps of:
step S210: establishing a dictionary and constructing a pattern prediction model.
In this embodiment, the dictionary may be used to translate between word segmentation and encoding, including translating words into element values of corresponding elements in the vector, and translating element values of corresponding elements in the vector into words. Specifically, the process of creating the dictionary is as follows:
acquiring description information of a plurality of preset dimensions of a plurality of online service entities, wherein the plurality of online service entities can be all online service entities on a platform; the method comprises the steps of counting a plurality of words and word frequencies contained in the description information of a plurality of preset dimensions of a plurality of online service entities, and obtaining a large amount of statistical information of the words possibly appearing in the description information and the case information by counting the words and word frequencies contained in the description information of the plurality of preset dimensions of a large number of online service entities. The words are sequenced according to the sequence of the word frequencies of the words from high to low, a dictionary comprising the words and sequencing numbers of the words is established according to the sequencing result, wherein the words are sequentially numbered according to the sequence of the sequencing result from front to back, so that each word has a unique sequencing number, and the words can be represented by the sequencing numbers, and table 1 shows the dictionary content in a specific example:
Figure BDA0002382482390000081
Figure BDA0002382482390000091
in table 1, numbering is started from 1, and the sequence numbers 1,2,3,4 … … n can be obtained according to the sequence result, wherein each sequence number corresponds to a word.
In this embodiment, the pattern prediction model is used to obtain a pattern vector according to the input description vector. Specifically, the process of constructing the pattern prediction model is as follows:
determining a plurality of online service entity samples, wherein the plurality of online service entity samples are samples configured with pattern information, so as to train a pattern prediction model by using the existing description information samples and pattern information samples of the plurality of online service entities; obtaining a plurality of description information samples with preset dimensionalities of each online service entity sample, extracting key participle samples from the description information samples with the dimensionalities, inquiring the key participle samples in an established dictionary, constructing description vector samples of the online service entity samples according to inquiry results, and taking the description vector samples as training input data; and performing word segmentation processing on the configured case information of each online service entity sample to obtain a plurality of case word segmentation samples, wherein the character length of the configured case information is within a preset length range, so that the case information within the preset length range is generated by using the trained case prediction model, and the case information is favorably displayed. And querying the plurality of pattern segmentation samples in the established dictionary, constructing pattern vector samples of the online service entity samples according to query results, and taking the pattern vector samples as training output data, wherein the pattern vector samples are formed by a plurality of sequencing numbers of the plurality of pattern segmentation samples in the dictionary, and the sequence of the plurality of sequencing numbers in the pattern vector is the same as the sequence of the plurality of pattern segmentation samples contained in the pattern information samples. Training the neural network model by using the training input data and the training output data, obtaining a pattern prediction model according to a training result, and taking the model parameter at the moment as the model parameter of the final pattern prediction model until the error between the pattern vector output by training and the pattern vector sample meets the error condition, thereby obtaining the pattern prediction model. In the embodiment of the present invention, the specific model type of the prediction model is not limited, and alternatively, the pattern prediction model may be a seq2seq model (sequence-to-sequence model).
Step S220: the method comprises the steps of collecting description information of a plurality of preset dimensions of an online service entity to be displayed.
The preset dimensions comprise any dimension capable of reflecting entity characteristics of the service entity. Optionally, the plurality of preset dimensions include an entity attribute information dimension, an evaluation information dimension, an entrance shop information dimension, and/or an activity information dimension, where the entity attribute information dimension may reflect attribute characteristics of the entity, for example, the working age, education (or training) experience of the entity; the evaluation information dimension can reflect evaluation characteristics obtained by the entity, such as exquisite handedness, good service attitude, and the like; the inbound store information dimension may reflect store characteristics of the entity's store, such as store location, name, and/or brand, etc.; and, the activity information dimension may reflect the contest characteristics of the entity, such as the name of the contest, the ranking of the contest, etc.
In this embodiment, the process of collecting the description information is respectively explained by the above listed multiple preset dimensions:
first, entity attribute information dimensions. When the description information of the dimension is collected, the working time information, training lead information, role information and/or certificate information of the online service entity to be displayed are collected. The online platform can receive the configuration of the description information of the dimension through a configuration page which provides the description information of the dimension of the entity attribute information.
Second, information dimensions are evaluated. When the description information of the dimension is collected, the evaluation information of the online service entity to be displayed as an evaluation object in the platform is obtained, and the evaluation information is a plurality of comments. The platform may associate each piece of evaluation information with a service entity, and specifically may associate the piece of evaluation information with the service entity to which the evaluation entry points according to the evaluation entry of the evaluation information, for example, the platform is provided with a plurality of evaluation entries of a plurality of service entities, and when evaluation is triggered through a certain evaluation entry, the evaluation information input after entering the certain evaluation entry is determined as the evaluation information associated with the service entity to which the evaluation entry points; alternatively, the evaluation information may be associated with a service entity corresponding to an entity identifier carried in the evaluation information, where the entity identifier is selected or input by a user when inputting the evaluation information, for example, the user evaluates in a store, selects to evaluate the service entity a when inputting a comment, or indicates that the evaluation object is the service entity a in the comment, and then associates the comment with the service entity a. Then, when acquiring the evaluation information of the online service entity to be displayed, acquiring the evaluation information associated with the online service entity to be displayed.
And thirdly, information dimension of the entrance shop. When the description information of the dimension is collected, matching the in-store shop of the online service entity to be displayed with a brand shop base, wherein the brand shop is screened out from a plurality of shops in the platform according to the number of branch shops and/or the distribution range of the branch shops, the brand shop base is formed, and the shop with the number of the branch shops exceeding the preset number and/or the distribution range of the branch shops exceeding the preset geographical range is determined as the brand shop; if the entrance shop is contained in the brand shop base, collecting brand information of the entrance shop, and representing the entity characteristics by the brand information of the shop so that the entity characteristics of the information dimension of the entrance shop are more representative; and if the entrance shop is not contained in the brand shop base, acquiring the identification information and the geographic position information of the entrance shop, and representing the entity characteristics by the identification information and the geographic position information of the shop.
And fourthly, activity information dimension. When the description information of the dimension is collected, name information of activities which are historically participated in, are participated in and/or are about to participate in by the online service entity to be shown is collected.
It should be noted that, in the embodiments of the present invention, the preset dimensions listed above are not limited, and in some other embodiments, a person skilled in the art may also flexibly increase or decrease the preset dimensions.
Step S230: extracting key participles from the description information of each dimension, inquiring the key participles in the established dictionary, and constructing the description vector of the online service entity to be displayed according to the inquiry result.
After the description information of a plurality of preset dimensions is collected, extracting key participles from the description information of each dimension to serve as key information of entity features of the dimension; then, by querying the dictionary, a description vector composed of the sequence numbers of the key information of a plurality of preset dimensions is constructed for predicting the pattern vector.
Specifically, the key participles are extracted for the description information of each dimension, wherein the number upper limit of the key participles of each dimension may be set to control the length of the description vector, the same number upper limit may be set for different dimensions, or different number upper limits may be set for different dimensions according to the size of the influence degree of the entity features of each dimension on the case information, in general, the size of the influence degree of the entity features of each dimension on the case information is in direct proportion to the number upper limit of the key participles of each dimension, for example, the influence degree of the entity features of the entity attribute information dimension on the case information is greater than the size of the influence degree of the entity features of the activity information dimension on the case information, and then a higher number upper limit of the key participles is assigned to the entity attribute dimension.
Further, for the plurality of preset dimensions mentioned in step S220, the process of extracting key participles from the description information is as follows:
first, entity attribute information dimensions. When extracting key participles from the practitioner time information, training development information, role information and/or certificate information of the dimension, key participles including the practitioner time length, training development, title and/or awarding certificate name may be extracted, for example, the extracted key participles of the entity attribute information dimension include "10 years of practitioner", "AAA hair style design institute", "hair style design director", "hair style design house medal".
Second, information dimensions are evaluated. Before extracting key word segmentation from the evaluation information of the dimension, constructing an evaluation hot word candidate set: acquiring description information of evaluation information dimensions of a plurality of online service entities (the description information at the moment is evaluation information), wherein the plurality of online service entities can be all online service entities on a platform, and the accuracy of evaluating hot word candidates and evaluating hot words in a centralized manner by enlarging the acquisition range; the ratings less than the preset number of words are filtered from the collected rating information to filter out low quality or default reviews. Performing word segmentation on the description information of the evaluation information dimensions of the online service entities, filtering stop words in the obtained multiple word segments, determining multiple evaluation word segments according to a filtering result, performing word segmentation on the filtered comment information by using a jieba word segmentation tool, and filtering the stop words based on a common stop word dictionary; and counting the occurrence frequency of the plurality of evaluation segmented words in the description information of the evaluation information dimensions of the plurality of online service entities, and for the embodiment of filtering processing of low-quality or default comments, counting the occurrence frequency of the plurality of evaluation segmented words in the remaining evaluation information after filtering, selecting a preset number of candidate segmented words from the plurality of evaluation segmented words according to the sequence of the occurrence frequencies from high to low and forming an evaluation hot word candidate set, for example, selecting 100 evaluation segmented words with the highest frequency to form the evaluation hot word candidate set. In the process of selecting the evaluation participles to form an evaluation hot word candidate set, the matching degree of each evaluation participle and a plurality of service entity evaluation dimensions can be calculated, whether the evaluation participle is a participle for evaluating the plurality of service entity evaluation dimensions is determined, if not, the evaluation participle is removed from the plurality of evaluation participles, wherein the plurality of service entity evaluation dimensions comprise a service entity adept style or field dimension, a service technology dimension of a service entity and/or a service attitude dimension of the service entity, and the remaining evaluation participles after removal processing are the participles for evaluating the style, field, technology and/or attitude of the service entity according to the occurrence frequency to form the evaluation hot word candidate set from the remaining evaluation participles.
After an evaluation hot word candidate set is constructed, a plurality of evaluation participles to be selected are split from the description information of the evaluation information dimension of the online service entity to be displayed, and low-quality or default comments can be filtered out and stop words can be filtered out in the same way as the process of constructing the evaluation hot word candidate set; matching the multiple candidate evaluation participles with candidate participles in an evaluation hot word candidate set, screening out key participles from the multiple candidate evaluation participles according to a matching result, aiming at any one candidate evaluation participle, and determining the candidate evaluation participle as a key participle with evaluation information dimensionality if the evaluation hot word candidate set contains the candidate evaluation participle; otherwise, the keyword is not determined. By the method, the quality and the quantity of the selected key word segmentation of the evaluation information dimensionality can be controlled simultaneously.
And thirdly, information dimension of the entrance shop. When key participles are extracted from the brand information, the identification information and/or the geographic position information of the dimensional in-store, if the in-store of the online service entity to be displayed is a brand store, the extracted key participles comprise brand names; if the shop where the online service entity to be displayed is located is a non-brand shop, the extracted key participle includes a shop name and a shop location.
And fourthly, activity information dimension. When extracting key participles from the description information of the dimension, the extracted key participles include the activity name and the participation tense (participated, participating or about to participate).
And after extracting the key participle of each dimension, inquiring the key participle in the dictionary, and constructing the description vector of the online service entity according to the sequence number of the key participle in the dictionary. The order of a plurality of preset dimensions can be set, and after a plurality of key participles corresponding to the preset dimensions are inquired in a dictionary, the sequence numbers of the key participles are sequentially used as the element values of each element in the description vector according to the order of the preset dimensions. The sequence of the plurality of preset dimensions is the same as the sequence of the plurality of preset dimensions in each description vector sample in training input data during training of the pattern prediction model, and the accuracy during prediction is improved by keeping the consistency of the input data during prediction and training.
Still taking the four preset dimensions mentioned in the foregoing as an example, the sequence of the key participles in the entity attribute information dimension, the evaluation information dimension, the store entering information dimension and the activity information dimension in the description vector is set to be from front to back, if the number of the key participles extracted in the four preset dimensions is 5,4,7 and 4 respectively, after the (5+4+7+4) key participles are queried in the dictionary, the ranking numbers of the 5 key participles in the entity attribute information dimension in the dictionary are used as the element values of the 1 st to 5 th elements of the description vector, the ranking numbers of the 4 key participles in the evaluation information dimension in the dictionary are used as the element values of the 6 th to 9 th elements of the description vector, and the ranking numbers of the 7 key participles in the store entering information dimension in the dictionary are used as the element values of the 10 th to 16 th elements of the description vector, and taking the sequencing number of the 4 key participles of the activity information dimension in the dictionary as the element value of the 17 th element to the 20 th element of the description vector, and further obtaining the description vector containing the 20 elements.
Step S240: inputting the description vector into a trained case prediction model, and generating case information of the online service entity to be displayed according to the case vector output by the case prediction model.
Specifically, the description vector is input into the case prediction model, and the case prediction model predicts and outputs a case vector, wherein each element in the case vector represents a participle forming the case information, and the element value of each element in the case vector is inquired in the sequence number of the dictionary, so that the participle corresponding to the element value can be determined, and the case information of the online service entity to be displayed can be generated.
According to the method for generating the language and pattern information of the online service entity provided by the embodiment, by acquiring the description information of a plurality of preset dimensions of the online service entity to be displayed, extracting key participles from the description information of the plurality of preset dimensions and constructing a description vector, wherein element values of a plurality of elements in the description vector can represent core features of the plurality of preset dimensions of the online service entity to be displayed; then, the description vector is input into the pattern prediction model, so that a pattern vector can be obtained through prediction, pattern information is generated through the pattern vector, and the pattern information can comprehensively represent the scattered characteristics of a plurality of preset dimensions in the input description vector. Therefore, according to the scheme of the embodiment, the reasonable file information can be generated by the characteristics of the plurality of preset dimensions of the online service entity to be displayed, and the file information can logically and hierarchically reflect the comprehensive characteristics of the online service entity to be displayed.
Fig. 3 is a schematic structural diagram illustrating a document information generating apparatus of an online service entity according to an embodiment of the present invention. As shown in fig. 3, the apparatus includes:
the acquisition module 310 is adapted to acquire description information of a plurality of preset dimensions of an online service entity to be displayed;
the construction module 320 is adapted to extract key participles from the description information of each dimension, query the key participles in the established dictionary, and construct the description vector of the online service entity to be displayed according to the query result;
the generating module 330 is adapted to input the description vector into the trained pattern prediction model, and generate the pattern information of the online service entity to be displayed according to the pattern vector output by the pattern prediction model.
In an optional manner, the apparatus further comprises:
a dictionary establishment module adapted to: acquiring description information of a plurality of preset dimensions of a plurality of online service entities; counting a plurality of words and word frequencies thereof contained in the description information of a plurality of preset dimensions of the plurality of online service entities; and sequencing the words according to the sequence of the word frequencies of the words from high to low, and establishing a dictionary containing the words and sequencing numbers thereof according to a sequencing result.
In an alternative form, the building module is further adapted to:
and inquiring the key participles in the dictionary, and constructing the description vector of the online service entity according to the sequence numbers of the key participles in the dictionary.
In an optional manner, the plurality of preset dimensions include an evaluation information dimension, and the apparatus further includes:
the evaluation hot word screening module is suitable for acquiring the description information of the evaluation information dimensions of a plurality of online service entities and performing word segmentation processing on the description information of the evaluation information dimensions of the plurality of online service entities; filtering the stop words in the obtained multiple participles, and determining multiple evaluation participles according to the filtering result; counting the occurrence frequency of a plurality of evaluation word segments in the description information of the evaluation information dimensionality of the plurality of online service entities; selecting a preset number of candidate participles from the plurality of evaluation participles according to the sequence of the occurrence frequency from high to low, and forming an evaluation hot word candidate set;
the building module is further adapted to:
and splitting a plurality of evaluation participles to be selected from the description information of the evaluation information dimension of the online service entity to be displayed, matching the plurality of evaluation participles to be selected with the candidate participles in the evaluation hot word candidate set, and screening out key participles from the plurality of evaluation participles to be selected according to the matching result.
In an alternative approach, the plurality of preset dimensions includes an inbound store information dimension;
the acquisition module is further adapted to:
matching an entrance shop of the online service entity to be displayed with a brand shop base, and if the entrance shop is contained in the brand shop base, acquiring brand information of the entrance shop; and if the entrance shop is not contained in the brand shop base, acquiring the identification information and the geographic position information of the entrance shop.
In an optional manner, the plurality of preset dimensions include an entity attribute information dimension;
the acquisition module is further adapted to: acquiring the working time information, training lead information, role information and/or certificate information of the online service entity to be displayed.
In an optional manner, the plurality of preset dimensions further includes an activity information dimension.
In an optional manner, the apparatus further comprises: a training module adapted to determine a plurality of online service entity samples; obtaining a plurality of description information samples with preset dimensionalities of each online service entity sample, extracting key word segmentation samples from the description information samples with the dimensionalities, inquiring the key word segmentation samples in an established dictionary, constructing description vector samples of the online service entity samples according to inquiry results, and taking the description vector samples as training input data;
performing word segmentation on the configured case information of each online service entity sample to obtain a plurality of case word segmentation samples, inquiring the plurality of case word segmentation samples in the established dictionary, constructing case vector samples of the online service entity samples according to the inquiry result, and taking the case vector samples as training output data;
and training a neural network model by using the training input data and the training output data, and obtaining a pattern prediction model according to a training result.
The embodiment of the invention provides a nonvolatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the file information generation method of the online service entity in any method embodiment.
Fig. 4 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor (processor)402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically execute the relevant steps in the above-described embodiment of the method for generating the pattern information for the online service entity of the computing device.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may specifically be configured to cause the processor 402 to perform the following operations:
acquiring description information of a plurality of preset dimensions of an online service entity to be displayed;
extracting key participles from the description information of each dimension, inquiring the key participles in the established dictionary, and constructing the description vector of the online service entity to be displayed according to the inquiry result;
and inputting the description vector into a trained pattern prediction model, and generating the pattern information of the online service entity to be displayed according to the pattern vector output by the pattern prediction model.
In an alternative, the program 410 further causes the processor to:
acquiring description information of a plurality of preset dimensions of a plurality of online service entities;
counting a plurality of words and word frequencies thereof contained in the description information of a plurality of preset dimensions of the plurality of online service entities;
and sequencing the words according to the sequence of the word frequencies of the words from high to low, and establishing a dictionary containing the words and sequencing numbers thereof according to a sequencing result.
In an alternative, the program 410 further causes the processor to:
and inquiring the key participles in the dictionary, and constructing the description vector of the online service entity according to the sequence numbers of the key participles in the dictionary.
In an alternative approach, where the plurality of preset dimensions includes an evaluation information dimension, the program 410 further causes the processor to:
acquiring description information of evaluation information dimensions of a plurality of online service entities, and performing word segmentation processing on the description information of the evaluation information dimensions of the plurality of online service entities; filtering the stop words in the obtained multiple participles, and determining multiple evaluation participles according to the filtering result;
counting the occurrence frequency of a plurality of evaluation word segments in the description information of the evaluation information dimensionality of the plurality of online service entities;
selecting a preset number of candidate participles from the plurality of evaluation participles according to the sequence of the occurrence frequency from high to low, and forming an evaluation hot word candidate set;
and splitting a plurality of evaluation participles to be selected from the description information of the evaluation information dimension of the online service entity to be displayed, matching the plurality of evaluation participles to be selected with the candidate participles in the evaluation hot word candidate set, and screening out key participles from the plurality of evaluation participles to be selected according to the matching result.
In an alternative approach, the plurality of preset dimensions includes an inbound store information dimension; the program 410 further causes the processor to:
matching an entrance shop of the online service entity to be displayed with a brand shop base, and if the entrance shop is contained in the brand shop base, acquiring brand information of the entrance shop; and if the entrance shop is not contained in the brand shop base, acquiring the identification information and the geographic position information of the entrance shop.
In an optional manner, the plurality of preset dimensions include an entity attribute information dimension; the program 410 further causes the processor to:
acquiring the working time information, training lead information, role information and/or certificate information of the online service entity to be displayed.
In an optional manner, the plurality of preset dimensions further includes an activity information dimension.
In an alternative, the program 410 further causes the processor to:
determining a plurality of online service entity samples; obtaining a plurality of description information samples with preset dimensionalities of each online service entity sample, extracting key word segmentation samples from the description information samples with the dimensionalities, inquiring the key word segmentation samples in an established dictionary, constructing description vector samples of the online service entity samples according to inquiry results, and taking the description vector samples as training input data;
performing word segmentation on the configured case information of each online service entity sample to obtain a plurality of case word segmentation samples, inquiring the plurality of case word segmentation samples in the established dictionary, constructing case vector samples of the online service entity samples according to the inquiry result, and taking the case vector samples as training output data;
and training a neural network model by using the training input data and the training output data, and obtaining a pattern prediction model according to a training result.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of embodiments of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best modes of embodiments of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. Embodiments of the invention may also be implemented as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing embodiments of the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.

Claims (14)

1. A method for generating file information of an online service entity comprises the following steps:
acquiring description information of a plurality of preset dimensions of an online service entity to be displayed;
extracting key participles from the description information of each dimension, inquiring words corresponding to the key participles in an established dictionary, sequentially using sequence numbers of the words corresponding to the key participles in the dictionary as element values of each element in a description vector according to the sequence of a preset dimension, and constructing the description vector of the online service entity to be displayed; the dictionary is used for converting between words and sequencing numbers;
inputting the description vector into a trained case prediction model to obtain a case vector, wherein each element in the case vector represents a word segmentation forming case information; inquiring the element value of each element in the case vector in the sequence number of the dictionary, determining a word corresponding to the element value as a participle, and generating the case information of the online service entity to be displayed;
wherein the dictionary is established by the steps of:
acquiring description information of a plurality of preset dimensions of a plurality of online service entities;
counting a plurality of words and word frequencies thereof contained in the description information of a plurality of preset dimensions of the plurality of online service entities;
and sequencing the words according to the sequence of the word frequencies of the words from high to low, and establishing a dictionary containing the words and sequencing numbers thereof according to a sequencing result.
2. The method of claim 1, wherein the plurality of preset dimensions includes an evaluation information dimension, the method further comprising:
acquiring description information of evaluation information dimensions of a plurality of online service entities, and performing word segmentation processing on the description information of the evaluation information dimensions of the plurality of online service entities; filtering the stop words in the obtained multiple participles, and determining multiple evaluation participles according to the filtering result;
counting the occurrence frequency of a plurality of evaluation word segments in the description information of the evaluation information dimensionality of the plurality of online service entities;
selecting a preset number of candidate participles from the plurality of evaluation participles according to the sequence of the occurrence frequency from high to low, and forming an evaluation hot word candidate set;
the extracting key word segmentation from the description information of each dimension further comprises:
and splitting a plurality of evaluation participles to be selected from the description information of the evaluation information dimension of the online service entity to be displayed, matching the plurality of evaluation participles to be selected with the candidate participles in the evaluation hot word candidate set, and screening out key participles from the plurality of evaluation participles to be selected according to the matching result.
3. The method of claim 1, wherein the plurality of preset dimensions includes an entry store information dimension;
the collecting the description information of a plurality of preset dimensions of the online service entity to be displayed further comprises:
matching an entrance shop of the online service entity to be displayed with a brand shop base, and if the entrance shop is contained in the brand shop base, acquiring brand information of the entrance shop; and if the entrance shop is not contained in the brand shop base, acquiring the identification information and the geographic position information of the entrance shop.
4. The method of claim 1, wherein the plurality of preset dimensions include an entity attribute information dimension;
the collecting the description information of a plurality of preset dimensions of the online service entity to be displayed further comprises:
acquiring the working time information, training lead information, role information and/or certificate information of the online service entity to be displayed.
5. The method of claim 1, wherein the plurality of preset dimensions further comprises an activity information dimension.
6. The method of any of claims 1-5, wherein the pattern prediction model is trained by:
determining a plurality of online service entity samples; obtaining a plurality of description information samples with preset dimensionalities of each online service entity sample, extracting key participle samples from the description information samples with the dimensionalities, inquiring words corresponding to the key participle samples in an established dictionary, constructing description vector samples of the online service entity samples according to inquiry results, and taking the description vector samples as training input data;
performing word segmentation on the configured case information of each online service entity sample to obtain a plurality of case word segmentation samples, inquiring words corresponding to the case word segmentation samples in an established dictionary, constructing case vector samples of the online service entity samples according to the inquiry result, and taking the case vector samples as training output data;
and training a neural network model by using the training input data and the training output data, and obtaining a pattern prediction model according to a training result.
7. A document information generating apparatus of an online service entity, comprising:
the acquisition module is suitable for acquiring the description information of a plurality of preset dimensions of the online service entity to be displayed;
the construction module is suitable for extracting key participles from the description information of each dimension, searching words corresponding to the key participles in an established dictionary, sequentially using sequence numbers of the words corresponding to the key participles in the dictionary as element values of each element in a description vector according to the sequence of a preset dimension, and constructing the description vector of the online service entity to be displayed; the dictionary is used for converting between words and sequencing numbers;
the generating module is suitable for inputting the description vector into a trained case prediction model to obtain a case vector, and each element in the case vector represents a word segmentation forming case information; inquiring the element value of each element in the case vector in the sequence number of the dictionary, determining a word corresponding to the element value as a participle, and generating the case information of the online service entity to be displayed;
wherein the apparatus further comprises:
a dictionary establishment module adapted to: acquiring description information of a plurality of preset dimensions of a plurality of online service entities; counting a plurality of words and word frequencies thereof contained in the description information of a plurality of preset dimensions of the plurality of online service entities; and sequencing the words according to the sequence of the word frequencies of the words from high to low, and establishing a dictionary containing the words and sequencing numbers thereof according to a sequencing result.
8. The apparatus of claim 7, wherein the plurality of preset dimensions include an evaluation information dimension, the apparatus further comprising:
the evaluation hot word screening module is suitable for acquiring the description information of the evaluation information dimensions of a plurality of online service entities and performing word segmentation processing on the description information of the evaluation information dimensions of the plurality of online service entities; filtering the stop words in the obtained multiple participles, and determining multiple evaluation participles according to the filtering result; counting the occurrence frequency of a plurality of evaluation word segments in the description information of the evaluation information dimensionality of the plurality of online service entities; selecting a preset number of candidate participles from the plurality of evaluation participles according to the sequence of the occurrence frequency from high to low, and forming an evaluation hot word candidate set;
the building module is further adapted to:
and splitting a plurality of evaluation participles to be selected from the description information of the evaluation information dimension of the online service entity to be displayed, matching the plurality of evaluation participles to be selected with the candidate participles in the evaluation hot word candidate set, and screening out key participles from the plurality of evaluation participles to be selected according to the matching result.
9. The apparatus of claim 7, wherein the plurality of preset dimensions includes an entry store information dimension;
the acquisition module is further adapted to:
matching an entrance shop of the online service entity to be displayed with a brand shop base, and if the entrance shop is contained in the brand shop base, acquiring brand information of the entrance shop; and if the entrance shop is not contained in the brand shop base, acquiring the identification information and the geographic position information of the entrance shop.
10. The apparatus of claim 7, wherein the plurality of preset dimensions include an entity attribute information dimension;
the acquisition module is further adapted to: acquiring the working time information, training lead information, role information and/or certificate information of the online service entity to be displayed.
11. The apparatus of claim 7, wherein the plurality of preset dimensions further comprises an activity information dimension.
12. The apparatus of any of claims 7-11, wherein the apparatus further comprises: a training module adapted to determine a plurality of online service entity samples; obtaining a plurality of description information samples with preset dimensionalities of each online service entity sample, extracting key participle samples from the description information samples with the dimensionalities, inquiring words corresponding to the key participle samples in an established dictionary, constructing description vector samples of the online service entity samples according to inquiry results, and taking the description vector samples as training input data;
performing word segmentation on the configured case information of each online service entity sample to obtain a plurality of case word segmentation samples, inquiring words corresponding to the case word segmentation samples in an established dictionary, constructing case vector samples of the online service entity samples according to the inquiry result, and taking the case vector samples as training output data;
and training a neural network model by using the training input data and the training output data, and obtaining a pattern prediction model according to a training result.
13. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the file information generation method of the online service entity in any one of claims 1-6.
14. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the method for generating the pattern information of the online service entity according to any one of claims 1 to 6.
CN202010087233.5A 2020-02-11 2020-02-11 Method and device for generating file information of online service entity Active CN111310445B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010087233.5A CN111310445B (en) 2020-02-11 2020-02-11 Method and device for generating file information of online service entity

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010087233.5A CN111310445B (en) 2020-02-11 2020-02-11 Method and device for generating file information of online service entity

Publications (2)

Publication Number Publication Date
CN111310445A CN111310445A (en) 2020-06-19
CN111310445B true CN111310445B (en) 2021-10-22

Family

ID=71161764

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010087233.5A Active CN111310445B (en) 2020-02-11 2020-02-11 Method and device for generating file information of online service entity

Country Status (1)

Country Link
CN (1) CN111310445B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104111933A (en) * 2013-04-17 2014-10-22 阿里巴巴集团控股有限公司 Method and device for acquiring business object label and building training model
CN110427617A (en) * 2019-07-22 2019-11-08 阿里巴巴集团控股有限公司 The generation method and device of pushed information
CN110555107A (en) * 2018-03-29 2019-12-10 阿里巴巴集团控股有限公司 method and device for determining business object theme and recommending business object

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109408163B (en) * 2018-09-07 2022-04-26 百度在线网络技术(北京)有限公司 Screen control method, device equipment and computer readable storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104111933A (en) * 2013-04-17 2014-10-22 阿里巴巴集团控股有限公司 Method and device for acquiring business object label and building training model
CN110555107A (en) * 2018-03-29 2019-12-10 阿里巴巴集团控股有限公司 method and device for determining business object theme and recommending business object
CN110427617A (en) * 2019-07-22 2019-11-08 阿里巴巴集团控股有限公司 The generation method and device of pushed information

Also Published As

Publication number Publication date
CN111310445A (en) 2020-06-19

Similar Documents

Publication Publication Date Title
CN107423613B (en) Method and device for determining device fingerprint according to similarity and server
KR101582108B1 (en) Document classification system, document classification method, and document classification program
CN112889042A (en) Identification and application of hyper-parameters in machine learning
CN108596695B (en) Entity pushing method and system
KR102063384B1 (en) Method for Registering Product Information by using Image
KR101491627B1 (en) Quantification method, apparatus and system of reviews for mobile application evaluation
CN109064265A (en) Purchase vehicle recommended method and system based on the network platform
CN111242318B (en) Service model training method and device based on heterogeneous feature library
CN110580489B (en) Data object classification system, method and equipment
CN110727857A (en) Method and device for identifying key features of potential users aiming at business objects
CN114238573A (en) Information pushing method and device based on text countermeasure sample
CN112669113A (en) Product recommendation method and device, storage medium and electronic device
CN113590678A (en) Portrait analysis method based on internet finance and big data analysis server
CN114579858A (en) Content recommendation method and device, electronic equipment and storage medium
CN116579351B (en) Analysis method and device for user evaluation information
CN110990701B (en) Book searching method, computing device and computer storage medium
CN111310445B (en) Method and device for generating file information of online service entity
CN109727056B (en) Financial institution recommendation method, device, storage medium and device
CN113543117A (en) Prediction method and device for number portability user and computing equipment
JPH11110409A (en) Method for classifying information and device therefor
CN113407849B (en) Coarse ordering method and device
JP2020004161A (en) Examination support apparatus, examination support method, and service providing method
KR102286661B1 (en) Chat based on-demand shopping curation apparatus
CN109446330B (en) Network service platform emotional tendency identification method, device, equipment and storage medium
CN111353803A (en) Advertiser classification method and device and computing 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